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=2,748 NCAAF N=1,323 TENNIS_WTA N=746 TENNIS_ATP N=652 MMA_MIXED_MARTIAL_ARTS N=518 NHL N=451 LALIGA N=274 AMERICANFOOTBALL_NFL N=271 SERIEA N=226 EPL N=224 LIGUE1 N=195 BUNDESLIGA N=179 UCL N=158 NFL_PRESEASON N=145 CRICKET_IPL N=27 NBA N=9

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=nhl

Overall: N = 451 · mean predicted 50.3% · actual win rate 49.4% · gap -0.8pp · Brier 0.235 · log-loss 0.661

Calibration by predicted-probability bucket.
Predicted-prob bucket	N	Mean predicted	Actual win rate	Gap (actual − predicted)	Brier
<50%	186	40.5%	37.6%	-2.9pp	0.233
50-55%	132	52.4%	53.0%	+0.6pp	0.248
55-60%	64	57.4%	48.4%	-9.0pp	0.258
60-65%	31	62.3%	71.0%	+8.7pp	0.212
65-70%	26	66.7%	73.1%	+6.4pp	0.200
70-75%	9	72.1%	100.0%	+27.9pp	0.078
75-80%	3	76.1%	66.7%	-9.4pp	0.230

JSON feed · Model CLV · Methodology

Calibration is computed from the prediction_history table. Bucket edges are 5pp wide (50-55%, 55-60%, etc.) with widened tails (<50%, 80-90%, 90%+) where data is sparser. Negative gap is the dangerous direction — actual win rate below stated confidence.