Model Predictions
| Model | Canisius | Rider | Spread | Result |
|---|---|---|---|---|
| Elo | 19.7% | 80.3% | - | โ |
| Bradley-Terry | 35.3% | 64.7% | - | โ |
| Bradley-Terry Recency | 35.5% | 64.5% | - | โ |
| Margin | 35.4% | 64.6% | - | โ |
| Margin Recency | 34.6% | 65.4% | - | โ |
| Pythagorean | 33.4% | 66.6% | - | โ |
| Adjusted Efficiency | 31.2% | 68.8% | - | โ |
| Log Adjusted | 31.5% | 68.5% | - | โ |
| Points Off/Def | 27.5% | 72.5% | - | โ |
| Points Off/Def Recency | 26.6% | 73.4% | - | โ |
| Core Ensemble | 32.6% | 67.4% | - | โ |
| Recency Ensemble | 32.5% | 67.5% | - | โ |
| Dynamic Bradley-Terry | 28.5% | 71.5% | - | โ |
| Adjusted Context Blend | 11.0% | 89.0% | - | โ |
Actual: Rider +14 (83-69). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.