Models on tabular data
Classification and regression on records such as inspection results.
We have no published scikit-learn build. Our Python 3.13 back ends serve data, and we say plainly that none of them trains a model.
Classification and regression on records such as inspection results.
A FastAPI service in front of a trained model.
A prediction that shows what drove it.
Moves onto 1.9 and a Python version it supports.
Illustration. A dashed outline marks where the technology would sit. We have no published build on it.
The 1.7 notes require Python 3.10 or newer.
The next minor release.
The latest minor release.
The latest patch release.
Source: scikit-learn release notes, scikit-learn.org, checked 5 November 2026. The release notes give months and not days.

A Python 3.13 and FastAPI product that grades accounts on six axes and shows which axis pulled the grade.
A Python 3.13 back end with telematics ingest and PostGIS.
Python
XGBoost
PyTorch
TensorFlow
Docker
Apache Airflowscikit-learn 1.9.1, released in September 2026. Version 1.9.0 came out in June 2026 and 1.8.0 in December 2025.
No. We say so on the first call and show the nearest work, which is a Python 3.13 back end and an AI product that grades accounts.
The 1.7 notes say Python 3.10 or newer. Python 3.10 reached end of life on 1 October 2026, so check the install page for the version you target.
You do, from the first commit. Repositories and cloud accounts stay in your name.
Thirty minutes on your data, your labels and your scikit-learn version. No sales pitch.