2025 WNBA Model Performance Analysis
Scope
All scored games in the selected league and season. AP Poll is excluded here.
Season
Comparing prediction accuracy across 163 games using multiple rating models.
7-day holdout coverage: 16/17 models .
Rolling Holdout Curves
Each point is a strict weekly holdout: train on all games before that week, test on that week. This first version uses a 21-day warmup, then 7-day holdouts stepped forward weekly.
Weekly strict holdout log loss. Lower is better. Showing 16 models across 21 windows. Click legend items to hide/show series.
Recent Window Winners
| Holdout | Best | Log Loss | Runner-up | Models |
|---|---|---|---|---|
| Oct 9 - Oct 10 | Elo | 0.222 | Bradley-Terry Recency (0.352) | 16 |
| Oct 2 - Oct 8 | Elo | 0.479 | Bradley-Terry Recency (0.500) | 16 |
| Sep 25 - Oct 1 | Home Team Baseline | 0.592 | Points Off/Def Recency (0.702) | 16 |
| Sep 18 - Sep 24 | Home Team Baseline | 0.685 | Points Off/Def Recency (0.699) | 16 |
| Sep 11 - Sep 17 | Points Off/Def | 0.610 | Margin (0.612) | 16 |
| Sep 4 - Sep 10 | Dynamic Bradley-Terry | 0.508 | Adjusted Context Blend (0.514) | 16 |
| Aug 28 - Sep 3 | Elo | 0.473 | Adjusted Context Blend (0.474) | 16 |
| Aug 21 - Aug 27 | Elo | 0.553 | Bradley-Terry Recency (0.579) | 16 |
Model Performance Leaderboard
Models ranked by strict holdout AUC when available (fallback: full-season AUC). Hover over column headers for explanations.
| # | Model | 7d Split | AUC | Acc | Brier | LogLoss | n | AUC 7d | Acc 7d | Brier 7d | n 7d |
|---|---|---|---|---|---|---|---|---|---|---|---|
| - | Elo Elo Streaming paired-comparison rating with recency baked into sequential updates. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.099 | 3 |
| - | Bradley-Terry Bradley-Terry Static logistic paired-comparison model with one team strength parameter. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.165 | 3 |
| - | Bradley-Terry Recency Bradley-Terry Recency Static Bradley-Terry with exponential recency weights on newer games. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.127 | 3 |
| - | Margin Margin Linear team-strength model fit on point differential instead of binary wins. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 33.3% | 0.263 | 3 |
| - | Margin Recency Margin Recency Margin regression with exponential recency weights on newer games. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.209 | 3 |
| - | Pythagorean Pythagorean Pythagorean win expectation from raw points scored and allowed. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.232 | 3 |
| - | Efficiency Efficiency Tempo-adjusted efficiency version of Pythagorean ratings. More → |
FULL
no 7d
|
- | - | - | - | 0 | - | - | - | 0 |
| - | Adjusted Efficiency Adjusted Efficiency Opponent-adjusted efficiency model with separate offensive and defensive components. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.229 | 3 |
| - | Log Adjusted Log Adjusted Log-scale adjusted efficiency model that downweights blowout leverage. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.231 | 3 |
| - | Points Off/Def Points Off/Def Raw points regression with separate offensive and defensive team parameters. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 33.3% | 0.265 | 3 |
| - | Points Off/Def Recency Points Off/Def Recency Off/def points regression with exponential recency weights. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.212 | 3 |
| - | Core Ensemble Core Ensemble Equal-logit blend of Elo, recency BT, recency margin, log-adjusted pyth, and points off/def. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.178 | 3 |
| - | Recency Ensemble Recency Ensemble Equal-logit blend of Elo, recency BT, recency margin, log-adjusted pyth, and recency points off/def. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.169 | 3 |
| - | Home Team Baseline Home Team Baseline Always favor the home team with a fixed prior. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 33.3% | 0.293 | 3 |
| - | Avg Margin Baseline Avg Margin Baseline Predict from simple average scoring margin in the training window. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.223 | 3 |
| - | Dynamic Bradley-Terry Dynamic Bradley-Terry Time-evolving paired-comparison model with latent team strength drift. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.179 | 3 |
| - | Adjusted Context Blend Adjusted Context Blend Experimental context-heavy win model blending strong team components with rest and venue context. More → |
STRICT
3g
|
- | - | - | - | 0 | - | 100.0% | 0.200 | 3 |
Methodology
ELO / Bradley-Terry
- ELO: Iterative updates, K=64, HCA=100
- BT: Static logistic regression on all games
- Both model win probability, not margin
- ELO updates after each game; BT fits once
Pythagorean Models
- Raw: Classic points scored/allowed formula
- Efficiency: Pace-adjusted (pts per possession)
- Adjusted: Opponent-adjusted efficiency
- Log: Log-linear multiplicative scale
Margin Regression
- Team-level ridge regression on point margin
- Linear Bradley-Terry (margin target)
- Alpha=0.05 (CV-tuned)
- Learns home advantage from data (~6 pts)
Baselines
- Home Team: Always predict home wins (60%)
- Avg Margin: Higher average margin wins
- Models should beat these to add value