StatsAI Football Prediction Research
Every month we publish a report on how accurate StatsAI predictions were in the previous month and how they compare with margin-free bookmaker odds on the same matches. Figures are frozen once published; if we find an error, the correction is added as a dated note.
Figures for the whole period, updated daily: AI model performance
Reports
The first report (October 2026) will be published on 2 Nov 2026.
How a report is made
- Everything is measured: every resolved prediction of the month, good or bad. Filtered views are always labelled.
- The AI model and the market are compared on the same events; the market is pre-match odds with the margin removed proportionally.
- Calibration is out of sample: each day's curve is learned only from the 90 days before that day.
- 95% intervals come from resampling whole days. Groups with fewer than 1,000 events are not used for conclusions.
- Before publication two independent calculations must agree to four decimals, and the text is checked in all three languages.
- No profit or ROI: the measures are Brier score, log loss, accuracy and calibration.
How to cite
StatsAI Football Prediction Research. https://statsai.bet/en/research
The figures and data may be reused freely with attribution (CC BY 4.0).
18+ only. Statistics, not betting advice. Terms of use