Model Predictions
| Model | Manhattan | Rider | Spread | Result |
|---|---|---|---|---|
| Elo | 20.1% | 79.9% | - | โ |
| Bradley-Terry | 33.2% | 66.8% | - | โ |
| Bradley-Terry Recency | 32.7% | 67.3% | - | โ |
| Margin | 44.2% | 55.8% | - | โ |
| Margin Recency | 44.2% | 55.8% | - | โ |
| Pythagorean | 53.5% | 46.5% | - | โ |
| Adjusted Efficiency | 56.1% | 43.9% | - | โ |
| Log Adjusted | 56.2% | 43.8% | - | โ |
| Points Off/Def | 45.2% | 54.8% | - | โ |
| Points Off/Def Recency | 45.2% | 54.8% | - | โ |
| Core Ensemble | 43.9% | 56.1% | - | โ |
| Recency Ensemble | 43.9% | 56.1% | - | โ |
| Dynamic Bradley-Terry | 41.2% | 58.8% | - | โ |
| Adjusted Context Blend | 14.7% | 85.3% | - | โ |
Actual: Rider +2 (67-65). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.