Model Predictions
| Model | Michigan | UCLA | Spread | Result |
|---|---|---|---|---|
| Elo | 16.0% | 84.0% | - | โ |
| Bradley-Terry | 33.5% | 66.5% | - | โ |
| Bradley-Terry Recency | 34.5% | 65.5% | - | โ |
| Margin | 32.2% | 67.8% | - | โ |
| Margin Recency | 33.0% | 67.0% | - | โ |
| Pythagorean | 42.3% | 57.7% | - | โ |
| Adjusted Efficiency | 31.8% | 68.2% | - | โ |
| Log Adjusted | 31.6% | 68.4% | - | โ |
| Points Off/Def | 35.7% | 64.3% | - | โ |
| Points Off/Def Recency | 36.7% | 63.3% | - | โ |
| Core Ensemble | 38.2% | 61.8% | - | โ |
| Recency Ensemble | 38.4% | 61.6% | - | โ |
| Dynamic Bradley-Terry | 61.4% | 38.6% | - | โ |
| Adjusted Context Blend | 8.4% | 91.6% | - | โ |
Actual: UCLA -5 (76-81). Win probabilities: out-of-sample forecasts from the weekly fit before the game, the same forecasts as the model pages.