<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Chronos-2 on Kwak Jazz</title><link>https://gwils28.github.io/en/tags/chronos-2/</link><description>Recent content in Chronos-2 on Kwak Jazz</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Wilson Goma</copyright><lastBuildDate>Mon, 09 Nov 2026 00:26:26 +0100</lastBuildDate><atom:link href="https://gwils28.github.io/en/tags/chronos-2/index.xml" rel="self" type="application/rss+xml"/><item><title>Time series foundation models: forecasting tomorrow's electricity consumption for 3,517 commercial buildings</title><link>https://gwils28.github.io/en/projects/flexgrid-prevision-j1/</link><pubDate>Sun, 08 Nov 2026 00:00:00 +0000</pubDate><guid>https://gwils28.github.io/en/projects/flexgrid-prevision-j1/</guid><description>The TSFM tech watch applied to a fictional balance responsible party, on real public data: LightGBM, Chronos-2 and their blend against RTE&amp;rsquo;s day-ahead forecast, published and debiased. A 2.7% MAPE on the portfolio against 5.6% without a model, a router that does not beat the blend, a cold start handled by the naive forecast, Timestral and TimesFM 3.0 in an addendum, a Dagster service and its replayed monitoring.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://gwils28.github.io/projects/flexgrid-prevision-j1/cover.png"/></item></channel></rss>