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=tennis_wta
| Predicted-prob bucket | N | Mean predicted | Actual win rate | Gap (actual − predicted) | Brier |
|---|---|---|---|---|---|
| 50-55% | 172 | 52.8% | 59.9% | +7.1pp | 0.242 |
| 55-60% | 168 | 56.7% | 58.3% | +1.6pp | 0.242 |
| 60-65% | 89 | 62.0% | 60.7% | -1.3pp | 0.236 |
| 65-70% | 130 | 67.2% | 76.9% | +9.7pp | 0.187 |
| 70-75% | 49 | 72.8% | 79.6% | +6.8pp | 0.169 |
| 75-80% | 186 | 76.0% | 75.3% | -0.7pp | 0.187 |
| 80-90% | 81 | 88.3% | 91.4% | +3.0pp | 0.079 |
| 90%+ | 34 | 94.7% | 97.1% | +2.4pp | 0.028 |