Model calibration audit

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.

Calibration cohort by sport (click to filter):
All sports MLB N=3,353TENNIS_WTA N=753TENNIS_ATP N=748MMA_MIXED_MARTIAL_ARTS N=407LIGUE1 N=89NFL_PRESEASON N=65NBA N=42NHL N=33LALIGA N=26SERIEA N=19EPL N=15UCL N=13NCAAB N=11CRICKET_IPL N=6BUNDESLIGA N=3

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_atp

Overall: N = 748 · mean predicted 63.6% · actual win rate 65.6% · gap +2.0pp · Brier 0.220 · log-loss 0.630
Calibration by predicted-probability bucket.
Predicted-prob bucket N Mean predicted Actual win rate Gap (actual − predicted) Brier
50-55% 163 52.4% 59.5% +7.2pp 0.247
55-60% 188 57.4% 58.0% +0.6pp 0.244
60-65% 84 61.6% 58.3% -3.3pp 0.242
65-70% 111 67.3% 77.5% +10.2pp 0.185
70-75% 77 71.7% 66.2% -5.5pp 0.225
75-80% 87 77.0% 74.7% -2.3pp 0.191
80-90% 18 83.8% 88.9% +5.0pp 0.099
90%+ 20 94.6% 90.0% -4.6pp 0.091