Nightly NBA predictions — with receipts.

Three machine-learning models pick every NBA game. Every prediction is logged, scored against the real result, and published — hits and misses alike.

Loading predictions…

How it works

1

Box scores in

Every game's team stats — shooting, rebounding, hustle, tracking.

2

Rolling form

Each team's recent play, distilled into rolling features.

3

Three models

A random forest, gradient boosting and a neural net each pick a winner and a margin.

4

Scored in public

Picks post nightly, then get graded against the final score. The full record →

Want the longer version — data, models, the nightly cycle? How HoopModel works →