Model Predictions
| Model | Maryland | Duke | Spread | Result |
|---|---|---|---|---|
| Elo | 33.9% | 66.1% | - | โ |
| Bradley-Terry | 42.0% | 58.0% | - | โ |
| Bradley-Terry Recency | 43.3% | 56.7% | - | โ |
| Margin | 42.4% | 57.6% | - | โ |
| Margin Recency | 42.4% | 57.6% | - | โ |
| Pythagorean | 50.8% | 49.2% | - | โ |
| Adjusted Efficiency | 59.5% | 40.5% | - | โ |
| Log Adjusted | 59.9% | 40.1% | - | โ |
| Points Off/Def | 43.2% | 56.8% | - | โ |
| Points Off/Def Recency | 43.2% | 56.8% | - | โ |
| Core Ensemble | 47.4% | 52.6% | - | โ |
| Recency Ensemble | 47.4% | 52.6% | - | โ |
| Dynamic Bradley-Terry | 39.7% | 60.3% | - | โ |
| Adjusted Context Blend | 24.2% | 75.8% | - | โ |
Actual: Duke +5 (75-70). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.