Updated: Monday, Dec 15 01:24:07 AM EST
Jacksonville Dolphins vs Texas A&M Aggies (Final)
75 - 112, (Margin: -37, Total: 187)
Reed Arena
Second-Half conditional estimates based on a margin of -25.0 points and 77.0 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)
======================================================================================================================================================
68.3 94.5 -26.2 (-36.3, -16.2) 162.8 (150.7, 175.0) 0.0 0.0 -26.2 162.8 2.0% 98.0% -5021
------------------------------------------------------------------------------------------------------------------------------------------------------
Live conditional estimates per 5 Minutes (+/- 1 deviation) (models are continuously adjusted)
------------------------------------------------------------------------------------------------------------------------------------------------------
TYPE 5M 10M 15M 20M 25M 30M 35M 40M
======================================================================================================================================================
E[SP] - - - - - - - -39.3
P[W] - - - - - - - 100.0%
ODDS - - - - - - - -
------------------------------------------------------------------------------------------------------------------------------------------------------
Ornstein-Uhlenbeck Process with BIC Model Selection**
TYPE L95% E[X] U95%
E[F|1H] -45.2 -22.6 0.0
E[F|NOW] -42.1 -39.0 -35.8
Deep Learning: Quantile GRU v6.0 (Neural Network with Calibrated Uncertainty)
TYPE L95% L68% E[X] U68% U95%
E[F|1H] -30.0 -26.3 -25.0 -23.4 -21.0
E[F|NOW] -45.9 -40.3 -38.4 -35.9 -32.3
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 01:24:07 AM EST
Back