Updated: Monday, Dec 15 01:22:17 AM EST
Thiel Tomcats vs Youngstown State Penguins (Final)
52 - 103, (Margin: -51, Total: 155)
Beeghly Center
Second-Half conditional estimates based on a margin of -24.0 points and 68.0 total points (models are continuously adjusted up to Halftime)
------------------------------------------------------------------------------------------------------------------------------------------------------
E[AWAY] E[HOME] E[SP] 68% CI E[TOTAL] 68% CI 2H-A 2H-H 2H-SP 2H-TTL AWAY WIN% HOME WIN% (ODDS HOME)
======================================================================================================================================================
59.7 84.7 -25.1 (-35.1, -15.0) 144.4 (132.2, 156.6) 0.0 0.0 -25.1 144.4 2.3% 97.7% -4190
------------------------------------------------------------------------------------------------------------------------------------------------------
Live conditional estimates per 5 Minutes (+/- 1 deviation) (models are continuously adjusted)
------------------------------------------------------------------------------------------------------------------------------------------------------
TYPE 5M 10M 15M 20M 25M 30M 35M 40M
======================================================================================================================================================
E[SP] - - - - - - - -51.3
P[W] - - - - - - - 100.0%
ODDS - - - - - - - -
------------------------------------------------------------------------------------------------------------------------------------------------------
Ornstein-Uhlenbeck Process with BIC Model Selection**
TYPE L95% E[X] U95%
E[F|1H] -42.1 -23.6 -5.1
E[F|NOW] -51.0 -51.0 -51.0
Deep Learning: Quantile GRU v6.0 (Neural Network with Calibrated Uncertainty)
TYPE L95% L68% E[X] U68% U95%
E[F|1H] -28.8 -25.3 -24.0 -22.5 -20.2
E[F|NOW] -59.9 -52.7 -50.1 -47.0 -42.2
Enhanced Ornstein-Uhlenbeck Process (BIC-optimized AR order, continuous-time Kalman filtering)
MODEL NOTES:
** O-U Process validated on 61,166 games (MAE: 8.50 pts, well-calibrated 68%/95% confidence intervals)
** GRU v6.0 validated on Fall 2025 (MAE: 10.99 pts, 5.2% better than previous LSTM)
CHART LEGEND:
1) Blue line: O-U Improved model trained on first-half data, locked at halftime (68% and 95% CI shown)
2) Green line: O-U Improved model continuously retrained as new plays arrive (68% CI shown)
3) Both lines use the same statistical model; divergence shows how live events update predictions
4) Model automatically selects AR(1) or AR(2) using BIC for optimal fit to irregular scoring events
Updated: Monday, Dec 15 01:22:17 AM EST
Back