<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>Arimancy Updates</title>
  <subtitle>Release notes and dataset updates from Arimancy.</subtitle>
  <id>https://arimancy.com/updates</id>
  <link rel="self" type="application/atom+xml" href="https://arimancy.com/feed.xml"/>
  <link rel="alternate" type="text/html" href="https://arimancy.com/updates"/>
  <updated>2026-07-22T00:00:00Z</updated>
  <author>
    <name>Arimancy LLC</name>
    <uri>https://arimancy.com</uri>
  </author>
  <entry>
    <title>Five datasets public and free, and an ERCOT correction</title>
    <id>https://arimancy.com/updates#2026-07-22-public-launch</id>
    <link rel="alternate" type="text/html" href="https://arimancy.com/updates#2026-07-22-public-launch"/>
    <updated>2026-07-22T00:00:00Z</updated>
    <summary type="text">All five Arimancy datasets are now public and free on Kaggle and Hugging Face under CC BY 4.0.</summary>
    <content type="html">&lt;p&gt;All five Arimancy datasets are now public and free on Kaggle and Hugging Face under CC BY 4.0.&lt;/p&gt;&lt;p&gt;ERCOT Hourly Demand + Population-Weighted Weather: Texas grid demand joined to population weighted weather, hourly, July 2015 to July 2026.&lt;/p&gt;&lt;p&gt;CAISO Hourly Demand + Population-Weighted Weather: the same schema for the California grid, hourly, July 2015 to July 2026.&lt;/p&gt;&lt;p&gt;PJM Hourly Demand + Population-Weighted Weather: the same schema for the PJM Interconnection, hourly, July 2015 to July 2026.&lt;/p&gt;&lt;p&gt;CFTC Commitments of Traders Weekly Panel: every COT report family in one weekly panel, 1986 to the most recent release, updated weekly.&lt;/p&gt;&lt;p&gt;Observed Weather for Every US Flight: every US domestic flight from January 2019 to July 2025 joined to observed weather at both airports.&lt;/p&gt;&lt;p&gt;ERCOT changed in this release, and anyone holding the earlier version should re-download it. The weather provenance was corrected to pinned ERA5 rather than a blended model selection, which changed both values and the schema from the originally published version.&lt;/p&gt;&lt;p&gt;The measured accuracy moved from 4.66% to 4.84% MAPE as a result, on a LightGBM baseline trained through 2024-12-31 and tested from 2025-01-01 onward. The number got slightly worse because the correction removed a defect that had been flattering the model. We publish the worse number because checkable accuracy claims are the point.&lt;/p&gt;</content>
  </entry>
  <entry>
    <title>ERCOT Hourly Demand + Weather — v1 release</title>
    <id>https://arimancy.com/updates#2026-07-05-ercot-v1</id>
    <link rel="alternate" type="text/html" href="https://arimancy.com/updates#2026-07-05-ercot-v1"/>
    <updated>2026-07-05T00:00:00Z</updated>
    <summary type="text">The first Arimancy dataset is live: ERCOT hourly demand joined to population-weighted weather, spanning 2015–2026 (96,537 rows, 27 columns). A LightGBM baseline reaches 4.66% MAPE against an 8.80% seasonal-naive benchmark. Available on Hugging Face and Kaggle under CC BY 4.0, with every imputed value flagged in the data and full source attribution to EIA, Catalyst Cooperative&apos;s PUDL, and Open-Meteo.</summary>
    <content type="html">&lt;p&gt;The first Arimancy dataset is live: ERCOT hourly demand joined to population-weighted weather, spanning 2015–2026 (96,537 rows, 27 columns). A LightGBM baseline reaches 4.66% MAPE against an 8.80% seasonal-naive benchmark. Available on Hugging Face and Kaggle under CC BY 4.0, with every imputed value flagged in the data and full source attribution to EIA, Catalyst Cooperative&apos;s PUDL, and Open-Meteo.&lt;/p&gt;</content>
  </entry>
</feed>
