Model Predictions
| Model | Manhattan | Canisius | Spread | Result |
|---|---|---|---|---|
| Elo | 78.3% | 21.7% | - | โ |
| Bradley-Terry | 80.4% | 19.6% | - | โ |
| Bradley-Terry Recency | 81.8% | 18.2% | - | โ |
| Margin | 57.1% | 42.9% | - | โ |
| Margin Recency | 58.2% | 41.8% | - | โ |
| Pythagorean | 61.1% | 38.9% | - | โ |
| Adjusted Efficiency | 78.4% | 21.6% | - | โ |
| Log Adjusted | 78.3% | 21.7% | - | โ |
| Points Off/Def | 54.7% | 45.3% | - | โ |
| Points Off/Def Recency | 56.0% | 44.0% | - | โ |
| Core Ensemble | 73.4% | 26.6% | - | โ |
| Recency Ensemble | 73.6% | 26.4% | - | โ |
| Dynamic Bradley-Terry | 83.0% | 17.0% | - | โ |
| Adjusted Context Blend | 79.1% | 20.9% | - | โ |
Actual: Canisius -3 (72-75). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.