Model Predictions
| Model | Siena | Canisius | Spread | Result |
|---|---|---|---|---|
| Elo | 68.0% | 32.0% | - | โ |
| Bradley-Terry | 69.6% | 30.4% | - | โ |
| Bradley-Terry Recency | 70.7% | 29.3% | - | โ |
| Margin | 48.5% | 51.5% | - | โ |
| Margin Recency | 49.5% | 50.5% | - | โ |
| Pythagorean | 59.8% | 40.2% | - | โ |
| Adjusted Efficiency | 71.6% | 28.4% | - | โ |
| Log Adjusted | 71.5% | 28.5% | - | โ |
| Points Off/Def | 44.1% | 55.9% | - | โ |
| Points Off/Def Recency | 45.1% | 54.9% | - | โ |
| Core Ensemble | 62.9% | 37.1% | - | โ |
| Recency Ensemble | 63.1% | 36.9% | - | โ |
| Dynamic Bradley-Terry | 78.6% | 21.4% | - | โ |
| Adjusted Context Blend | 63.4% | 36.6% | - | โ |
Actual: Canisius +7 (84-77). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.