<?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 Jorge Vega</title><link>http://jvega.xyz/tags/python/</link><description>Recent content in Python on Jorge Vega</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 10 Jul 2026 14:31:34 +0200</lastBuildDate><atom:link href="http://jvega.xyz/tags/python/index.xml" rel="self" type="application/rss+xml"/><item><title>Trading Pipelines — End-to-End Financial ML Framework</title><link>http://jvega.xyz/posts/tradingpipelines/</link><pubDate>Thu, 09 Jul 2026 20:00:00 +0200</pubDate><guid>http://jvega.xyz/posts/tradingpipelines/</guid><description>&lt;p&gt;A proof-of-concept project that proposes an end-to-end architecture for a financial machine learning framework. It covers the full lifecycle — from raw market data ingestion and feature engineering to model training, hyperparameter optimization, model serving, and interactive visualization — all orchestrated as reproducible pipelines.&lt;/p&gt;
&lt;h2 id="architecture"&gt;Architecture&lt;/h2&gt;
&lt;p&gt;The system is composed of five main layers:&lt;/p&gt;
&lt;h3 id="data-ingestion"&gt;Data Ingestion&lt;/h3&gt;
&lt;p&gt;Raw financial data is loaded into a local &lt;strong&gt;DuckDB&lt;/strong&gt; database using &lt;strong&gt;dlt&lt;/strong&gt; incremental pipelines, orchestrated by &lt;strong&gt;Apache Airflow&lt;/strong&gt;:&lt;/p&gt;</description></item></channel></rss>