<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:googleplay="http://www.google.com/schemas/play-podcasts/1.0"><channel><title><![CDATA[Unexpected Correlations by Aperiodic]]></title><description><![CDATA[Research on order flow, liquidity and the cost of trading crypto and tokenized assets (stocks, indices, gold, oil, FX), with the code to rerun it. From the team behind aperiodic.io.]]></description><link>https://blog.aperiodic.io</link><image><url>https://substackcdn.com/image/fetch/$s_!IaFj!,w_256,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9d34ea24-a92a-4769-9c79-e4b6cc972e4c_520x520.png</url><title>Unexpected Correlations by Aperiodic</title><link>https://blog.aperiodic.io</link></image><generator>Substack</generator><lastBuildDate>Sat, 21 Nov 2026 20:56:45 GMT</lastBuildDate><atom:link href="https://blog.aperiodic.io/feed" rel="self" type="application/rss+xml"/><copyright><![CDATA[Aperiodic]]></copyright><language><![CDATA[en]]></language><webMaster><![CDATA[unexpectedcorrelations@substack.com]]></webMaster><itunes:owner><itunes:email><![CDATA[unexpectedcorrelations@substack.com]]></itunes:email><itunes:name><![CDATA[Mark Aron Szulyovszky]]></itunes:name></itunes:owner><itunes:author><![CDATA[Mark Aron Szulyovszky]]></itunes:author><googleplay:owner><![CDATA[unexpectedcorrelations@substack.com]]></googleplay:owner><googleplay:email><![CDATA[unexpectedcorrelations@substack.com]]></googleplay:email><googleplay:author><![CDATA[Mark Aron Szulyovszky]]></googleplay:author><itunes:block><![CDATA[Yes]]></itunes:block><item><title><![CDATA[We trained a model on 25+ stock perps, it shows strong asymmetric profitability outside traditional market hours.]]></title><description><![CDATA[A machine-learning study with the full method and code: using microstructure metrics, a walk-forward LightGBM model; eight months out of sample]]></description><link>https://blog.aperiodic.io/p/closed-market-stock-perps</link><guid isPermaLink="false">https://blog.aperiodic.io/p/closed-market-stock-perps</guid><dc:creator><![CDATA[Daniel Szemerey]]></dc:creator><pubDate>Thu, 19 Nov 2026 15:21:19 GMT</pubDate><enclosure url="https://substack-post-media.s3.amazonaws.com/public/images/9696ca8a-c0fc-437b-a7df-267601858d78_2560x1340.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p>You can trade Nvidia stock at 3am on a Sunday, through its perpetual future on Hyperliquid, while the underlying market on NASDAQ is closed. What does price discovery look like during the overnight session? What is driving price movements?</p><p>While Nasdaq is open, it anchors the price of these stocks, and arbitrageurs keep the perpetual futures in line. But nights, weekends and holidays add up to more than half the week. In those hours the perpetuals essentially run independent price discovery, influenced by the current market microstructure, potentially more than during peak liquidity.</p><p>We tested four simple signals, measuring how well each one predicts the next 15 minutes, segmenting into 2 different periods: while Nasdaq is open and then while it is closed. During regular hours, predictability is both low, but once Nasdaq closes, market microstructure metrics multiply their predictive power. We built a small model te demonstrate it: it made money out of sample when Nasdaq was closed and lost money when it was open, with the same features, fees and code.</p><p>Caveat: the edge is small and it is shrinking. It also needs fees under a basis point.</p><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><h2>I. Overnight price discovery</h2><p>trade.xyz is a stock-perp exchange built on Hyperliquid. It lists single names such as NVDA and TSLA, and two indices, <code>SP500</code> and <code>XYZ100</code> (its Nasdaq-100). Binance lists perps on 26 of the same names.</p><p>Every perpetual has a matching oracle feed. That is the reference price the exchange uses to mark positions and set funding. During regular hours it follows the price set by &#8220;tradFi&#8221; exchanges. What happens when that feed is inactive? Our hypothesis was that market microstructure metrics are considerably more predictive during these times.</p><p>To test it, I labelled every five-minute bar with its New York session. Overnight (20:00 to 04:00), weekends (Friday 20:00 to Sunday 20:00) and NYSE holidays count as closed. Regular hours (09:30 to 16:00) are the control. I left out the grey-zone: pre-market and after-hours, because some cash trading happens then. The data covers 28 of the most liquid US stock perps on trade.xyz, from January 1 to November 11, 2026. I pulled it with the Aperiodic Python client: <strong><a href="https://aperiodic.io/catalog/l1_price?utm_source=substack&amp;utm_medium=post&amp;utm_campaign=closed-market-stock-perps">l1_price</a></strong> for the best bid and ask and their sizes, and <strong><a href="https://aperiodic.io/catalog/derivative_price?utm_source=substack&amp;utm_medium=post&amp;utm_campaign=closed-market-stock-perps">derivative_price</a></strong> for the oracle.</p><p></p><h2>II. The microstructure metrics</h2><p>Four metrics that we found to be predictive:</p><ul><li><p>book imbalance: (bid size &#8722; ask size) / (bid size + ask size) at the best quotes;</p></li><li><p>the premium: how far the perp&#8217;s mid sits from the oracle, minus its 1-day average;</p></li><li><p>the perp&#8217;s own return over the last 15 minutes;</p></li><li><p>the <code>XYZ100</code> index perp&#8217;s return over the last 15 minutes.</p></li></ul><p>For each metric I computed its rank correlation (IC) with the next 15-minute mid return. I did this per symbol and then averaged across the 28. The t-statistics in brackets run across symbols. They show whether the effect holds name by name, not just in one name.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!vWxt!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!vWxt!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!vWxt!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!vWxt!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!vWxt!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!vWxt!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:212601,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://blog.aperiodic.io/i/225631992?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!vWxt!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!vWxt!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!vWxt!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!vWxt!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5eb99a1d-d38f-46f2-a4e5-0df37b549a16_2560x1440.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">Rank IC by session, with t-statistics</figcaption></figure></div><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!oiqn!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4ef2dd6c-1cbe-4b64-85dc-a43c0dff2130_2560x1440.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!oiqn!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4ef2dd6c-1cbe-4b64-85dc-a43c0dff2130_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!oiqn!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4ef2dd6c-1cbe-4b64-85dc-a43c0dff2130_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!oiqn!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4ef2dd6c-1cbe-4b64-85dc-a43c0dff2130_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!oiqn!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4ef2dd6c-1cbe-4b64-85dc-a43c0dff2130_2560x1440.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!oiqn!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4ef2dd6c-1cbe-4b64-85dc-a43c0dff2130_2560x1440.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/4ef2dd6c-1cbe-4b64-85dc-a43c0dff2130_2560x1440.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" title="" srcset="https://substackcdn.com/image/fetch/$s_!oiqn!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4ef2dd6c-1cbe-4b64-85dc-a43c0dff2130_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!oiqn!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4ef2dd6c-1cbe-4b64-85dc-a43c0dff2130_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!oiqn!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4ef2dd6c-1cbe-4b64-85dc-a43c0dff2130_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!oiqn!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4ef2dd6c-1cbe-4b64-85dc-a43c0dff2130_2560x1440.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">Every signal is stronger when Nasdaq is shut</figcaption></figure></div><p>Every signal gets stronger from left to right. During regular hours the best one stays under 2%, and two are no different from zero. At weekends all four sit between roughly 4% and 6%, and every one is clearly significant.</p><p>Binance shows very similar results, with an additional predictive metric: the gap between Binance&#8217;s price and Hyperliquid&#8217;s. When Nasdaq is closed, Binance follows the price on Hyperliquid, and the gap predicts Binance&#8217;s next 15 minutes clearly (an IC of about &#8722;3%). During regular hours the gap, it loses all of its predictive power, which makes sense if both venues simply follow Nasdaq then.</p><p>One note on method. I measured every return from the mid price, never from the last trade, as those bounce between bid and ask, which disguises itself as a reversal that&#8217;s not actually tradeable. This is even more prominent during the illiquid weekend / overnight sessions.</p><h2>III. The why</h2><p>Let&#8217;s start with book imbalance: when Nasdaq closes it&#8217;s book is pretty thin: about $1,000 at the best quote. A lopsided queue on a book that thin usually moves the price the way it leans. There is little on the other side to stop it.</p><p>The premium and the reversal are one story seen from two ends. Someone sends a burst of orders in one direction. On a thin book, the price moves further than the news behind those orders justifies. The perp drifts away from its oracle, and part of the move comes back. Equity researchers call this the return to liquidity provision (Nagel 2012). It should be more predictive during times when market makers are lessa active.</p><p>The index lead is the familiar lead-lag between a liquid index and thinner single names. The <code>XYZ100</code> perp moves first, and single names follow within minutes. My best guess is that people trade macro views through the index, so news reaches it before it reaches NVDA&#8217;s thin book. During the day the cash market and its futures take in news together, and the lag disappears.</p><p>Every metrics&#8217; IC are also stronger at weekends than overnight. I think one reason covers all four. On weekday nights, Nasdaq-100 futures still trade in Chicago (<a href="https://www.cmegroup.com/markets/equities/nasdaq/e-mini-nasdaq-100.contractSpecs.html">CME&#8217;s hours</a>), so the perps have a partial anchor, while not on the weekends.</p><h2>IV. The model</h2><p>We built an replicable, simple ensemble model with best practices to see if these low-capacity edges could be tradeable when combined.</p><p>We used 5 minute data as an input, with a potentiall important difference: the bars that do not see new quotes are nulled out, so a stale oder book imbalance is not carried forward. Every feature uses only data up to the end of its own bar, and is using local timestamped event aggregates that we serve at Aperiodic.</p><ul><li><p><code>book_imbalance</code>: (bid size &#8722; ask size) / (bid size + ask size), at the bar&#8217;s last best bid and ask</p></li><li><p><code>premium</code>: 10,000 &#215; ln(mid / oracle), minus its own rolling mean over the last 288 bars (one day), per symbol, once at least 50 bars exist</p></li><li><p><code>return_15m</code>: 10,000 &#215; (ln mid now &#8722; ln mid three bars ago)</p></li><li><p><code>index_return_15m</code>: <code>return_15m</code> of the <code>XYZ100</code> perp at the same timestamp</p></li><li><p>target: 10,000 &#215; (ln mid three bars ahead &#8722; ln mid now), clipped at &#177;300 bp</p></li></ul><p>For each test month from April to November, I fit a new model on all previous bars of the same session group. The main model learns from closed bars (overnight, weekend, holiday), and the control learns from regular-hours bars. The window expands from January 1, so the training set grows from about 130,000 bars for the April refit to about 900,000 for November.</p><p>All 28 symbols share one model, and the model gets no symbol identifier. I drop training rows without a quote or a target. The training data stops two days before the test month starts, so no 15-minute target reaches into the test month. There is no early stopping, no validation split, and no tuning on the test months; I ran the grid in section VII after I had fixed the design.</p><h3>The learner</h3><p>The learner is LightGBM regressor, with the default hyperparameters, except:</p><ul><li><p>Objective: Huber, with &#948; = 30 bp</p></li><li><p>Leaves per tree: 7</p></li><li><p>Minimum bars per leaf: 2,000</p></li><li><p>Learning rate: 0.05</p></li><li><p>Trees: 150, a fixed number</p></li><li><p>Seed: 1, deterministic mode</p></li></ul><p>I chose Huber because 15-minute returns on these books have fat tails, and a squared loss lets a few big moves pull the whole fit. I kept the trees small and the leaves large so each split needs a broad pattern across thousands of bars.</p><h3>What it learned</h3><p>Out of sample, the closed-market forecast has a rank IC of 5.2% over about 820,000 test bars. The regular-hours model scores &#8722;0.3% over about 290,000. These two numbers pool every symbol and bar into one rank correlation; the single-signal table in section II averages per-symbol ICs instead.</p><p>The four features, Averaged over the eight closed-market refits, each takes between a fifth and a third of the total split gain:</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!ruIW!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F33f59656-65be-4086-b126-3230c321e09e_2560x1440.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!ruIW!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F33f59656-65be-4086-b126-3230c321e09e_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!ruIW!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F33f59656-65be-4086-b126-3230c321e09e_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!ruIW!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F33f59656-65be-4086-b126-3230c321e09e_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!ruIW!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F33f59656-65be-4086-b126-3230c321e09e_2560x1440.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!ruIW!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F33f59656-65be-4086-b126-3230c321e09e_2560x1440.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/33f59656-65be-4086-b126-3230c321e09e_2560x1440.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:173862,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://blog.aperiodic.io/i/225631992?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F33f59656-65be-4086-b126-3230c321e09e_2560x1440.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!ruIW!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F33f59656-65be-4086-b126-3230c321e09e_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!ruIW!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F33f59656-65be-4086-b126-3230c321e09e_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!ruIW!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F33f59656-65be-4086-b126-3230c321e09e_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!ruIW!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F33f59656-65be-4086-b126-3230c321e09e_2560x1440.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">What the model splits on</figcaption></figure></div><h2>V. A follow-up test: Seoul and Tokyo</h2><p>If the effect comes from the cash market being closed, it should follow each stock&#8217;s own exchange, not New York&#8217;s. trade.xyz lists three stocks that let us check this: SK Hynix, Samsung and Kioxia. They trade in Seoul and Tokyo, which are open during the US night.</p><p>I ran the same monthly refits, trained only on the US names&#8217; closed bars, and applied each month&#8217;s model to these three. The model never saw them in training. On weekdays when both their home market and New York were closed, its IC was about 10%. At weekends it was about 6%. While Seoul and Tokyo were trading, it fell to 2%. And when New York was open but Seoul and Tokyo were not, it stayed around 6%. It makes sense: New York opening does nothing to anchor a stock that trades in Seoul or Tokyo.</p><p>Two caveats, thought: the weekend number is lower than the weekday one, the opposite of the US pattern, and I can&#8217;t explain that yet. I also used 00:00 to 06:30 UTC on weekdays as their home hours and ignored Korean and Japanese holidays, so the split is a little blurred.</p><p>It&#8217;s good sign for the original hypothesis that the model never saw these stocks, and it found its edge when their own exchanges were closed.</p><h2>VI. Can you trade it?</h2><h3>The rule</h3><p>At the close of every bar:</p><ol><li><p>If no position is open, the absolute forecast is above the month&#8217;s threshold, and the spread is under 5 bp, enter in the forecast&#8217;s direction. A buy pays that bar&#8217;s last ask; a sell gets its last bid.</p></li><li><p>Fifteen minutes (three bars) later, check the forecast again. If it still points the same way and is above half the threshold, hold for another 15 minutes. Repeat, for at most 6 hours.</p></li><li><p>Otherwise exit across the spread: a long sells at the bid, a short buys back at the ask.</p></li><li><p>If bars are missing between entry and exit, skip the trade.</p></li><li><p>Charge 1.5 bp in fees on each side, on top of the spread.</p></li></ol><p>The threshold is the 99.9th percentile of the absolute forecasts the model made on its own training data. Each refit sets its own: about 6 bp in April, and between 8 and 9.5 bp from June on (the monthly table below). Every trade has the same notional, and its result is its net return in bp.</p><h3>Results</h3><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!MxEm!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F85da630d-49fc-4996-aec7-88a3816b665e_2560x1440.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!MxEm!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F85da630d-49fc-4996-aec7-88a3816b665e_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!MxEm!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F85da630d-49fc-4996-aec7-88a3816b665e_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!MxEm!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F85da630d-49fc-4996-aec7-88a3816b665e_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!MxEm!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F85da630d-49fc-4996-aec7-88a3816b665e_2560x1440.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!MxEm!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F85da630d-49fc-4996-aec7-88a3816b665e_2560x1440.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/85da630d-49fc-4996-aec7-88a3816b665e_2560x1440.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" title="" srcset="https://substackcdn.com/image/fetch/$s_!MxEm!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F85da630d-49fc-4996-aec7-88a3816b665e_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!MxEm!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F85da630d-49fc-4996-aec7-88a3816b665e_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!MxEm!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F85da630d-49fc-4996-aec7-88a3816b665e_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!MxEm!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F85da630d-49fc-4996-aec7-88a3816b665e_2560x1440.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">Backtest, April 1 to November 11, 2026</figcaption></figure></div><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!ispt!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd73ce822-7085-4377-8113-43878c1636c5_2560x1440.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!ispt!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd73ce822-7085-4377-8113-43878c1636c5_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!ispt!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd73ce822-7085-4377-8113-43878c1636c5_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!ispt!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd73ce822-7085-4377-8113-43878c1636c5_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!ispt!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd73ce822-7085-4377-8113-43878c1636c5_2560x1440.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!ispt!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd73ce822-7085-4377-8113-43878c1636c5_2560x1440.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/d73ce822-7085-4377-8113-43878c1636c5_2560x1440.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" title="" srcset="https://substackcdn.com/image/fetch/$s_!ispt!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd73ce822-7085-4377-8113-43878c1636c5_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!ispt!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd73ce822-7085-4377-8113-43878c1636c5_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!ispt!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd73ce822-7085-4377-8113-43878c1636c5_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!ispt!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd73ce822-7085-4377-8113-43878c1636c5_2560x1440.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">Same model: it only works while Nasdaq is closed</figcaption></figure></div><p>The base case makes about 11 bp a trade. Higher fees and a delay each take a large bite, and both together leave nothing.</p><ul><li><p>Overnight: trades 175, net bp per trade +7.1</p></li><li><p>Weekend: trades 172, net bp per trade +12.1</p></li><li><p>Holiday: trades 19, net bp per trade +36.3</p></li></ul><h3>The trades</h3><ul><li><p>Trades: 366</p></li><li><p>Days with a trade: 126</p></li><li><p>Symbols traded: 27 of 28</p></li><li><p>Win rate: 57%</p></li><li><p>Longs: 342, +10.2 bp each</p></li><li><p>Shorts: 24, +22.1 bp each</p></li><li><p>Median holding time: 15 minutes</p></li><li><p>Trades held past 15 minutes: 9%</p></li><li><p>Trades that reached the 6-hour cap: none</p></li><li><p>Median spread at entry: 2.0 bp</p></li><li><p>Median absolute forecast at entry: 8.8 bp</p></li></ul><p>The trades are highly skewed towads buy. The average long enters after the perp has fallen about 100 bp in 15 minutes. At that point it sits about 60 bp below its usual premium to the oracle, and the book leans toward the bid. The average short is the mirror image, after a rise of about 130 bp. So in practice the model mostly buys sharp drops that overshoot.</p><p>Could the long bias distort the results? Over all closed-market test &#8220;bars&#8221;, the average 15-minute return is about +0.1 bp, and it is positive exactly half the time. Drift explains almost none of the 10 bp per long edge. It&#8217;s difficult to tell exactly why the extreme forecasts are nearly all buys, but our guess is that sharp drops on a thin book overshoot more often than sharp spikes, and that&#8217;s the fundamental behaviour this model is trying to exploit.</p><h3>Month by month</h3><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!5gHf!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe905144a-ebfa-4d8d-afe3-2ab1c8e70a5e_2560x1440.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!5gHf!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe905144a-ebfa-4d8d-afe3-2ab1c8e70a5e_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!5gHf!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe905144a-ebfa-4d8d-afe3-2ab1c8e70a5e_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!5gHf!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe905144a-ebfa-4d8d-afe3-2ab1c8e70a5e_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!5gHf!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe905144a-ebfa-4d8d-afe3-2ab1c8e70a5e_2560x1440.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!5gHf!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe905144a-ebfa-4d8d-afe3-2ab1c8e70a5e_2560x1440.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/e905144a-ebfa-4d8d-afe3-2ab1c8e70a5e_2560x1440.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" title="" srcset="https://substackcdn.com/image/fetch/$s_!5gHf!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe905144a-ebfa-4d8d-afe3-2ab1c8e70a5e_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!5gHf!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe905144a-ebfa-4d8d-afe3-2ab1c8e70a5e_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!5gHf!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe905144a-ebfa-4d8d-afe3-2ab1c8e70a5e_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!5gHf!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe905144a-ebfa-4d8d-afe3-2ab1c8e70a5e_2560x1440.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">Month by month, closed market</figcaption></figure></div><p>The IC falls in most months, from 8.5% in May to 2.4% in November, and three months lost money. See section VIII expanding on that.</p><p>The regular-hours control lost money in seven of its eight months, and its monthly IC never went above about 2%. Most of its losses came on three sell-off days in October and November. On each of them it bought many names at once and &#8220;held on&#8221;. </p><h2>VII. How simpler and more complex model variations performed</h2><p>A linear model ranks almost as well, but it doesn&#8217;t hit the original trading threshold. Plain OLS (an intercept and the four features, fit on rows with no missing values, with missing test values set to zero) reaches an IC of almost 5%. At a fixed 6 bp entry threshold it takes nearly 1,600 trades and makes less than 1 bp on each. </p><p>Deeper trees did worse. With 300 or 600 trees, profit per trade fell as the trees got deeper. More trees on shallow 3-leaf trees went the other way. But I ran this grid after choosing 7 leaves and 150 trees, so I wouldn&#8217;t swap in the better number.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!812x!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!812x!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!812x!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!812x!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!812x!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!812x!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:177634,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://blog.aperiodic.io/i/225631992?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!812x!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!812x!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!812x!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!812x!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5d35750a-9793-4453-b368-b1e5bb45db66_2560x1440.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">Profit per trade by tree size</figcaption></figure></div><p>The entry rule mattered less than I expected. I kept the 0.1% rate from an earlier version of this study. Rerun on the public data, April to July alone would have picked 0.2%:</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!9OPW!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!9OPW!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!9OPW!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!9OPW!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!9OPW!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!9OPW!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:175959,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://blog.aperiodic.io/i/225631992?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!9OPW!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png 424w, https://substackcdn.com/image/fetch/$s_!9OPW!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png 848w, https://substackcdn.com/image/fetch/$s_!9OPW!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png 1272w, https://substackcdn.com/image/fetch/$s_!9OPW!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9456a1db-abba-4bb0-8c59-9e9d9ed8091d_2560x1440.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">Entry rate, April to July only</figcaption></figure></div><p>A fixed 8 bp threshold over the whole test period gave 469 trades at +9.8 bp each and the same Sharpe of 3.2 as the 0.1% rate.</p><h2>VIII. Caveats</h2><p>The edge is shrinking. The forecast&#8217;s IC was about 8% in April and May and below 2.5% in early November. Three of the eight months lost money. The obvious explanation is that others found these edges, and that liquidity is increasing.</p><p>It&#8217;s somewhat latency sensitive. Entering five minutes late cuts the profit from 11 bp a trade to under 4, and the t-statistic falls to about 1. The signals go stale within minutes.</p><p>It&#8217;s Fees decide whether it works at all. At 4.5 bp per side the profit drops to about 5 bp a trade. Hyperliquid&#8217;s docs put the taker fee on a HIP-3 market in growth mode at 0.0045% to 0.009%, under 1 bp, against 0.045% on the base perp tier (<a href="https://hyperliquid.gitbook.io/hyperliquid-docs/trading/fees">fees</a>).</p><p>It is capacity-constrained: about $1,000 of top-level liquidity in the order book for a typical closed-hours bar.</p><p>It has a very significant long bias.</p><p>The backtest is too optimistic. Every trade is executed at the last bid and ask of its 5-minute bar, with no latency and no funding.</p><p>And the sample is short: seven and a half months, on a young exchange.</p><h2>IX. Reproduce it</h2><p>The one-signal version takes a minute. This pulls NVDA&#8217;s perp through the Aperiodic API and compares book imbalance on weekdays and weekends:</p><pre><code><code>from datetime import date
import polars as pl
from aperiodic import get_metrics

q = get_metrics(metric="l1_price", timestamp="true", interval="5m",
                exchange="hyperliquid-perps", symbol="perpetual-XYZ:NVDA-USDC:USDC",
                start_date=date(2026, 9, 1), end_date=date(2026, 10, 31))

et = pl.col("time").dt.replace_time_zone("UTC").dt.convert_time_zone("America/New_York")
mid = ((pl.col("bid_price") + pl.col("ask_price")) / 2).log()
print(q.with_columns(
        imbalance=(pl.col("bid_amount") - pl.col("ask_amount")) / (pl.col("bid_amount") + pl.col("ask_amount")),
        next_15m=(mid.shift(-3) - mid) * 1e4,
        weekend=(et.dt.weekday() &gt;= 6),
    )
    .group_by("weekend")
    .agg(ic=pl.corr(pl.col("imbalance").rank(), pl.col("next_15m").rank())))</code></code></pre><p>For September and October it prints an IC of about 1% on weekdays and almost 4% at weekends.</p><p>The full study is a few short Python files on the same client, in <a href="https://github.com/aperiodic-io/notebooks/tree/main/research/closed-market-stock-perps">aperiodic-io/notebooks</a>:</p><ul><li><p><code>data.py</code> pulls the quotes and oracle prices and builds the 5-minute panel;</p></li><li><p><code>model.py</code> holds the session calendar, the features, the refits and the backtest;</p></li><li><p><code>study.py</code> computes every table and both charts;</p></li><li><p><code>details.py</code> computes the refit, feature and trade details in sections IV and VI.</p></li></ul><p>Run <code>pip install "aperiodic[polars]" lightgbm</code>, then <code>python study.py --root ./closed_market</code>. </p><p>Both the snippet and the full study need 2026 data, which comes with <a href="https://aperiodic.io/pricing?utm_source=substack&amp;utm_medium=post&amp;utm_campaign=closed-market-stock-perps">Pro</a>. A free key gets you every metric for 2025 on BTC, ETH, SOL and 10 tokenized assets.. The metrics are <a href="https://aperiodic.io/catalog/l1_price">l1_price</a> and <a href="https://aperiodic.io/catalog/derivative_price">derivative_price</a>.</p><p>Next I want to run the same test on other markets that trade around the clock against one that doesn&#8217;t: gold, oil and FX perps at the weekend. If you need help with data, feel free to DM me!</p><h2>Appendix: universe and calendar</h2><p>The 28 perps on trade.xyz, by the month of their first quote in our data:</p><ul><li><p>January 2026: HOOD, INTC, MU, PLTR, TSLA</p></li><li><p>February: AAPL, COIN, CRCL, MSFT, ORCL</p></li><li><p>March: AMD, MSTR, NVDA</p></li><li><p>April: AMZN, GOOGL, META, SNDK, <code>XYZ100</code></p></li><li><p>May: CRWV</p></li><li><p>June: RKLB, <code>SP500</code></p></li><li><p>July: CBRS, MRVL</p></li><li><p>August: LITE, MRNA, NBIS, SOXL, SPCX</p></li></ul><p>I label sessions in New York time, so they follow the daylight-saving switches. The NYSE full-day holidays in the calendar are January 1, January 19, February 16, April 3, May 25, June 19, July 3 and September 7 (November 26 falls after the sample ends).</p><h2>References</h2><ul><li><p>Nagel, S. (2012). Evaporating liquidity. <em>Review of Financial Studies</em>, 25(7).</p></li></ul>]]></content:encoded></item><item><title><![CDATA[Aperiodic: Democratizing Crypto Order Flow, Liquidity & Market Microstructure Metrics]]></title><description><![CDATA[What 200+ Terabytes of Tick Data Looks Like When It's Actually Useful]]></description><link>https://blog.aperiodic.io/p/aperiodic-democratizing-crypto-order</link><guid isPermaLink="false">https://blog.aperiodic.io/p/aperiodic-democratizing-crypto-order</guid><dc:creator><![CDATA[Mark Aron Szulyovszky]]></dc:creator><pubDate>Wed, 18 Mar 2026 09:53:02 GMT</pubDate><enclosure url="https://substack-post-media.s3.amazonaws.com/public/images/fb9332fe-695d-4bc7-95b4-d427c23e3d48_3022x1522.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p></p><p>It&#8217;s a big day for us: we&#8217;re opening <strong><a href="https://aperiodic.io">Aperiodic</a></strong> and our whole data catalog for the public.</p><p>It&#8217;s been long time in the making. We&#8217;ve been customers to all crypto data platforms and came out disappointed with the quality and variety of offering. For anyone who&#8217;s remotely serious trying to build quantitative strategies, you need:</p><ul><li><p><strong>Point-in-time</strong> data</p></li><li><p>Basic and advanced <strong>liquidity metrics</strong> (slippage, bid/ask price twap/vwap, top-of-the-book and deep aggregate order book liquidity)</p></li><li><p>A large variety of <strong>unique market microstructure metrics</strong> that describe the state of the market well - (Run imbalance, small / larger order flow volume, </p></li><li><p>Full exchange coverage <strong>without</strong> <strong>survivorship bias</strong></p></li><li><p><strong>Local</strong>-<strong>timestamped</strong> versions of all time series</p></li></ul><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><p>You may get the maximum of 1 or 2 of these with the existing providers - and all with Aperiodic.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://aperiodic.io/" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!R-bh!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bc062b-031d-4dc1-8a90-c8dd536c4476_2138x1244.png 424w, https://substackcdn.com/image/fetch/$s_!R-bh!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bc062b-031d-4dc1-8a90-c8dd536c4476_2138x1244.png 848w, https://substackcdn.com/image/fetch/$s_!R-bh!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bc062b-031d-4dc1-8a90-c8dd536c4476_2138x1244.png 1272w, https://substackcdn.com/image/fetch/$s_!R-bh!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bc062b-031d-4dc1-8a90-c8dd536c4476_2138x1244.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!R-bh!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bc062b-031d-4dc1-8a90-c8dd536c4476_2138x1244.png" width="1456" height="847" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/c3bc062b-031d-4dc1-8a90-c8dd536c4476_2138x1244.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:847,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:584549,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;https://aperiodic.io/&quot;,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:&quot;https://blog.unravel.finance/i/191151070?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bc062b-031d-4dc1-8a90-c8dd536c4476_2138x1244.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!R-bh!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bc062b-031d-4dc1-8a90-c8dd536c4476_2138x1244.png 424w, https://substackcdn.com/image/fetch/$s_!R-bh!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bc062b-031d-4dc1-8a90-c8dd536c4476_2138x1244.png 848w, https://substackcdn.com/image/fetch/$s_!R-bh!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bc062b-031d-4dc1-8a90-c8dd536c4476_2138x1244.png 1272w, https://substackcdn.com/image/fetch/$s_!R-bh!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bc062b-031d-4dc1-8a90-c8dd536c4476_2138x1244.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p></p><h3>What&#8217;s in it?</h3><p>Over the last couple of years, we&#8217;ve run hundreds of queries on L1, L2 data to test hypotheses around what kind of metrics could have alpha. We&#8217;re opening up the whole market microstructure catalog to the public.</p><p>Unlike others, Aperiodic gives you <strong>full history for your <a href="https://aperiodic.io/">subscription price</a></strong><a href="https://aperiodic.io/">.</a></p><p></p><p>A couple of unique metrics available that&#8217;s not offered elsewhere:</p><p><strong><a href="https://aperiodic.io/metrics/l2">Deep L2 Imbalances</a> &#8212;</strong> Bid/ask quantity imbalance aggregated across multiple order book depths (5, 10, 20, 25 levels), rather than just the top of book.</p><p><strong><a href="https://aperiodic.io/catalog/flow">Flow Entropy</a> &#8212;</strong> A Shannon entropy measure applied to the distribution of buy and sell trade arrivals over a window, quantifying how &#8220;disordered&#8221; or unpredictable the order flow is. Low entropy signals a structured, directional market where trend-following strategies tend to be more effective, while high entropy reflects choppy, mean-reverting conditions where directional signals break down.</p><p><strong><a href="https://aperiodic.io/catalog/slippage">Slippage</a> &#8212;</strong> The realized cost of executing a market order against the live L1 order book.</p><p><strong><a href="https://aperiodic.io/metrics/trades">Kyle lambda</a> &#8212;</strong> An empirical estimate of Kyle&#8217;s &#955;, measuring price impact per unit of signed order flow.</p><p><strong><a href="https://aperiodic.io/metrics/trades">Large trade reversal</a> &#8212;</strong> A metric capturing how much of the price move driven by a large aggressive trade subsequently reverts within the interval &#8212; distinguishing informed flow (which produces permanent impact) from uninformed or liquidity-driven flow (which mean-reverts). </p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!EoZn!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!EoZn!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png 424w, https://substackcdn.com/image/fetch/$s_!EoZn!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png 848w, https://substackcdn.com/image/fetch/$s_!EoZn!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png 1272w, https://substackcdn.com/image/fetch/$s_!EoZn!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!EoZn!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png" width="1456" height="916" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/cce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:916,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:461717,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://blog.unravel.finance/i/191151070?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!EoZn!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png 424w, https://substackcdn.com/image/fetch/$s_!EoZn!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png 848w, https://substackcdn.com/image/fetch/$s_!EoZn!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png 1272w, https://substackcdn.com/image/fetch/$s_!EoZn!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcce956a7-2c7d-4ae1-95e3-5cbbd90e334b_2578x1622.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>Browse more than 100+ metrics over <strong><a href="https://aperiodic.io/catalog">here</a></strong>!</p><p></p><h2>The most convenient data interface we could imagine</h2><p>Aperiodic is designed for the you: the API returns pre-signed URLs of ready-to-use parquet files that you can download with arbitrary concurrency (no rate limits), instead of an arbitrary format that you&#8217;d need to parse &amp; figure out how to store.</p><p>We released a lightweight python wrapper <strong><a href="https://pypi.org/project/aperiodic/">here</a></strong> as well.</p><p><strong>Download all historical data</strong> for a set of metrics for all symbols in a <a href="https://github.com/aperiodic-io/client/blob/main/examples/downloader.py">couple of lines of code</a>.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!N_jw!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!N_jw!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png 424w, https://substackcdn.com/image/fetch/$s_!N_jw!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png 848w, https://substackcdn.com/image/fetch/$s_!N_jw!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png 1272w, https://substackcdn.com/image/fetch/$s_!N_jw!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!N_jw!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png" width="1456" height="684" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/d4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:684,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:176472,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://blog.unravel.finance/i/191151070?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!N_jw!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png 424w, https://substackcdn.com/image/fetch/$s_!N_jw!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png 848w, https://substackcdn.com/image/fetch/$s_!N_jw!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png 1272w, https://substackcdn.com/image/fetch/$s_!N_jw!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4c0aaa2-df74-4967-951c-edf740c62879_2492x1170.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>We also offer direct Object Store bucket access for yearly Prime subscribers.</p><p></p><h2>Data infrastructure you don&#8217;t have to build</h2><p>Over the last couple of years, we&#8217;ve ingested <strong>hundreds of Terabytes</strong> of crypto market data, and built a very effective infrastructure that lets us query it in any way imaginable.</p><p>The only alternative up until today to access these metrics are:</p><ol><li><p>buy raw tick / L2 data (<strong>very</strong> <strong>expensive</strong>)</p></li><li><p>figure out a way to<strong> store it </strong>(could be <strong>even more expensive</strong>)</p></li><li><p><strong>query</strong> it (expensive, weeks of work)</p></li><li><p>keep it <strong>up-to-date </strong>(months of work)</p></li></ol><p>Paying tens of thousands of dollars in the process to cloud providers and for a small team of experienced data engineers.</p><p>Aperiodic will get you access to these metrics so you can focus on your research &amp; analysis from day 1, instead of spending months on data engineering pipelines.</p><p></p><h2>What would you like to see next?</h2><p>We maintain an collaborative, ambitious roadmap and very much welcome your feedback on the most useful additions: <a href="https://aperiodic.io/roadmap">Aperiodic</a><strong><a href="https://aperiodic.io/roadmap"> Roadmap</a>.</strong></p><p>Please shoot us a message if you have any ideas (metrics, delivery methods, etc.) you&#8217;d like to see here.</p><p>We hope Aperiodic expands your access to data that was previously out of reach; to celebrate the launch, we&#8217;re offering <strong><a href="https://aperiodic.io/pricing">40% off annual subscriptions</a></strong>!</p><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><p></p><p></p><p></p><p></p>]]></content:encoded></item><item><title><![CDATA[Research bits #1: The Most Underrated Metric in (Factor) Research]]></title><description><![CDATA[We&#8217;re switching over to small, more frequent posts that are easier to write & read - hope you like it!]]></description><link>https://blog.aperiodic.io/p/research-bits-1-the-most-underrated</link><guid isPermaLink="false">https://blog.aperiodic.io/p/research-bits-1-the-most-underrated</guid><dc:creator><![CDATA[Mark Aron Szulyovszky]]></dc:creator><pubDate>Thu, 11 Sep 2025 15:57:35 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!ndxy!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>We&#8217;re switching over to small, more frequent posts that are easier to write &amp; read - hope you like it! </em></p><p>One of our biggest factor research breakthrough came when we made turnover a first class citizen. The lesson was: high IC is essential, but not sufficient by itself.</p><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><p>It&#8217;s easy to skim over the fact that a high turnover factor is not directly comparable to a low turnover one - they&#8217;re qualitatively different, and will exhibit fundamentally more or less (statistical) significance.</p><p>We also started to systematically turn unprofitable, too-high turnover factors into profitable ones by applying simple smoothing / moving averages.</p><p>Example: Altair, our highest variance factor, flips the portfolio almost daily&#8212;completely unrealistic once costs are included. To keep ourselves honest and avoid overfitting, we target a daily turnover of 30-40% for any factor (that has a higher turnover by default) &#8212; before we even look at performance.</p><p>This avoids the usual bias towards performance, as well as it makes the factors comparable.</p><p></p><p>See the difference yourself: &#8220;Altair&#8221; raw (with 100% daily turnover)</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://unravel.finance/portfolio/altair.40?smoothing=0" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!ndxy!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png 424w, https://substackcdn.com/image/fetch/$s_!ndxy!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png 848w, https://substackcdn.com/image/fetch/$s_!ndxy!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png 1272w, https://substackcdn.com/image/fetch/$s_!ndxy!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!ndxy!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png" width="1456" height="486" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/eed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:486,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:122562,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;https://unravel.finance/portfolio/altair.40?smoothing=0&quot;,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://blog.unravel.finance/i/173366636?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!ndxy!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png 424w, https://substackcdn.com/image/fetch/$s_!ndxy!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png 848w, https://substackcdn.com/image/fetch/$s_!ndxy!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png 1272w, https://substackcdn.com/image/fetch/$s_!ndxy!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Feed6d16e-8d66-47d5-a919-c7a647b04996_2266x756.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><a href="https://unravel.finance/portfolio/altair.40?smoothing=0">Interactive version</a></p><p></p><p>When we apply a 20-day moving average:</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://unravel.finance/portfolio/altair.40" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!CJCe!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6a66cf4d-5764-41c7-86c2-15c4c31c6c48_2286x998.png 424w, https://substackcdn.com/image/fetch/$s_!CJCe!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6a66cf4d-5764-41c7-86c2-15c4c31c6c48_2286x998.png 848w, https://substackcdn.com/image/fetch/$s_!CJCe!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6a66cf4d-5764-41c7-86c2-15c4c31c6c48_2286x998.png 1272w, https://substackcdn.com/image/fetch/$s_!CJCe!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6a66cf4d-5764-41c7-86c2-15c4c31c6c48_2286x998.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!CJCe!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6a66cf4d-5764-41c7-86c2-15c4c31c6c48_2286x998.png" width="1456" height="636" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/6a66cf4d-5764-41c7-86c2-15c4c31c6c48_2286x998.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:636,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:null,&quot;alt&quot;:&quot;&quot;,&quot;title&quot;:null,&quot;type&quot;:null,&quot;href&quot;:&quot;https://unravel.finance/portfolio/altair.40&quot;,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" title="" srcset="https://substackcdn.com/image/fetch/$s_!CJCe!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6a66cf4d-5764-41c7-86c2-15c4c31c6c48_2286x998.png 424w, https://substackcdn.com/image/fetch/$s_!CJCe!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6a66cf4d-5764-41c7-86c2-15c4c31c6c48_2286x998.png 848w, https://substackcdn.com/image/fetch/$s_!CJCe!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6a66cf4d-5764-41c7-86c2-15c4c31c6c48_2286x998.png 1272w, https://substackcdn.com/image/fetch/$s_!CJCe!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6a66cf4d-5764-41c7-86c2-15c4c31c6c48_2286x998.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><a href="https://unravel.finance/portfolio/altair.40">Interactive version</a></p><p></p><p>As always, happy to connect on <a href="https://www.linkedin.com/in/almostintuitive/">LinkedIn</a> and talk shop!</p><p>Catch you in a couple of days with another short post!</p><div class="captioned-button-wrap" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/p/research-bits-1-the-most-underrated?utm_source=substack&utm_medium=email&utm_content=share&action=share&quot;,&quot;text&quot;:&quot;Share&quot;}" data-component-name="CaptionedButtonToDOM"><div class="preamble"><p class="cta-caption"></p></div><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/p/research-bits-1-the-most-underrated?utm_source=substack&utm_medium=email&utm_content=share&action=share&quot;,&quot;text&quot;:&quot;Share&quot;}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/p/research-bits-1-the-most-underrated?utm_source=substack&utm_medium=email&utm_content=share&action=share"><span>Share</span></a></p></div>]]></content:encoded></item><item><title><![CDATA[Cross-Sectional Alpha Factors in Crypto: 2+ Sharpe Ratio Without Overfitting]]></title><description><![CDATA[In the early &#8217;90s, the quant forefathers (Fama and French) introduced their now-canonical factor models: first three, then five, and eventually seven, explaining much of the variation in US equity returns.]]></description><link>https://blog.aperiodic.io/p/cross-sectional-alpha-factors-in</link><guid isPermaLink="false">https://blog.aperiodic.io/p/cross-sectional-alpha-factors-in</guid><dc:creator><![CDATA[Mark Aron Szulyovszky]]></dc:creator><pubDate>Thu, 14 Aug 2025 16:15:47 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!AS5b!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<div class="captioned-image-container"><figure><a class="image-link image2" target="_blank" href="https://unravel.finance/portfolio/foundational_adaptive.40" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!AS5b!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 424w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 848w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 1272w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!AS5b!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png" width="425" height="216.00274725274724" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:740,&quot;width&quot;:1456,&quot;resizeWidth&quot;:425,&quot;bytes&quot;:242809,&quot;alt&quot;:&quot;&quot;,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;https://unravel.finance/portfolio/foundational_adaptive.40&quot;,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/164728995?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" title="" srcset="https://substackcdn.com/image/fetch/$s_!AS5b!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 424w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 848w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 1272w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 1456w" sizes="100vw" fetchpriority="high"></picture><div></div></div></a></figure></div><p>In the early &#8217;90s, the quant forefathers (Fama and French) introduced their now-canonical factor models: first three, then five, and eventually seven, explaining much of the variation in US equity returns. Today, these models are used to understand what easy-to-replicate risk factors managers are being exposed to. Allocators will want to pay for only the truly unique return sources that can&#8217;t be replicated with a couple of lines of SQL.</p><p>Crypto markets are currently in the state where many of these &#8220;traditional&#8221; factors can be still considered alpha, with considerable return potential.</p><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><p>It&#8217;s important to note that these cross-sectional factors work without any directional exposure - the regular crypto boom-bust cycle may affect how effective they are, but by design, they have 50-50%  long and short exposure at any point in time.</p><p></p><h3><strong>How a Long/Short Factor Portfolio Works &#8212; in Brief</strong></h3><ol><li><p><strong>Define the universe</strong> &#8211; e.g., the top 50 digital assets by market cap, updated on a rolling basis to avoid any lookahead bias.</p></li><li><p><strong>Choose a factor metric</strong> &#8211; for example, momentum measured as the percentage return over the past <em>n</em> days.</p></li><li><p><strong>Rank the assets daily</strong> based on that metric.</p></li><li><p><strong>Go long the leaders, short the laggards</strong> &#8211; take equal-weighted long positions in the top 20% and equal-weighted short positions in the bottom 20%.</p></li></ol><p>This structure isolates the factor exposure while remaining market-neutral.</p><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!gEQR!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc4133009-3752-40c2-b4ba-5279c54f2a3c_2152x638.png 424w, https://substackcdn.com/image/fetch/$s_!gEQR!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc4133009-3752-40c2-b4ba-5279c54f2a3c_2152x638.png 848w, https://substackcdn.com/image/fetch/$s_!gEQR!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc4133009-3752-40c2-b4ba-5279c54f2a3c_2152x638.png 1272w, https://substackcdn.com/image/fetch/$s_!gEQR!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc4133009-3752-40c2-b4ba-5279c54f2a3c_2152x638.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!gEQR!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc4133009-3752-40c2-b4ba-5279c54f2a3c_2152x638.png" width="584" height="173.27472527472528" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/c4133009-3752-40c2-b4ba-5279c54f2a3c_2152x638.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:432,&quot;width&quot;:1456,&quot;resizeWidth&quot;:584,&quot;bytes&quot;:94941,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/164728995?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc4133009-3752-40c2-b4ba-5279c54f2a3c_2152x638.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!gEQR!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc4133009-3752-40c2-b4ba-5279c54f2a3c_2152x638.png 424w, https://substackcdn.com/image/fetch/$s_!gEQR!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc4133009-3752-40c2-b4ba-5279c54f2a3c_2152x638.png 848w, https://substackcdn.com/image/fetch/$s_!gEQR!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc4133009-3752-40c2-b4ba-5279c54f2a3c_2152x638.png 1272w, https://substackcdn.com/image/fetch/$s_!gEQR!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc4133009-3752-40c2-b4ba-5279c54f2a3c_2152x638.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div></div></div></div><figcaption class="image-caption">A typical allocation for a given day (targeting 200% gross exposure)</figcaption></figure></div><p></p><h2><strong>Cross-sectional Momentum</strong></h2><p>Cross-sectional momentum is a well-documented anomaly: assets that outperform over a given formation period (&#8220;winners&#8221;) tend to continue outperforming those that underperform (&#8220;losers&#8221;)&#8212;at least in equities.</p><p>The same applies to digital assets, with a couple of caveats:</p><ul><li><p><strong>Shorter horizons</strong> &#8211; In equities, momentum signals often span 6&#8211;12 months; in crypto, they&#8217;re concentrated over much shorter windows (~30-day formation periods) and decay rapidly, sometimes reversing within months.</p></li><li><p><strong>Crash-prone behavior</strong> &#8211; Momentum crashes in crypto are typically triggered by violent reversals in a handful of assets (e.g., short-squeezed losers), rather than broad market shifts.</p></li><li><p><strong>Large-cap dominance</strong> &#8211; Most of the returns come from top-40 market-cap coins; smaller tokens suffer from liquidity constraints and higher idiosyncratic risk.</p></li><li><p><strong>Regime sensitivity</strong> &#8211; Performance weakens in low-sentiment market regimes.</p><p></p></li></ul><p>There&#8217;s clear evidence that even<strong> </strong>the simplest <strong>long-only, time-series momentum strategy</strong> on Bitcoin have consistently outperforms in risk-adjusted terms - but it works well in the cross-section as well. </p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://unravel.finance/portfolio/momentum.40https://unravel.finance/portfolio/momentum.40" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!fBQ8!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3220e37a-be7a-4c7b-af24-ee47e7c33a99_2196x994.png 424w, https://substackcdn.com/image/fetch/$s_!fBQ8!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3220e37a-be7a-4c7b-af24-ee47e7c33a99_2196x994.png 848w, https://substackcdn.com/image/fetch/$s_!fBQ8!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3220e37a-be7a-4c7b-af24-ee47e7c33a99_2196x994.png 1272w, https://substackcdn.com/image/fetch/$s_!fBQ8!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3220e37a-be7a-4c7b-af24-ee47e7c33a99_2196x994.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!fBQ8!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3220e37a-be7a-4c7b-af24-ee47e7c33a99_2196x994.png" width="1456" height="659" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/3220e37a-be7a-4c7b-af24-ee47e7c33a99_2196x994.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:659,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:193782,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;https://unravel.finance/portfolio/momentum.40https://unravel.finance/portfolio/momentum.40&quot;,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/164728995?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3220e37a-be7a-4c7b-af24-ee47e7c33a99_2196x994.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!fBQ8!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3220e37a-be7a-4c7b-af24-ee47e7c33a99_2196x994.png 424w, https://substackcdn.com/image/fetch/$s_!fBQ8!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3220e37a-be7a-4c7b-af24-ee47e7c33a99_2196x994.png 848w, https://substackcdn.com/image/fetch/$s_!fBQ8!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3220e37a-be7a-4c7b-af24-ee47e7c33a99_2196x994.png 1272w, https://substackcdn.com/image/fetch/$s_!fBQ8!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3220e37a-be7a-4c7b-af24-ee47e7c33a99_2196x994.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">The returns of the long/short cross-sectional, simple momentum portfolio - <a href="https://unravel.finance/portfolio/momentum.40">interactive version</a>.</figcaption></figure></div><div class="captioned-image-container"><figure><a class="image-link image2" target="_blank" href="https://unravel.finance/portfolio/momentum.40" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!KqSK!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd0c58564-577b-4f9e-93af-59b1c870c2f6_2102x946.png 424w, https://substackcdn.com/image/fetch/$s_!KqSK!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd0c58564-577b-4f9e-93af-59b1c870c2f6_2102x946.png 848w, https://substackcdn.com/image/fetch/$s_!KqSK!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd0c58564-577b-4f9e-93af-59b1c870c2f6_2102x946.png 1272w, https://substackcdn.com/image/fetch/$s_!KqSK!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd0c58564-577b-4f9e-93af-59b1c870c2f6_2102x946.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!KqSK!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd0c58564-577b-4f9e-93af-59b1c870c2f6_2102x946.png" width="490" height="220.43269230769232" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/d0c58564-577b-4f9e-93af-59b1c870c2f6_2102x946.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:655,&quot;width&quot;:1456,&quot;resizeWidth&quot;:490,&quot;bytes&quot;:92756,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;https://unravel.finance/portfolio/momentum.40&quot;,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/164728995?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd0c58564-577b-4f9e-93af-59b1c870c2f6_2102x946.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!KqSK!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd0c58564-577b-4f9e-93af-59b1c870c2f6_2102x946.png 424w, https://substackcdn.com/image/fetch/$s_!KqSK!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd0c58564-577b-4f9e-93af-59b1c870c2f6_2102x946.png 848w, https://substackcdn.com/image/fetch/$s_!KqSK!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd0c58564-577b-4f9e-93af-59b1c870c2f6_2102x946.png 1272w, https://substackcdn.com/image/fetch/$s_!KqSK!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd0c58564-577b-4f9e-93af-59b1c870c2f6_2102x946.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div></div></div></a><figcaption class="image-caption">Average next day returns per factor quantile.</figcaption></figure></div><h2><strong>Carry in the cross-section</strong></h2><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><p>Unlike momentum, the carry factor traces its roots to commodity markets, where futures often trade at sustained premiums or discounts to spot prices due to factors like storage costs, seasonal patterns, and supply constraints. By expiry, these gaps must close, creating a well-defined arbitrage opportunity.</p><p>In crypto, carry is most easily measured via <strong>perpetual futures funding rates</strong>&#8212;periodic payments between traders designed to keep perpetual prices anchored to spot. When perpetuals trade above spot, longs pay shorts; when they trade below, shorts pay longs.</p><p>There are two ways to implement carry in this context:</p><ul><li><p><strong>Hard arbitrage</strong> &#8211; Short assets with high funding rates, buy the same notional exposure in spot, and hedge out any price risk. Profits come directly from the funding payments.</p></li><li><p><strong>Soft (cross-sectional) carry</strong> &#8211; Short the assets with the highest funding rates and go long those with the lowest (or most negative), without explicit hedging. Here, returns come from both the funding spread and differences in expected asset performance.</p></li></ul><p>Funding rates vary across exchanges, so we use an <strong>open-interest-weighted composite</strong> to avoid exchange-specific distortions and better capture the underlying carry signal.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://unravel.finance/portfolio/carry_enhanced.40" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!NNXC!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F38824ffb-a9b6-4ba3-8d0c-be25032e6f6c_2134x1002.png 424w, https://substackcdn.com/image/fetch/$s_!NNXC!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F38824ffb-a9b6-4ba3-8d0c-be25032e6f6c_2134x1002.png 848w, https://substackcdn.com/image/fetch/$s_!NNXC!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F38824ffb-a9b6-4ba3-8d0c-be25032e6f6c_2134x1002.png 1272w, https://substackcdn.com/image/fetch/$s_!NNXC!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F38824ffb-a9b6-4ba3-8d0c-be25032e6f6c_2134x1002.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!NNXC!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F38824ffb-a9b6-4ba3-8d0c-be25032e6f6c_2134x1002.png" width="1456" height="684" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/38824ffb-a9b6-4ba3-8d0c-be25032e6f6c_2134x1002.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:684,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:175446,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;https://unravel.finance/portfolio/carry_enhanced.40&quot;,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/164728995?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F38824ffb-a9b6-4ba3-8d0c-be25032e6f6c_2134x1002.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!NNXC!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F38824ffb-a9b6-4ba3-8d0c-be25032e6f6c_2134x1002.png 424w, https://substackcdn.com/image/fetch/$s_!NNXC!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F38824ffb-a9b6-4ba3-8d0c-be25032e6f6c_2134x1002.png 848w, https://substackcdn.com/image/fetch/$s_!NNXC!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F38824ffb-a9b6-4ba3-8d0c-be25032e6f6c_2134x1002.png 1272w, https://substackcdn.com/image/fetch/$s_!NNXC!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F38824ffb-a9b6-4ba3-8d0c-be25032e6f6c_2134x1002.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">Returns of the long/short, cross-sectional &#8220;enhanced carry&#8221; portfolio - <a href="https://unravel.finance/portfolio/carry_enhanced.40">interactive version</a></figcaption></figure></div><div class="captioned-image-container"><figure><a class="image-link image2" target="_blank" href="https://unravel.finance/portfolio/carry_enhanced.40" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!YmL4!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd5841ee2-afca-48c8-9f87-57229bf24250_2044x968.png 424w, https://substackcdn.com/image/fetch/$s_!YmL4!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd5841ee2-afca-48c8-9f87-57229bf24250_2044x968.png 848w, https://substackcdn.com/image/fetch/$s_!YmL4!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd5841ee2-afca-48c8-9f87-57229bf24250_2044x968.png 1272w, https://substackcdn.com/image/fetch/$s_!YmL4!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd5841ee2-afca-48c8-9f87-57229bf24250_2044x968.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!YmL4!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd5841ee2-afca-48c8-9f87-57229bf24250_2044x968.png" width="503" height="238.37225274725276" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/d5841ee2-afca-48c8-9f87-57229bf24250_2044x968.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:690,&quot;width&quot;:1456,&quot;resizeWidth&quot;:503,&quot;bytes&quot;:102062,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;https://unravel.finance/portfolio/carry_enhanced.40&quot;,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/164728995?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd5841ee2-afca-48c8-9f87-57229bf24250_2044x968.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!YmL4!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd5841ee2-afca-48c8-9f87-57229bf24250_2044x968.png 424w, https://substackcdn.com/image/fetch/$s_!YmL4!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd5841ee2-afca-48c8-9f87-57229bf24250_2044x968.png 848w, https://substackcdn.com/image/fetch/$s_!YmL4!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd5841ee2-afca-48c8-9f87-57229bf24250_2044x968.png 1272w, https://substackcdn.com/image/fetch/$s_!YmL4!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd5841ee2-afca-48c8-9f87-57229bf24250_2044x968.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div></div></div></a><figcaption class="image-caption">Average next day returns per factor quantile</figcaption></figure></div><p></p><h2>The Caveats</h2><p>Building <strong>crypto-specific, market-neutral, cross-sectional portfolios</strong> is far from straightforward. In equities, short availability is a primary constraint; in crypto, the bigger hurdle is <strong>survivorship bias</strong>&#8212;it&#8217;s often difficult to source reliable data for delisted or inactive tokens.</p><p>Beyond that, most crypto assets&#8212;outside of a handful of large-cap names&#8212;behave more like <strong>penny stocks</strong> than mid-cap companies: thinly traded, highly volatile, and frequently subject to pump-and-dump dynamics. Historical testing before ~2020 is of limited use, as the market only reached a comparable level of maturity in the past five years.</p><p>Even in this recent period, creating a stable, tradable universe is challenging. We use market cap ranking with additional <strong>volume, volatility, and availability filters</strong>, with smoothing to limit turnover and avoid overreacting to temporary shifts in liquidity (memecoin spikes).</p><p>Another key complication is the <strong>dispersion of volatility</strong> within the tradable universe. In equities, volatility differences are significant; in crypto, they&#8217;re extreme - Bitcoin and the average memecoin might as well be different asset classes. Equal notional long and short positions can still leave the portfolio heavily tilted toward the more volatile side. To address this we apply <strong>inverse volatility weighting</strong> at the portfolio level so highly volatile tokens get proportionally smaller allocations.</p><p>But what&#8217;s the alternative to cross-sectional strategies? Potentially overfitting specific signals to individual assets, or abandoning market neutrality entirely.</p><p></p><h2>Achieving Sharpe Ratio of 2+ without Overfitting </h2><p>No single factor can consistently forecast returns across all market regimes&#8212;it&#8217;s an unrealistic expectation. Probably everyone is tired of the mantra &#8220;diversification is the only free lunch&#8221; - but diversification works <strong>particularly well </strong>in the context of multi-factor portfolios. The combination doesn&#8217;t need to be particularly sophisticated either, even a simple arithmetic average of signals can deliver <strong>tangible benefits</strong>:</p><ul><li><p><strong>Reduced turnover</strong> &#8211; When factors disagree, offsetting positions naturally cancel out.</p></li><li><p><strong>Greatly improved risk-adjusted returns</strong> &#8211; Uncorrelated return streams smooth the equity curve and raise Sharpe.</p></li></ul><p>When we put these <strong>2</strong> (Momentum + Enhanced Carry) established, well-known factors in a single, portfolio, we get something we call &#8220;<a href="https://unravel.finance/portfolio/foundational.40">Foundational</a>&#8221; portfolio:</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!AS5b!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!AS5b!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 424w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 848w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 1272w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!AS5b!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png" width="567" height="288.1730769230769" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:740,&quot;width&quot;:1456,&quot;resizeWidth&quot;:567,&quot;bytes&quot;:242809,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/164728995?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!AS5b!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 424w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 848w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 1272w, https://substackcdn.com/image/fetch/$s_!AS5b!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27ad1859-004c-47ba-befb-895ba844ad30_2180x1108.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption"><a href="https://unravel.finance/portfolio/foundational.40">Link to the interactive tearsheet</a></figcaption></figure></div><p><strong>How Far Can This Scale?</strong></p><p>Diversification may be the only free lunch, but even free lunches have limits. Once you ensemble more than about six factors, the marginal benefit drops to near zero. We currently track ~20 alpha factors (50 overall) and have found it&#8217;s easier to build <strong>three orthogonal portfolios with Sharpe &#8776; 2.5</strong> than to squeeze a single portfolio up to Sharpe 3.</p><p>This breadth puts us in a unique position: we can selectively <strong>publish and license</strong> some of our proprietary factors without compromising our core edge. You can <strong>see <a href="https://unravel.finance/portfolios/40">their live performance</a> on </strong>Unravel, and if you&#8217;d like to dig deeper, <a href="http://email:mark@unravel.finance">reach out</a>.</p><p>As always, happy to connect on <a href="https://www.linkedin.com/in/almostintuitive/">LinkedIn</a> and talk shop!</p><p></p><p>* The Sharpe Ratio of &#8220;Foundational&#8221; is actually less than 2, but we track other multi-factor portfolios with considerably higher risk-adjusted returns.</p><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption">Thanks for reading Unexpected Correlations! Subscribe for free to receive new posts.</p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div>]]></content:encoded></item><item><title><![CDATA[How Speculative Money Flows into Crypto]]></title><description><![CDATA[Measuring how exogenous risk factors predict crypto returns]]></description><link>https://blog.aperiodic.io/p/how-speculative-money-flows-into</link><guid isPermaLink="false">https://blog.aperiodic.io/p/how-speculative-money-flows-into</guid><dc:creator><![CDATA[Mark Aron Szulyovszky]]></dc:creator><pubDate>Mon, 28 Apr 2025 15:28:20 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/$s_!GFN-!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p>Compared to traditional futures or equities, crypto markets offer <em>greater transparency</em>&#8212;thanks primarily to the public blockchain and also to the unique culture that shaped the industry. This opens up <em>new opportunities</em> for investors and traders to monitor and measure liquidity dynamics that are otherwise hidden in conventional markets.</p><p>We&#8217;ve outlined a base framework to systematically identify and measure the drivers of crypto liquidity&#8212;beginning with external macro factors and progressively focusing inward on ecosystem-specific effects. With an emphasis on the qualitative aspects of these factors &#8212; specifically, measuring and reporting on their <em><strong>predictive power</strong>.</em></p><p></p><h2>1.  Outside the ecosystem: Global / Macro Factors </h2><p>These are usually slow moving factors &#8212; the kind that talking heads on CNBC would be talking about, if they were talking about crypto:</p><p><strong><a href="https://unravel.finance/risk/BTC/index_speculative_flow">Speculative Flow</a></strong> - The overall liquidity that&#8217;s moving towards more speculative, risky assets, like: <em>tech stocks, emerging markets, high yield bonds</em>.</p><p>These has been the quantitatively most consistently predictive factors over the last 5 years. Technically, they should be called &#8220;Momentum Spillover&#8221; effects - the momentum of other asset classes heavily affect the crypto market, creating predictable patterns that can be effectively used to manage risk. </p><p>For example, the <a href="http://unravel.finance/risk/BTC/momentum_spillover_equities_cloud">momentum of cloud computing stocks</a> has been leading the overall crypto market&#8217;s returns.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="http://unravel.finance/risk/BTC/momentum_spillover_equities_cloud" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!GFN-!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png 424w, https://substackcdn.com/image/fetch/$s_!GFN-!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png 848w, https://substackcdn.com/image/fetch/$s_!GFN-!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png 1272w, https://substackcdn.com/image/fetch/$s_!GFN-!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!GFN-!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png" width="1456" height="425" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:425,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:437777,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;http://unravel.finance/risk/BTC/momentum_spillover_equities_cloud&quot;,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/162127973?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!GFN-!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png 424w, https://substackcdn.com/image/fetch/$s_!GFN-!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png 848w, https://substackcdn.com/image/fetch/$s_!GFN-!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png 1272w, https://substackcdn.com/image/fetch/$s_!GFN-!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F937a8db9-1f9c-46e2-8734-ec58c0847484_3634x1060.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">When the momentum of the cloud computing sector is high, we observed substantially higher 30 day Bitcoin forward returns.</figcaption></figure></div><p><strong>Safe heaven perception</strong> - When the current perception of Bitcoin is closer to Gold than a speculative asset, it&#8217;ll behave differently during times of stress and &#8220;risk-off&#8221; events. We could quantify this relationship by measuring the <a href="https://unravel.finance/risk/BTC/btc_gold_correlation">rolling correlation</a> coefficient between <a href="https://unravel.finance/risk/BTC/btc_gold_correlation">Bitcoin and Gold&#8217;s returns</a>, with the following results:</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!Xejw!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe4524684-9be6-463d-879d-697705cba3fd_2526x864.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!Xejw!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe4524684-9be6-463d-879d-697705cba3fd_2526x864.png 424w, https://substackcdn.com/image/fetch/$s_!Xejw!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe4524684-9be6-463d-879d-697705cba3fd_2526x864.png 848w, https://substackcdn.com/image/fetch/$s_!Xejw!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe4524684-9be6-463d-879d-697705cba3fd_2526x864.png 1272w, https://substackcdn.com/image/fetch/$s_!Xejw!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe4524684-9be6-463d-879d-697705cba3fd_2526x864.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!Xejw!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe4524684-9be6-463d-879d-697705cba3fd_2526x864.png" width="1456" height="498" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/e4524684-9be6-463d-879d-697705cba3fd_2526x864.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:498,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:182605,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/162127973?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe4524684-9be6-463d-879d-697705cba3fd_2526x864.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!Xejw!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe4524684-9be6-463d-879d-697705cba3fd_2526x864.png 424w, https://substackcdn.com/image/fetch/$s_!Xejw!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe4524684-9be6-463d-879d-697705cba3fd_2526x864.png 848w, https://substackcdn.com/image/fetch/$s_!Xejw!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe4524684-9be6-463d-879d-697705cba3fd_2526x864.png 1272w, https://substackcdn.com/image/fetch/$s_!Xejw!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe4524684-9be6-463d-879d-697705cba3fd_2526x864.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">Bitcoin&#8217;s average next 30 day returns (forward returns) when correlation with the asset class is higher (blue) or lower (yellow).</figcaption></figure></div><p>We see that the <em>highe</em>r Bitcoin&#8217;s <a href="https://unravel.finance/risk/BTC/btc_gold_correlation">correlation was with gold,</a> the <em>higher</em> its forward returns are. And, that the opposite this is true when measuring Bitcoin&#8217;s <a href="https://unravel.finance/risk/BTC/btc_tech_correlation">correlation with tech equities</a>.</p><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><p></p><h2>2. Closer to the Ecosystem: Money entering the sidelines</h2><p><strong><a href="https://unravel.finance/risk/BTC/stablecoin_supply">Stablecoin Market Cap</a> (Indirect) - </strong>Tether and other stablecoin providers report their tokens in circulation. But as of lately, there&#8217;s increased adoption in stablecoins to settle native currency transactions - and not all of it is going to crypto. There are more fine-grained measures of that may be more reliable, see below.</p><p><strong><a href="https://unravel.finance/risk/BTC/stablecoin_exchange_inflow">Stablecoin Exchange Inflow &amp; Netflow</a> (More direct) - </strong>Exchanges publish their wallet addresses for transparency reasons &#8212; we track the largest 40 exchanges stablecoin in &amp; outflows, which enables a closer look at what&#8217;s happening within the stablecoin ecosystem.</p><p>The rationale is: there are very few reasons to park stablecoins on exchanges other than considering buying something with them.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://unravel.finance/risk/BTC/stablecoin_exchange_inflow" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!IiTs!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0bcb0c78-48bb-44d6-b448-0973c0ff6ff9_3634x1060.png 424w, https://substackcdn.com/image/fetch/$s_!IiTs!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0bcb0c78-48bb-44d6-b448-0973c0ff6ff9_3634x1060.png 848w, https://substackcdn.com/image/fetch/$s_!IiTs!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0bcb0c78-48bb-44d6-b448-0973c0ff6ff9_3634x1060.png 1272w, https://substackcdn.com/image/fetch/$s_!IiTs!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0bcb0c78-48bb-44d6-b448-0973c0ff6ff9_3634x1060.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!IiTs!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0bcb0c78-48bb-44d6-b448-0973c0ff6ff9_3634x1060.png" width="1456" height="425" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/0bcb0c78-48bb-44d6-b448-0973c0ff6ff9_3634x1060.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:425,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:457282,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;https://unravel.finance/risk/BTC/stablecoin_exchange_inflow&quot;,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/162127973?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0bcb0c78-48bb-44d6-b448-0973c0ff6ff9_3634x1060.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!IiTs!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0bcb0c78-48bb-44d6-b448-0973c0ff6ff9_3634x1060.png 424w, https://substackcdn.com/image/fetch/$s_!IiTs!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0bcb0c78-48bb-44d6-b448-0973c0ff6ff9_3634x1060.png 848w, https://substackcdn.com/image/fetch/$s_!IiTs!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0bcb0c78-48bb-44d6-b448-0973c0ff6ff9_3634x1060.png 1272w, https://substackcdn.com/image/fetch/$s_!IiTs!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0bcb0c78-48bb-44d6-b448-0973c0ff6ff9_3634x1060.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption">An <a href="https://unravel.finance/risk/BTC/stablecoin_exchange_inflow">example useful risk factor</a>, that&#8217;s only predictive at one of the extremes &#8212; where the hypothesis aligns well with the data. When stablecoin inflows are extremely low, it&#8217;s worth considering cutting long exposure.</figcaption></figure></div><p><strong>ETF Netflow (Direct) - </strong>The spot Bitcoin ETF was launched in January 2024, had quite a good run since then, and it&#8217;s commonly understood as a proxy for institutional interest. There&#8217;s transparency here as well, providers publish the amount that entities holds, daily. Thanks to market makers, the ETFs are are - during normal circumstances - keep their NAV closely aligned with their market price, and that money flows into crypto effectively immediately through them &#8212; making this more of a direct channel for money to enter the crypto markets.</p><p>And evaluating its predictive power is tricky, as there&#8217;s only a bit more than a year of history available - which also coincided with a major bull run, making it very hard to judge whether it represents skill, <em>we&#8217;ll dig into it in a later article.</em></p><p></p><h2>3. Inside the Ecosystem: Leverage</h2><p>Leverage is an effective indication of crypto system-wide risk, as it&#8217;s increasing the likelihood of sudden de-leveraging effects &amp; large amount of forced liquidations.</p><p>This is exacerbated by the lack of circuit-breakers &#8212; a safety net that equity markets usually possess &#8212; and the result is usually a 10-20% wipeout of the whole ecosystem&#8217;s market cap within an hour.</p><p>Estimating leverage in the ecosystem can be done with various metrics, including:</p><p><strong><a href="https://unravel.finance/risk/BTC/funding_rates_aggregated">Funding rates of perpetual futures</a></strong> - the &#8220;carry&#8221; that traders need to pay in order to maintain their position on (leveraged) futures contracts. The higher, the more people are willing to pay a premium to stay long. The only reason for that is to maintain leverage, making it a good candidate for a leverage proxy metric.</p><p><strong><a href="https://unravel.finance/risk/BTC/liquidations_total">Liquidations</a></strong> - a large round of liquidations (caused by large moves) usually means leverage is flushed out of the system: you can only get liquidated by being over-leveraged. </p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://unravel.finance/risk/BTC/liquidations_total" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!sU9A!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec947657-505f-47a3-b703-0efd54e1039b_3634x1060.png 424w, https://substackcdn.com/image/fetch/$s_!sU9A!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec947657-505f-47a3-b703-0efd54e1039b_3634x1060.png 848w, https://substackcdn.com/image/fetch/$s_!sU9A!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec947657-505f-47a3-b703-0efd54e1039b_3634x1060.png 1272w, https://substackcdn.com/image/fetch/$s_!sU9A!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec947657-505f-47a3-b703-0efd54e1039b_3634x1060.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!sU9A!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec947657-505f-47a3-b703-0efd54e1039b_3634x1060.png" width="1456" height="425" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/ec947657-505f-47a3-b703-0efd54e1039b_3634x1060.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:425,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:468712,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;https://unravel.finance/risk/BTC/liquidations_total&quot;,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/162127973?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec947657-505f-47a3-b703-0efd54e1039b_3634x1060.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!sU9A!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec947657-505f-47a3-b703-0efd54e1039b_3634x1060.png 424w, https://substackcdn.com/image/fetch/$s_!sU9A!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec947657-505f-47a3-b703-0efd54e1039b_3634x1060.png 848w, https://substackcdn.com/image/fetch/$s_!sU9A!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec947657-505f-47a3-b703-0efd54e1039b_3634x1060.png 1272w, https://substackcdn.com/image/fetch/$s_!sU9A!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fec947657-505f-47a3-b703-0efd54e1039b_3634x1060.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><strong><a href="https://unravel.finance/risk/BTC/longshortratio">Long / short ratio</a></strong> - the volume of long positions, divided by the shorts. At the extremes, it can highlight the fact that the vast majority of the participants are already &#8220;very long&#8221; and the market can&#8217;t be really stretched further. </p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://unravel.finance/risk/BTC/longshortratio" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!ZSy1!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5c8bfc08-9008-404d-9d8e-371944c9c284_3634x1060.png 424w, https://substackcdn.com/image/fetch/$s_!ZSy1!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5c8bfc08-9008-404d-9d8e-371944c9c284_3634x1060.png 848w, https://substackcdn.com/image/fetch/$s_!ZSy1!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5c8bfc08-9008-404d-9d8e-371944c9c284_3634x1060.png 1272w, https://substackcdn.com/image/fetch/$s_!ZSy1!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5c8bfc08-9008-404d-9d8e-371944c9c284_3634x1060.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!ZSy1!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5c8bfc08-9008-404d-9d8e-371944c9c284_3634x1060.png" width="1456" height="425" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/5c8bfc08-9008-404d-9d8e-371944c9c284_3634x1060.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:425,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:677686,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;https://unravel.finance/risk/BTC/longshortratio&quot;,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/162127973?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5c8bfc08-9008-404d-9d8e-371944c9c284_3634x1060.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!ZSy1!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5c8bfc08-9008-404d-9d8e-371944c9c284_3634x1060.png 424w, https://substackcdn.com/image/fetch/$s_!ZSy1!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5c8bfc08-9008-404d-9d8e-371944c9c284_3634x1060.png 848w, https://substackcdn.com/image/fetch/$s_!ZSy1!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5c8bfc08-9008-404d-9d8e-371944c9c284_3634x1060.png 1272w, https://substackcdn.com/image/fetch/$s_!ZSy1!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5c8bfc08-9008-404d-9d8e-371944c9c284_3634x1060.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p><strong><a href="http://stablecoin_margin_borrow_rates">Margin borrow rates</a></strong> - traders usually borrow stablecoins to long other assets. The higher this rate is, the more people are borrowing, making it a relevant proxy metric.</p><p><em>We&#8217;ll explore these factors in an upcoming article, keep tuned!</em></p><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><p></p><p>Aside from the ecosystem-wide factors, there are also<a href="http://unravel.markets/risk/ETH"> asset-specific ones</a>, mainly along the lines of: public perception (trends/ fads), fundamentals (usefulness), and sentiment &amp; momentum, which are usually difficult to disentangle.</p><p></p><h2>How to use these factors?</h2><p>The best framing for these factors is: they&#8217;re <em><strong>risk proxies</strong></em>, covering valuable, otherwise ignored aspects of the market, and can be used effectively to size directional exposure.</p><p>Traditionally, if you wanted to manage your portfolio&#8217;s risk with quantitative methods, you&#8217;d be relying on recent volatility to cut size when markets are volatile. But, it works less well in crypto &#8212; <em>we&#8217;ll cover this later. It&#8217;s not that it doesn&#8217;t work because many market participants are already using this technique, more that the large amount of leverage and the sudden liquidity shocks mimic market-wide volatility-based risk management and erode its usefulness.</em></p><p>What would an effective risk management layer look like, that also includes exogenous risk factors?</p><ol><li><p>When <strong><a href="https://unravel.finance/risk/BTC/index_speculative_flow">less-to-no money is flowing into</a></strong> the crypto ecosystem, <strong>reduce directional exposure</strong>. Especially when the metrics indicate that money is about to start flowing <em>out of crypto</em>, like people moving their<a href="https://unravel.finance/risk/BTC/exchange_outflow"> crypto assets to exchanges</a>.   </p></li></ol><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://unravel.finance/risk/BTC/index_speculative_flow" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!RunP!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff48f76a8-3704-4ec3-aa4c-19e2fe859302_3634x1060.png 424w, https://substackcdn.com/image/fetch/$s_!RunP!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff48f76a8-3704-4ec3-aa4c-19e2fe859302_3634x1060.png 848w, https://substackcdn.com/image/fetch/$s_!RunP!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff48f76a8-3704-4ec3-aa4c-19e2fe859302_3634x1060.png 1272w, https://substackcdn.com/image/fetch/$s_!RunP!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff48f76a8-3704-4ec3-aa4c-19e2fe859302_3634x1060.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!RunP!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff48f76a8-3704-4ec3-aa4c-19e2fe859302_3634x1060.png" width="1456" height="425" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/f48f76a8-3704-4ec3-aa4c-19e2fe859302_3634x1060.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:425,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:423499,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:&quot;https://unravel.finance/risk/BTC/index_speculative_flow&quot;,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/162127973?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff48f76a8-3704-4ec3-aa4c-19e2fe859302_3634x1060.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!RunP!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff48f76a8-3704-4ec3-aa4c-19e2fe859302_3634x1060.png 424w, https://substackcdn.com/image/fetch/$s_!RunP!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff48f76a8-3704-4ec3-aa4c-19e2fe859302_3634x1060.png 848w, https://substackcdn.com/image/fetch/$s_!RunP!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff48f76a8-3704-4ec3-aa4c-19e2fe859302_3634x1060.png 1272w, https://substackcdn.com/image/fetch/$s_!RunP!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff48f76a8-3704-4ec3-aa4c-19e2fe859302_3634x1060.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-GK1x3M" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-GK1x3M" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a><figcaption class="image-caption"><a href="https://unravel.finance/risk/BTC/index_speculative_flow">The Speculative Flow</a> index that encompasses multiple money flow metrics &amp; its predictive properties</figcaption></figure></div><ol start="2"><li><p>When ecosystem-wide leverage is the highest, the risk of an even smaller shock creating an cascading sell-off is higher. Proactively <strong>reducing exposure during prolonged over-leveraged periods is beneficial</strong> - before an inevitable, sudden de-leveraging event happens. By that time, it&#8217;s already too late: liquidity dries up and there&#8217;s no effective way to hedge anymore.</p></li></ol><p>These risk factors work <em>even better</em> when applied on the more speculative assets, starting from <a href="https://unravel.finance/risk/ETH">Ethereum</a> and going down in market cap &#8212; because their returns are more <em>purely</em> driven by speculative money flow &amp; leverage.</p><p></p><p>We realized the value of broadening risk metrics beyond traditional measures by incorporating money flow and liquidity indicators&#8212; with <strong><a href="https://unravel.finance">Unravel</a></strong>, we&#8217;re working on making this research <em>accessible and easy to apply</em>.</p><p>Especially for risk management is <em>needed the most</em>: for the <a href="https://unravel.finance/risk/BTC">most volatile assets</a>.</p><p></p><p>As always, happy to connect on <a href="https://www.linkedin.com/in/almostintuitive/">LinkedIn</a> or <a href="https://x.com/almostintuitive/">X</a>!</p><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><p></p>]]></content:encoded></item><item><title><![CDATA[The unreasonable effectiveness of volatility targeting - and where it falls short]]></title><description><![CDATA[Part 1: Introduction, a paradox & blindspots]]></description><link>https://blog.aperiodic.io/p/the-unreasonable-effectiveness-of</link><guid isPermaLink="false">https://blog.aperiodic.io/p/the-unreasonable-effectiveness-of</guid><dc:creator><![CDATA[Mark Aron Szulyovszky]]></dc:creator><pubDate>Tue, 22 Apr 2025 16:25:04 GMT</pubDate><enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fedcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png" length="0" type="image/jpeg"/><content:encoded><![CDATA[<p><em>This is part 1 of our in-depth investigation of how quantitative risk management could help improve risk-adjusted returns: I'll explain what volatility targeting is, explore a seemingly paradoxical phenomenon, and highlight its blindspots.</em></p><p></p><p>Volatility targeting&#8217;s goal is to keep an asset or portfolio&#8217;s volatility within reasonable boundaries, by actively adjusting exposure - it&#8217;s among the very few <em>effective, universal</em> techniques in quantitative finance. I can&#8217;t really think of many other than &#8220;diversification&#8221; and volatility targeting, if I had to answer on the spot.</p><p>A quick intro: <em>inverse volatility scaling</em> means when an asset is <strong>getting more volatile</strong>, you should <strong>reduce</strong> your exposure to it. People usually measure volatility with a rolling standard deviation of an asset&#8217;s returns. It looks usually something like this:</p><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!O5V5!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe630228a-49a1-42be-98dc-34a01fca5a19_547x416.png 424w, https://substackcdn.com/image/fetch/$s_!O5V5!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe630228a-49a1-42be-98dc-34a01fca5a19_547x416.png 848w, https://substackcdn.com/image/fetch/$s_!O5V5!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe630228a-49a1-42be-98dc-34a01fca5a19_547x416.png 1272w, https://substackcdn.com/image/fetch/$s_!O5V5!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe630228a-49a1-42be-98dc-34a01fca5a19_547x416.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/$s_!O5V5!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe630228a-49a1-42be-98dc-34a01fca5a19_547x416.png" width="307" height="233.47714808043875" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/e630228a-49a1-42be-98dc-34a01fca5a19_547x416.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:416,&quot;width&quot;:547,&quot;resizeWidth&quot;:307,&quot;bytes&quot;:37342,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/161697112?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe630228a-49a1-42be-98dc-34a01fca5a19_547x416.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!O5V5!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe630228a-49a1-42be-98dc-34a01fca5a19_547x416.png 424w, https://substackcdn.com/image/fetch/$s_!O5V5!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe630228a-49a1-42be-98dc-34a01fca5a19_547x416.png 848w, https://substackcdn.com/image/fetch/$s_!O5V5!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe630228a-49a1-42be-98dc-34a01fca5a19_547x416.png 1272w, https://substackcdn.com/image/fetch/$s_!O5V5!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe630228a-49a1-42be-98dc-34a01fca5a19_547x416.png 1456w" sizes="100vw" fetchpriority="high"></picture><div></div></div></div></figure></div><p>Volatility usually <em><a href="https://en.wikipedia.org/wiki/Volatility_clustering">clusters</a></em> &#8212; when the markets are volatile, they stay volatile for some time. You can kind of see it on the chart above, it doesn&#8217;t go &#8220;go back immediately&#8221; to its starting position<a class="footnote-anchor" data-component-name="FootnoteAnchorToDOM" id="footnote-anchor-1" href="#footnote-1" target="_self">1</a>. But, it does mean revert after some time.</p><p><em>Volatility targeting</em> is using inverse volatility scaling with a pre-defined (annualized) volatility target level. The S&amp;P500&#8217;s annualized volatility is around 16%, Bitcoin&#8217;s is around 60%.</p><p>You can make your strategy, or asset&#8217;s cumulative returns <em>comparable</em> by using the same volatility target on them. It&#8217;s also a good way to <em>normalize</em> the risk contribution of each asset within a portfolio - so a really volatile asset won&#8217;t dominate it.</p><p></p><h3>What&#8217;s the opposite of volatility targeting?</h3><p>I&#8217;d say &#8220;<em>buying the dip</em>&#8221; is a pretty good contender - as inverse volatility scaling can be translated into: &#8220;<em>reducing your exposure on a dip</em>&#8221;.</p><p>And buying the dip is also<strong> effective.</strong> I think fundamentally almost all systematic strategies that trade the SP500 only a couple times per year, long-only, are <em>quantitative equivalent</em> of &#8220;buying-the-dip&#8221; (and ideally should be called as such, for transparency reasons). Retail investors kind of intuitively understand its effectiveness.</p><p>If you plot the average 30 day forward returns when the SP500 was in a drawdown, you&#8217;d see this<a class="footnote-anchor" data-component-name="FootnoteAnchorToDOM" id="footnote-anchor-2" href="#footnote-2" target="_self">2</a>:</p><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!Bm8k!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e5be398-fbdd-4663-80c4-34d6592715f3_665x432.png 424w, https://substackcdn.com/image/fetch/$s_!Bm8k!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e5be398-fbdd-4663-80c4-34d6592715f3_665x432.png 848w, https://substackcdn.com/image/fetch/$s_!Bm8k!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e5be398-fbdd-4663-80c4-34d6592715f3_665x432.png 1272w, https://substackcdn.com/image/fetch/$s_!Bm8k!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e5be398-fbdd-4663-80c4-34d6592715f3_665x432.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!Bm8k!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e5be398-fbdd-4663-80c4-34d6592715f3_665x432.png" width="355" height="230.61654135338347" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/2e5be398-fbdd-4663-80c4-34d6592715f3_665x432.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:432,&quot;width&quot;:665,&quot;resizeWidth&quot;:355,&quot;bytes&quot;:21815,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/161697112?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e5be398-fbdd-4663-80c4-34d6592715f3_665x432.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!Bm8k!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e5be398-fbdd-4663-80c4-34d6592715f3_665x432.png 424w, https://substackcdn.com/image/fetch/$s_!Bm8k!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e5be398-fbdd-4663-80c4-34d6592715f3_665x432.png 848w, https://substackcdn.com/image/fetch/$s_!Bm8k!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e5be398-fbdd-4663-80c4-34d6592715f3_665x432.png 1272w, https://substackcdn.com/image/fetch/$s_!Bm8k!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2e5be398-fbdd-4663-80c4-34d6592715f3_665x432.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div></div></div></div><figcaption class="image-caption"><em>The higher the drawdown, the larger the 30 day forward returns (SPY). Check footnote for the caveat with these plots.</em></figcaption></figure></div><p>This chart indicates that you should have bought the most when SP500 is in the biggest drawdown &#8212; thank you for that, captain hindsight! Of course this is not something that can be effectively executed, and definitely can not be called a risk management technique.</p><p>There are <strong>fundamental differences</strong> here that makes this comparison impossible: buy-the-dip assumes you have cash to allocate, while volatility targeting assumes that you are fully invested (calculated based on the current volatility level).</p><p>Although you could add to a position if it gets volatile (which usually means its price is falling), that&#8217;d would be more of <em>&#8220;buy more when in drawdown&#8221;</em> technique. But that sounds pretty dangerous, kind of the opposite of a risk management strategy.</p><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><p></p><h2>The paradox</h2><p>We looked at what the average returns were when the SP500 was in different drawdowns. Let&#8217;s look at what they are when volatility is in a certain range<a class="footnote-anchor" data-component-name="FootnoteAnchorToDOM" id="footnote-anchor-3" href="#footnote-3" target="_self">3</a>:</p><div class="captioned-image-container"><figure><div class="image-link image2" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!9X9q!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fedcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png 424w, https://substackcdn.com/image/fetch/$s_!9X9q!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fedcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png 848w, https://substackcdn.com/image/fetch/$s_!9X9q!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fedcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png 1272w, https://substackcdn.com/image/fetch/$s_!9X9q!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fedcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!9X9q!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fedcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png" width="338" height="226.73291925465838" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/edcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:432,&quot;width&quot;:644,&quot;resizeWidth&quot;:338,&quot;bytes&quot;:20682,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/161697112?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fedcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!9X9q!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fedcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png 424w, https://substackcdn.com/image/fetch/$s_!9X9q!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fedcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png 848w, https://substackcdn.com/image/fetch/$s_!9X9q!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fedcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png 1272w, https://substackcdn.com/image/fetch/$s_!9X9q!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fedcf1a6a-d5a3-4c11-8347-52d3437d1fe6_644x432.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div></div></div></div><figcaption class="image-caption">The higher the annualized volatility, the higher the returns - as well as there&#8217;s a massive increase in volatility as well. Check footnote for the caveat with these plots.</figcaption></figure></div><p> When volatility was really high, we get higher average forward returns, than in the low volatility regime - there&#8217;s a <em>catch</em> of course. But that&#8217;s the <strong>opposite</strong> of what we&#8217;re looking for! </p><p>Let&#8217;s look at the simplest possible backtest we could create, where we use volatility targeting with a 20 day rolling window on the SP500, rebalancing daily, with fixed 0.1% transaction costs:</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-img" target="_blank" href="https://substackcdn.com/image/fetch/$s_!FYb7!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/$s_!FYb7!,w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png 424w, https://substackcdn.com/image/fetch/$s_!FYb7!,w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png 848w, https://substackcdn.com/image/fetch/$s_!FYb7!,w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png 1272w, https://substackcdn.com/image/fetch/$s_!FYb7!,w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png 1456w" sizes="auto, 100vw"><img src="https://substackcdn.com/image/fetch/$s_!FYb7!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png" width="1189" height="651" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:651,&quot;width&quot;:1189,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:111788,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:true,&quot;topImage&quot;:false,&quot;internalRedirect&quot;:&quot;https://unexpectedcorrelations.substack.com/i/161697112?img=https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png&quot;,&quot;isProcessing&quot;:false,&quot;align&quot;:null,&quot;offset&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/$s_!FYb7!,w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png 424w, https://substackcdn.com/image/fetch/$s_!FYb7!,w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png 848w, https://substackcdn.com/image/fetch/$s_!FYb7!,w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png 1272w, https://substackcdn.com/image/fetch/$s_!FYb7!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9c646159-b7d9-4028-bbfd-77101fa53aaa_1189x651.png 1456w" sizes="auto, 100vw" loading="lazy"></picture><div class="image-link-expand"><div class="pencraft pc-display-flex pc-gap-8 pc-reset"><button class="pencraft pc-reset pencraft icon-container restack-image buttonBase-tqxFUX" tabindex="0" type="button"><svg aria-hidden="true" width="20" height="20" viewBox="0 0 20 20" fill="none" stroke-width="1.5" stroke="var(--color-fg-primary)" stroke-linecap="round" stroke-linejoin="round" xmlns="http://www.w3.org/2000/svg" class="icon-noB79L"><g><path d="M2.53001 7.81595C3.49179 4.73911 6.43281 2.5 9.91173 2.5C13.1684 2.5 15.9537 4.46214 17.0852 7.23684L17.6179 8.67647M17.6179 8.67647L18.5002 4.26471M17.6179 8.67647L13.6473 6.91176M17.4995 12.1841C16.5378 15.2609 13.5967 17.5 10.1178 17.5C6.86118 17.5 4.07589 15.5379 2.94432 12.7632L2.41165 11.3235M2.41165 11.3235L1.5293 15.7353M2.41165 11.3235L6.38224 13.0882"></path></g></svg></button><button class="pencraft pc-reset pencraft icon-container view-image buttonBase-tqxFUX" tabindex="0" type="button"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2 lucide-maximize-2 icon-noB79L"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></button></div></div></div></a></figure></div><p>You usually get 10-20% increase in risk-adjusted returns when you &#8220;blindly&#8221;<a class="footnote-anchor" data-component-name="FootnoteAnchorToDOM" id="footnote-anchor-4" href="#footnote-4" target="_self">4</a> apply volatility targeting on an asset.<a class="footnote-anchor" data-component-name="FootnoteAnchorToDOM" id="footnote-anchor-5" href="#footnote-5" target="_self">5</a></p><p><em>How is this possible? How come </em></p><p>It&#8217;s mainly because of &#8220;volatility drag&#8221; - the difference between cumulative average returns (a multiplicative process) and average returns (an additive process). We could mitigate its effect by averaging log returns instead of arithmetic returns, per <a href="https://robotwealth.com/the-intuition-of-log-returns/">Kris&#8217; explanation</a>.</p><p></p><h2>Try it yourself</h2><p>We released a small python package (with MIT Licence) that helps you apply volatility targeting on any return series.</p><p>It&#8217;s a collection of transparent, easy-to-audit functions, that we wrapped it into a package called <code>risklab</code> on <a href="https://pypi.org/project/risklab/">pypi</a> &#8212; it&#8217;s super easy to use:</p><pre><code>vol_signal = scale_to_target_volatility(
    target_volatility=0.16, # the annualized volatility target
    rolling_window=20,
    returns=sp500_data["Close"].pct_change(),
    upper_limit=2.0,
    lag=0,
    fill_initial_period_with_mean=False,
    annualization_period=252,
)
results = backtest_signal(
    signal=vol_signal,
    underlying=sp500_data["Close"].pct_change(),
    transaction_cost=0.001,
    lag=0,
)</code></pre><p>Explore what asset classes volatility targeting works best for using <code>risklab</code> and <a href="https://github.com/unravel-finance/risklab/blob/main/notebooks/vol-targeting.py">this</a> notebook.</p><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><h2>Is this a silver bullet? What am I missing? </h2><p>I personally always felt a bit cautious using only past volatility to manage risk. It basically means you&#8217;re over-leveraged at times when volatility is very low, to compensate for reduced leverage when its high. Looks fine in a backtest, but it&#8217;s a lot more uncomfortable when you are actually trading.</p><p>The missing piece is the realization that:</p><blockquote><h3><em><strong>not all periods of very low volatility are created equal.</strong></em></h3></blockquote><p>Unexpected events may hit when:</p><ul><li><p>Volume, liquidity is structurally low</p></li><li><p>Implied volatility and the volatility risk premium is low</p></li><li><p>Leverage is high</p></li></ul><p>In those cases, you probably see massive moves, &#8220;de-leveraging&#8221; events where people have to reduce their exposure. Some may call it &#8220;Risk parity sell-of&#8221; or &#8220;Carry trade unwinds&#8221; - and their effect are probably <strong>exaggerated</strong> by the widespread usage of <em>volatility-based risk management itself</em>!</p><p>Last summer, implied &amp; realized volatility were all at the lowest points in the last couple of years. VIX term structure was extremely flat, volumes were low (usual summer break vibes) &#8212; all of these were signs that a small sell-off could trigger a lot bigger one.</p><p>Can we use these and similar, asset-specific, or market-wide risk factors to reduce the harm of the sudden de-leveraging events, like August 2024? I believe so &#8212; you can explore them for crypto here, and will cover more assets soon.</p><p>We work on <a href="https://unravel.finance/">Unravel</a>, where we make <strong>forward-looking, exogenous risk factors</strong> available and easy-to-use - starting with the <a href="https://unravel.finance/risk/BTC">most volatile assets</a>.</p><p>As always, happy to connect on <a href="https://www.linkedin.com/in/almostintuitive/">LinkedIn</a> or <a href="https://x.com/almostintuitive/">X</a>.</p><p class="button-wrapper" data-attrs="{&quot;url&quot;:&quot;https://blog.aperiodic.io/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe now&quot;,&quot;action&quot;:null,&quot;class&quot;:null}" data-component-name="ButtonCreateButton"><a class="button primary" href="https://blog.aperiodic.io/subscribe?"><span>Subscribe now</span></a></p><p></p><p><em>This is part 1 of an in-depth investigation of how quantitative risk management could help improve risk-adjusted returns. We&#8217;ll cover the mechanics, the implementation details, benchmark the different &#8220;risk proxies&#8221;, ensembling and a lot more!</em></p><div class="footnote" data-component-name="FootnoteToDOM"><a id="footnote-1" href="#footnote-anchor-1" class="footnote-number" contenteditable="false" target="_self">1</a><div class="footnote-content"><p>Although there&#8217;s definitely an artifact here: the rolling window calculation.</p></div></div><div class="footnote" data-component-name="FootnoteToDOM"><a id="footnote-2" href="#footnote-anchor-2" class="footnote-number" contenteditable="false" target="_self">2</a><div class="footnote-content"><p><em>These factor plots are misleading, as they&#8217;re using equal bin size, and the number of observations in each bin are very skewed - the market is mainly in a low-volatile state.</em></p></div></div><div class="footnote" data-component-name="FootnoteToDOM"><a id="footnote-3" href="#footnote-anchor-3" class="footnote-number" contenteditable="false" target="_self">3</a><div class="footnote-content"><p><em>These factor plots are misleading, as they&#8217;re using equal bin size, and the number of observations in each bin are very skewed - the market is mainly in a low-volatile state.</em></p></div></div><div class="footnote" data-component-name="FootnoteToDOM"><a id="footnote-4" href="#footnote-anchor-4" class="footnote-number" contenteditable="false" target="_self">4</a><div class="footnote-content"><p>&#8220;Blindly&#8221; in this case does mean using a 20 day lookback window, coming from reasonable priors, but there&#8217;s always a chance that this is overfitting already.</p></div></div><div class="footnote" data-component-name="FootnoteToDOM"><a id="footnote-5" href="#footnote-anchor-5" class="footnote-number" contenteditable="false" target="_self">5</a><div class="footnote-content"><p>Although it didn&#8217;t perform particularly well in equities after 2008!</p></div></div>]]></content:encoded></item></channel></rss>