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

MLB Baseball

baseball • Performance Deep Dive

Trained Never Predicted Never
All-Time Average (142 folds)
Flat ROI
+33.4%
Hit Rate
55.3%
+2.9pp vs b/e
Recent Trend (last 3 folds · Mar 25–Apr 28, 2026 ) ↓ Declining
Flat ROI
+20.4%
-13pp vs avg
Hit Rate
52.9%
Out-of-sample Accuracy
54.6%

Avg across 142 folds

AUC-ROC
0.560

0.5 = coin flip · 1.0 = perfect

Log Loss
0.6827

Lower is better

Brier Score
0.2449

Probability calibration

142 validation folds
Apr 26, 2017 – Apr 28, 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 mlb 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: LightGBMModel
Calibration: platt
All-Time Average (140 folds)
Flat ROI
+54.1%
Hit Rate
64.7%
+12.3pp vs b/e
Recent Trend (last 2 folds · Mar 25–Apr 28, 2026 ) ↑ Improving
Flat ROI
+75.0%
+20.9pp vs avg
Hit Rate
75.4%
Out-of-sample Accuracy
54.7%

Avg across 140 folds

AUC-ROC
0.559

0.5 = coin flip · 1.0 = perfect

Log Loss
0.6818

Lower is better

Brier Score
0.2445

Probability calibration

140 validation folds
Apr 26, 2017 – Apr 28, 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 mlb 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: LightGBMModel
Calibration: platt
All-Time Average (140 folds)
Flat ROI
+37.3%
Hit Rate
68.1%
+15.7pp vs b/e
Recent Trend (last 2 folds · Mar 25–Apr 28, 2026 ) ↑ Improving
Flat ROI
+51.4%
+14.2pp vs avg
Hit Rate
71.4%
Out-of-sample Accuracy
53.1%

Avg across 140 folds

AUC-ROC
0.556

0.5 = coin flip · 1.0 = perfect

Log Loss
0.6863

Lower is better

Brier Score
0.2466

Probability calibration

140 validation folds
Apr 26, 2017 – Apr 28, 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 mlb 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 (142 folds)
Flat ROI
+34.4%
Hit Rate
65.2%
+12.8pp vs b/e
Recent Trend (last 3 folds · Mar 25–Apr 28, 2026 ) ↓ Declining
Flat ROI
+32.9%
-1.5pp vs avg
Hit Rate
62.5%
Out-of-sample Accuracy
53.2%

Avg across 142 folds

AUC-ROC
0.551

0.5 = coin flip · 1.0 = perfect

Log Loss
0.6870

Lower is better

Brier Score
0.2470

Probability calibration

142 validation folds
Apr 26, 2017 – Apr 28, 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 mlb 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
Avg RMSE
4.477

Root mean squared error

Avg MAE
3.542

Mean absolute error

R² Score
-0.0020

Explained variance

142 validation folds
Apr 26, 2017 – Apr 28, 2026

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
4.490

Root mean squared error

Avg MAE
3.565

Mean absolute error

R² Score
-0.0102

Explained variance

142 validation folds
Apr 26, 2017 – Apr 28, 2026

Fold-by-Fold Metrics

Supporter+ required

Supporter access required

Unlock fold-level charts to identify training stability.

Unlock Supporter
Model: LightGBMRegressorModel
Calibration: platt