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

WNBA Basketball

basketball • Performance Deep Dive

Trained Never Predicted Never
All-Time Average (88 folds)
Flat ROI
+44.9%
Hit Rate
50.3%
-2.1pp vs b/e
Recent Trend (last 3 folds · Aug 28–Oct 10, 2025 ) ↑ Improving
Flat ROI
+55.5%
+10.6pp vs avg
Hit Rate
57.1%
Out-of-sample Accuracy
58.7%

Avg across 88 folds

AUC-ROC
0.651

0.5 = coin flip · 1.0 = perfect

Log Loss
0.6606

Lower is better

Brier Score
0.2342

Probability calibration

88 validation folds
Jul 13, 2017 – Oct 10, 2025

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 wnba 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 (76 folds)
Flat ROI
+30.6%
Hit Rate
68.3%
+15.9pp vs b/e
Recent Trend (last 1 folds · Aug 21–Oct 10, 2025 ) ↑ Improving
Flat ROI
+87.0%
+56.3pp vs avg
Hit Rate
100.0%
Out-of-sample Accuracy
55.3%

Avg across 76 folds

AUC-ROC
0.584

0.5 = coin flip · 1.0 = perfect

Log Loss
0.6752

Lower is better

Brier Score
0.2415

Probability calibration

76 validation folds
Jun 22, 2018 – Oct 10, 2025

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 wnba 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: CatBoostModel
Calibration: platt
All-Time Average (76 folds)
Flat ROI
+19.9%
Hit Rate
62.8%
+10.4pp vs b/e
Recent Trend (last 2 folds · Aug 21–Oct 10, 2025 ) ↓ Declining
Flat ROI
+14.0%
-5.9pp vs avg
Hit Rate
59.5%
Out-of-sample Accuracy
54.5%

Avg across 76 folds

AUC-ROC
0.592

0.5 = coin flip · 1.0 = perfect

Log Loss
0.6841

Lower is better

Brier Score
0.2455

Probability calibration

76 validation folds
Jun 22, 2018 – Oct 10, 2025

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 wnba 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
13.356

Root mean squared error

Avg MAE
10.883

Mean absolute error

R² Score
0.0174

Explained variance

88 validation folds
Jul 13, 2017 – Oct 10, 2025

Fold-by-Fold Metrics

Supporter+ required

Supporter access required

Unlock fold-level charts to identify training stability.

Unlock Supporter
Model: LightGBMRegressorModel
Calibration: platt
Avg RMSE
17.495

Root mean squared error

Avg MAE
13.649

Mean absolute error

R² Score
-0.0279

Explained variance

88 validation folds
Jul 13, 2017 – Oct 10, 2025

Fold-by-Fold Metrics

Supporter+ required

Supporter access required

Unlock fold-level charts to identify training stability.

Unlock Supporter
Model: LightGBMRegressorModel
Calibration: platt