Menu
Login Get Started
All Sports Performance
AD TEST MODE
PERFORMANCE HEADER
Mock Placement 728x90
NB

NBA Basketball

basketball • Performance Deep Dive

Trained 6d ago Predicted 4w ago
All-Time Average (137 folds)
Flat ROI
+45.7%
Hit Rate
72.1%
+19.7pp vs b/e
Recent Trend (last 0 folds · Apr 15–Jun 8, 2026 )
Flat ROI
Hit Rate
Out-of-sample Accuracy
58.2%

Avg across 137 folds

AUC-ROC
0.603

0.5 = coin flip · 1.0 = perfect

Log Loss
0.6681

Lower is better

Brier Score
0.2379

Probability calibration

137 validation folds
Nov 21, 2017 – Jun 8, 2026

Final Holdout Test

Held back from all training and fold evaluation — the cleanest out-of-sample signal.

No holdout data available. Re-run prediction-system run --sport nba to generate holdout metrics.

Fold-by-Fold Metrics

Supporter+ required

Supporter access required

Unlock fold-level charts to identify training stability.

Unlock Supporter

Betting Simulation

Supporter+
Recommendation ROI
Recommendation Win Rate
Universe ROI
Universe Win Rate

Supporter access required

Unlock Supporter
Model: XGBoostModel
Calibration: platt
All-Time Average (137 folds)
Flat ROI
+34.0%
Hit Rate
70.2%
+17.8pp vs b/e
Recent Trend (last 0 folds · Apr 15–Jun 8, 2026 )
Flat ROI
Hit Rate
Out-of-sample Accuracy
58.9%

Avg across 137 folds

AUC-ROC
0.600

0.5 = coin flip · 1.0 = perfect

Log Loss
0.6659

Lower is better

Brier Score
0.2368

Probability calibration

137 validation folds
Nov 21, 2017 – Jun 8, 2026

Final Holdout Test

Held back from all training and fold evaluation — the cleanest out-of-sample signal.

No holdout data available. Re-run prediction-system run --sport nba to generate holdout metrics.

Fold-by-Fold Metrics

Supporter+ required

Supporter access required

Unlock fold-level charts to identify training stability.

Unlock Supporter

Betting Simulation

Supporter+
Recommendation ROI
Recommendation Win Rate
Universe ROI
Universe Win Rate

Supporter access required

Unlock Supporter
Model: XGBoostModel
Calibration: platt
All-Time Average (136 folds)
Flat ROI
+27.8%
Hit Rate
66.5%
+14.1pp vs b/e
Recent Trend (last 0 folds · Apr 15–Jun 8, 2026 )
Flat ROI
Hit Rate
Out-of-sample Accuracy
56.8%

Avg across 136 folds

AUC-ROC
0.589

0.5 = coin flip · 1.0 = perfect

Log Loss
0.6774

Lower is better

Brier Score
0.2423

Probability calibration

136 validation folds
Nov 21, 2017 – Jun 8, 2026

Final Holdout Test

Held back from all training and fold evaluation — the cleanest out-of-sample signal.

No holdout data available. Re-run prediction-system run --sport nba to generate holdout metrics.

Fold-by-Fold Metrics

Supporter+ required

Supporter access required

Unlock fold-level charts to identify training stability.

Unlock Supporter

Betting Simulation

Supporter+
Recommendation ROI
Recommendation Win Rate
Universe ROI
Universe Win Rate

Supporter access required

Unlock Supporter
Model: XGBoostModel
Calibration: platt
Avg RMSE
19.757

Root mean squared error

Avg MAE
15.721

Mean absolute error

R² Score
-0.0429

Explained variance

137 validation folds
Nov 21, 2017 – Jun 8, 2026

Fold-by-Fold Metrics

Supporter+ required

Supporter access required

Unlock fold-level charts to identify training stability.

Unlock Supporter
Model: LightGBMRegressorModel
Calibration: platt