<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Hmm on Chris Zeng</title>
    <link>https://chris-zeng.pages.dev/tags/hmm/</link>
    <description>Recent content in Hmm on Chris Zeng</description>
    <image>
      <title>Chris Zeng</title>
      <url>https://chris-zeng.pages.dev/img/headshot.jpg</url>
      <link>https://chris-zeng.pages.dev/img/headshot.jpg</link>
    </image>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 29 Jun 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://chris-zeng.pages.dev/tags/hmm/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Can a Hidden Markov Model Find Trading Regimes?</title>
      <link>https://chris-zeng.pages.dev/posts/hmm-trading-regimes/</link>
      <pubDate>Mon, 29 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://chris-zeng.pages.dev/posts/hmm-trading-regimes/</guid>
      <description>I put a Hidden Markov Model on order-flow data expecting it to discover sticky, tradeable market regimes. On one feature it became a fancy way to smooth the sign of order flow — 50% accuracy. On many features it latched onto volatility instead of direction and actively destroyed the small signal that was there. Here&amp;rsquo;s how HMMs work, how to wire one up without secretly leaking the future, and why the machinery didn&amp;rsquo;t earn its keep.</description>
    </item>
  </channel>
</rss>
