<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Python on aperrot 🍹 home</title><link>https://uningenieur.fr/tags/python/</link><description>Recent content in Python on aperrot 🍹 home</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 03 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://uningenieur.fr/tags/python/index.xml" rel="self" type="application/rss+xml"/><item><title>I turned a quant research paper into a trading bot that runs itself</title><link>https://uningenieur.fr/posts/crypto-trading-bot/</link><pubDate>Fri, 03 Apr 2026 00:00:00 +0000</pubDate><guid>https://uningenieur.fr/posts/crypto-trading-bot/</guid><description>&lt;p&gt;A while back I read a 2025 paper in the &lt;em&gt;International Journal of Forecasting&lt;/em&gt;
(Gurgul et al.,
&lt;a href="https://www.sciencedirect.com/science/article/pii/S0169207025000147"&gt;&lt;em&gt;&amp;ldquo;Deep learning and NLP in cryptocurrency forecasting&amp;rdquo;&lt;/em&gt;&lt;/a&gt;,
&lt;a href="https://arxiv.org/abs/2311.14759"&gt;free preprint&lt;/a&gt;) and got a little obsessed with
one question: could I actually make it &lt;em&gt;run&lt;/em&gt;? Not a notebook I open once and
forget, but a real thing that wakes up every morning, fetches the day&amp;rsquo;s data and
places a trade before I have had my coffee.&lt;/p&gt;</description></item></channel></rss>