For every bucket of predicted probability, what did the model actually hit? A well-calibrated model has actual win rate ≈ predicted prob. A negative gap means the model is overconfident in that bucket (dangerous); positive gap means it's underpredicting (safe). Rows turn red when |gap| > 5pp AND N ≥ 10.
Combined "all sports" is rarely meaningful — sports differ in market efficiency, signal availability, and base rates. Use the chips to drill into a single sport. N<50 (red) means the calibration is brittle; N≥200 (green) is trustworthy.
Filter: window=90d · sport=ligue1
| Predicted-prob bucket | N | Mean predicted | Actual win rate | Gap (actual − predicted) | Brier |
|---|---|---|---|---|---|
| <50% | 12 | 43.9% | 25.0% | -18.9pp | 0.209 |
| 50-55% | 32 | 52.5% | 50.0% | -2.5pp | 0.250 |
| 55-60% | 30 | 57.2% | 70.0% | +12.8pp | 0.228 |
| 60-65% | 8 | 62.2% | 62.5% | +0.3pp | 0.234 |
| 65-70% | 6 | 67.4% | 100.0% | +32.6pp | 0.107 |
| 70-75% | 1 | 73.0% | 100.0% | +27.0pp | 0.073 |