Dynamic Bradley-Terry
Time-evolving paired-comparison model with latent team strength drift.
| Status | implemented | Short Name | DynBT |
|---|---|---|---|
| Rating Style | elo | Where Shown | teams rankings, team pages, model performance |
Model Card
Glicko-style paired-comparison model with team uncertainty that expands during idle stretches and tightens with new games. This is the first explicit temporal paired-comparison model beyond static BT plus recency weighting.
Validation on this page uses stored season-level full-fit rows plus strict weekly rolling holdouts. Rolling ranks are based on average weekly log loss in the selected league/season. Current scope: All Games. All scored games in the selected league and season. AP Poll is excluded here.
Selected League / Season
Use the selected scope to inspect this model against peers and across rolling weekly holdouts.
| Full Fit AUC | - · 0 games |
|---|---|
| 7-Day Holdout Log Loss | 0.688 (#14) · 13 games |
| Rolling Avg Log Loss | 0.595 (#10) · 22 windows |
| Window Wins | 0 · 67.5% rolling accuracy |
Full-fit AUC is only available where the older stored-rating batch produced that model for the selected scope. Recency and ensemble families can still have valid 7-day and rolling holdout results even when the full-fit columns are blank.
Rolling Holdout Curves
Selected model plus comparison peers for NCAAM 2025-2026. The focus line is Dynamic Bradley-Terry. Click legend items to hide/show peers.
Weekly strict holdout log loss. Lower is better. Showing 6 models across 22 windows.
Recent Windows
| Holdout | Log Loss | Rank | Winner |
|---|---|---|---|
| Apr 1 - Apr 6 | 0.688 | #14/16 | Log Adjusted (0.537) |
| Mar 25 - Mar 31 | 0.665 | #14/16 | Log Adjusted (0.600) |
| Mar 18 - Mar 24 | 0.578 | #10/16 | Adjusted Efficiency (0.447) |
| Mar 11 - Mar 17 | 0.618 | #7/16 | Margin Recency (0.599) |
| Mar 4 - Mar 10 | 0.595 | #4/16 | Core Ensemble (0.587) |
| Feb 25 - Mar 3 | 0.605 | #8/16 | Points Off/Def Recency (0.578) |
| Feb 18 - Feb 24 | 0.613 | #8/16 | Margin (0.590) |
| Feb 11 - Feb 17 | 0.623 | #7/16 | Recency Ensemble (0.614) |
Selected Scope Peer Table
Comparison snapshot for NCAAM 2025-2026. Rows are ordered by rolling log-loss rank; full-fit AUC may be blank for models that do not have legacy full-season rows stored for this scope.
| Model | Full AUC | AUC Rank | 7d LogLoss | 7d Rank | Rolling LL | Rolling Rank | Windows |
|---|---|---|---|---|---|---|---|
| Margin | 0.822 | #2 | 0.577 | #4 | 0.548 | #1 | 22 |
| Core Ensemble | - | - | 0.620 | #6 | 0.551 | #2 | 22 |
| Recency Ensemble | - | - | 0.637 | #7 | 0.553 | #3 | 22 |
| Margin Recency | - | - | 0.641 | #8 | 0.554 | #4 | 22 |
| Points Off/Def | 0.812 | #5 | 0.579 | #5 | 0.561 | #5 | 22 |
| Dynamic Bradley-Terry | - | - | 0.688 | #14 | 0.595 | #10 | 22 |
League × Season Summary
Cross-scope validation history for Dynamic Bradley-Terry. Rolling ranks are by average weekly log loss.
| League | Season | Full AUC | AUC Rank | 7d LL | 7d Rank | Rolling LL | Rolling Rank | Windows | Wins |
|---|---|---|---|---|---|---|---|---|---|
| WNBA | 2025 | - | - | 0.549 | #6 | 0.628 | #5 | 21 | 1 |
| NCAAWD2 | 2025-2026 | - | - | 0.506 | #8 | 0.569 | #6 | 14 | 2 |
| NCAAW | 2025-2026 | - | - | 0.603 | #9 | 0.555 | #8 | 22 | 0 |
| NCAAMD2 | 2025-2026 | - | - | 0.564 | #10 | 0.597 | #10 | 13 | 0 |
| NCAAM | 2025-2026 | - | - | 0.688 | #14 | 0.595 | #10 | 22 | 0 |
| NBA | 2025-2026 | - | - | 0.590 | #3 | 0.618 | #6 | 26 | 1 |
| GLEAGUE | 2025-2026 | - | - | 0.860 | #14 | 0.691 | #13 | 22 | 3 |
Output Coverage
Stored site-output rows for this model.
| League | Season | Rows |
|---|---|---|
| WNBA | 2025 | 17 |
| NCAAWD3 | 2025-2026 | 584 |
| NCAAWD2 | 2025-2026 | 518 |
| NCAAW | 2025-2026 | 592 |
| NCAAMD3 | 2025-2026 | 649 |
| NCAAMD2 | 2025-2026 | 508 |
| NCAAM | 2025-2026 | 704 |
| NBA | 2025-2026 | 37 |
| GLEAGUE | 2025-2026 | 31 |