The Lab Analytics|Basketball
2025-26 SEASON
Predictions for
04/02
Total Games
4
High Confidence (70%+)
0
Medium (60-70%)
4
Low (<60%)
0
4 games shown
▼ Medium (60-70%) 4 games
Med 70%
+EDGE +6%35
10:30 PM — +6.5% EDGE
Rutgers
30.4% 14-19
+160
@
Creighton PICK
69.6% 15-17
-192
Predicted Winner Creighton (69.6%)
Spread
Creighton -5.5
Med 69%
36
09:30 PM — CONFLICT
Illinois State
31.3% 23-12
@
Auburn PICK
68.7% 20-16
Predicted Winner Auburn (68.7%)
Spread
Auburn -7.5
Med 67%
58
07:00 PM — CLOSE
New Mexico
32.9% 26-10
@
Tulsa PICK
67.1% 29-7
Predicted Winner Tulsa (67.1%)
Spread
Tulsa -2.5
Med 63%
42
08:00 PM — CLOSE
Stanford
36.7% 20-12
@
West Virginia PICK
63.3% 18-14
Predicted Winner West Virginia (63.3%)
Spread
Virginia -1.5
TIERED RECOMMENDATION SYSTEM
PREMIUM: 80%+ conf, 5+ edge (88.5% win, 69.1% ROI) • GOOD: 75%+ conf, 7+ edge (82.7% win, 57.9% ROI)
Based on 4,181 game analysis

No games in this category.

▼ Medium (60-70%) 1 games
Med 70%
+EDGE +6%35
10:30 PM — +6.5% EDGE
Rutgers
30.4% 14-19
+160
@
Creighton PICK
69.6% 15-17
-192
Predicted Winner Creighton (69.6%)
Spread
Creighton -5.5
▼ Medium (60-70%) 2 games
Med 67%
58
07:00 PM — CLOSE
New Mexico
32.9% 26-10
@
Tulsa PICK
67.1% 29-7
Predicted Winner Tulsa (67.1%)
Spread
Tulsa -2.5
Med 63%
42
08:00 PM — CLOSE
Stanford
36.7% 20-12
@
West Virginia PICK
63.3% 18-14
Predicted Winner West Virginia (63.3%)
Spread
Virginia -1.5
▼ Medium (60-70%) 1 games
Med 63%
42
08:00 PM — UNDERDOG ML
Stanford
36.7% 20-12
@
West Virginia PICK
63.3% 18-14
Predicted Winner West Virginia (63.3%)
Spread
Virginia -1.5
Game Pick Confidence Moneyline Expected Value Time (ET)
Creighton vs Rutgers Creighton FAV 69.6% -192 ⭐ +5.8% 10:30 PM

No games in this category.

▼ Medium (60-70%) 1 games
Med 70%
+EDGE +6%35
10:30 PM — +6.5% EDGE
Rutgers
30.4% 14-19
+160
@
Creighton PICK
69.6% 15-17
-192
Predicted Winner Creighton (69.6%)
Spread
Creighton -5.5

No games in this category.

Model Explainability (SHAP Analysis)

SHAP (SHapley Additive exPlanations) values show which features have the most impact on our model's predictions. The values below represent the mean absolute SHAP value across all 4 games today.

XGBoost Win/Loss Model

Feature importance for win/loss predictions. Higher values indicate stronger influence on the predicted outcome.

Dominance Diff
0.2566
Away Team Implied Probability
0.1741
Point Spread
0.1075
Quality Dominance Diff
0.0950
Srs Diff Rolling
0.0821
Conference Game True
0.0487
Efficiency Diff
0.0398
Home Cumsum Fouls
0.0336
Away Offensive Rating
0.0317
Away Cumsum Reb Offensive
0.0305

How to interpret: Features at the top have the largest average impact on predictions. The bar width shows relative importance, and the number shows the mean absolute SHAP value.

Technical note: SHAP values are calculated for each game individually, then averaged to show overall feature importance across today's predictions.

NCAA Basketball Prediction Model

Win/Loss: xgb_basketball.pkl | Points: XGB-POINTS (dual-perspective) (xgb_points.joblib)

Generated: Thursday, April 02, 2026 • 2026-04-02T18:01:04.129712

The Lab Analytics · 2026 · Privacy Policy