Model Predictions
| Model | Canisius | Fairfield | Spread | Result |
|---|---|---|---|---|
| Elo | 21.3% | 78.7% | - | โ |
| Bradley-Terry | 37.0% | 63.0% | - | โ |
| Bradley-Terry Recency | 36.0% | 64.0% | - | โ |
| Margin | 28.4% | 71.6% | - | โ |
| Margin Recency | 27.8% | 72.2% | - | โ |
| Pythagorean | 45.5% | 54.5% | - | โ |
| Adjusted Efficiency | 28.0% | 72.0% | - | โ |
| Log Adjusted | 27.9% | 72.1% | - | โ |
| Points Off/Def | 26.7% | 73.3% | - | โ |
| Points Off/Def Recency | 26.1% | 73.9% | - | โ |
| Core Ensemble | 29.6% | 70.4% | - | โ |
| Recency Ensemble | 29.5% | 70.5% | - | โ |
| Dynamic Bradley-Terry | 30.4% | 69.6% | - | โ |
| Adjusted Context Blend | 15.3% | 84.7% | - | โ |
Actual: Fairfield +12 (69-57). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.