Model Predictions
| Model | Buffalo | Canisius | Spread | Result |
|---|---|---|---|---|
| Elo | 26.6% | 73.4% | - | โ |
| Bradley-Terry | 41.2% | 58.8% | - | โ |
| Bradley-Terry Recency | 41.1% | 58.9% | - | โ |
| Margin | 23.0% | 77.0% | - | โ |
| Margin Recency | 23.0% | 77.0% | - | โ |
| Pythagorean | 47.3% | 52.7% | - | โ |
| Adjusted Efficiency | 27.2% | 72.8% | - | โ |
| Log Adjusted | 27.5% | 72.5% | - | โ |
| Points Off/Def | 21.4% | 78.6% | - | โ |
| Points Off/Def Recency | 21.2% | 78.8% | - | โ |
| Core Ensemble | 29.5% | 70.5% | - | โ |
| Recency Ensemble | 29.5% | 70.5% | - | โ |
| Dynamic Bradley-Terry | 31.0% | 69.0% | - | โ |
| Adjusted Context Blend | 7.7% | 92.3% | - | โ |
Actual: Canisius +6 (71-65). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.