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_wta

Overall: N = 753 · mean predicted 66.0% · actual win rate 69.3% · gap +3.3pp · Brier 0.202 · log-loss 0.589
Calibration by predicted-probability bucket.
Predicted-prob bucket N Mean predicted Actual win rate Gap (actual − predicted) Brier
50-55% 157 52.9% 61.8% +8.8pp 0.241
55-60% 136 56.5% 54.4% -2.1pp 0.248
60-65% 83 62.0% 61.4% -0.6pp 0.234
65-70% 123 67.2% 78.0% +10.8pp 0.183
70-75% 42 72.5% 78.6% +6.1pp 0.174
75-80% 133 76.3% 74.4% -1.8pp 0.191
80-90% 54 87.9% 88.9% +1.0pp 0.099
90%+ 25 94.9% 96.0% +1.1pp 0.036