Model Predictions
| Model | Harvard | Brown | Spread | Result |
|---|---|---|---|---|
| Elo | 26.4% | 73.6% | - | โ |
| Bradley-Terry | 52.8% | 47.2% | - | โ |
| Bradley-Terry Recency | 48.9% | 51.1% | - | โ |
| Margin | 45.1% | 54.9% | - | โ |
| Margin Recency | 43.6% | 56.4% | - | โ |
| Pythagorean | 50.5% | 49.5% | - | โ |
| Adjusted Efficiency | 64.8% | 35.2% | - | โ |
| Log Adjusted | 65.0% | 35.0% | - | โ |
| Points Off/Def | 44.1% | 55.9% | - | โ |
| Points Off/Def Recency | 42.3% | 57.7% | - | โ |
| Core Ensemble | 48.7% | 51.3% | - | โ |
| Recency Ensemble | 48.3% | 51.7% | - | โ |
| Dynamic Bradley-Terry | 44.1% | 55.9% | - | โ |
| Adjusted Context Blend | 33.2% | 66.8% | - | โ |
Actual: Brown +5 (91-86). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.