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% | 117 | 52.4% | 53.0% | +0.6pp | 0.246 |
| 55-60% | 159 | 56.9% | 56.6% | -0.3pp | 0.245 |
| 60-65% | 60 | 62.2% | 55.0% | -7.2pp | 0.251 |
| 65-70% | 75 | 67.5% | 64.0% | -3.5pp | 0.232 |
| 70-75% | 38 | 73.0% | 76.3% | +3.3pp | 0.178 |
| 75-80% | 172 | 75.8% | 73.8% | -2.0pp | 0.195 |
| 80-90% | 83 | 87.3% | 86.7% | -0.5pp | 0.113 |
| 90%+ | 30 | 93.1% | 96.7% | +3.5pp | 0.033 |