Model Predictions
| Model | Fairfield | Canisius | Spread | Result |
|---|---|---|---|---|
| Elo | 63.3% | 36.7% | - | โ |
| Bradley-Terry | 65.5% | 34.5% | - | โ |
| Bradley-Terry Recency | 67.5% | 32.5% | - | โ |
| Margin | 40.7% | 59.3% | - | โ |
| Margin Recency | 41.2% | 58.8% | - | โ |
| Pythagorean | 52.3% | 47.7% | - | โ |
| Adjusted Efficiency | 50.2% | 49.8% | - | โ |
| Log Adjusted | 49.8% | 50.2% | - | โ |
| Points Off/Def | 36.8% | 63.2% | - | โ |
| Points Off/Def Recency | 37.5% | 62.5% | - | โ |
| Core Ensemble | 54.3% | 45.7% | - | โ |
| Recency Ensemble | 54.4% | 45.6% | - | โ |
| Dynamic Bradley-Terry | 74.9% | 25.1% | - | โ |
| Adjusted Context Blend | 51.4% | 48.6% | - | โ |
Actual: Canisius -5 (71-76). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.