<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Stan on Stuart Lacy</title><link>/tags/stan/</link><description>Recent content in Stan on Stuart Lacy</description><generator>Hugo -- gohugo.io</generator><language>en-uk</language><copyright>&amp;copy; 2023 Stuart Lacy</copyright><lastBuildDate>Mon, 26 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="/tags/stan/index.xml" rel="self" type="application/rss+xml"/><item><title>Modelling running fitness and predicting race times: an AI-assisted investigation</title><link>/2026/10/26/modelling-running-fitness-and-predicting-race-times-an-ai-assisted-investigation/</link><pubDate>Mon, 26 Oct 2026 00:00:00 +0000</pubDate><guid>/2026/10/26/modelling-running-fitness-and-predicting-race-times-an-ai-assisted-investigation/</guid><description>Motivation Ever since I took control of my own running data, I&amp;rsquo;ve been gradually adding features to reduce my reliance on Strava/Garmin&amp;rsquo;s analytics and have it all custom instead for my training purposes. One bit of analysis I&amp;rsquo;ve always wanted to do is model my fitness with the objective of providing accurate race time predictions (or at least more accurate than Garmin&amp;rsquo;s which I&amp;rsquo;m wildly sceptical of - I&amp;rsquo;ve no idea how accurate Strava&amp;rsquo;s are as I don&amp;rsquo;t pay for premium).</description></item></channel></rss>