Model Predictions
| Model | Cornell | Harvard | Spread | Result |
|---|---|---|---|---|
| Elo | 13.9% | 86.1% | - | โ |
| Bradley-Terry | 23.4% | 76.6% | - | โ |
| Bradley-Terry Recency | 24.6% | 75.4% | - | โ |
| Margin | 19.6% | 80.4% | - | โ |
| Margin Recency | 19.7% | 80.3% | - | โ |
| Pythagorean | 28.4% | 71.6% | - | โ |
| Adjusted Efficiency | 9.7% | 90.3% | - | โ |
| Log Adjusted | 9.6% | 90.4% | - | โ |
| Points Off/Def | 19.9% | 80.1% | - | โ |
| Points Off/Def Recency | 20.1% | 79.9% | - | โ |
| Core Ensemble | 20.0% | 80.0% | - | โ |
| Recency Ensemble | 20.1% | 79.9% | - | โ |
| Dynamic Bradley-Terry | 34.9% | 65.1% | - | โ |
| Adjusted Context Blend | 5.7% | 94.3% | - | โ |
Actual: Harvard -13 (69-82). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.