🐻⬇️🏀

2025-2026 NCAAW Model Performance Analysis

Scope

All scored games in the selected league and season. AP Poll is excluded here.

Source season: 2698 games. Comparative evidence is unavailable until a verified common holdout cohort is recorded.

Model Catalog

Comparative evaluation is held for this season. Legacy/full-fit rows are not ranked because they do not prove one shared out-of-sample game cohort. Reason: pending_cohort_contract.

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.

Log Loss Brier AUC Accuracy

No cohort-receipted rolling validation is available for this league/season yet. Legacy rolling rows are intentionally hidden until their common-cohort promotion contract is installed.

Model Performance Leaderboard

Models are ranked only by AUC on one verified common 7-day holdout cohort. Unsupported or pending families are never treated as zero.

# Model Cohort AUC 7d Acc 7d Brier 7d LogLoss 7d n 7d
- Elo Elo Streaming paired-comparison rating with recency baked into sequential updates. More → PENDING
receipt required
- - - - -
- Bradley-Terry Bradley-Terry Static logistic paired-comparison model with one team strength parameter. More → PENDING
receipt required
- - - - -
- Bradley-Terry Recency Bradley-Terry Recency Static Bradley-Terry with exponential recency weights on newer games. More → PENDING
receipt required
- - - - -
- Margin Margin Linear team-strength model fit on point differential instead of binary wins. More → PENDING
receipt required
- - - - -
- Margin Recency Margin Recency Margin regression with exponential recency weights on newer games. More → PENDING
receipt required
- - - - -
- Pythagorean Pythagorean Pythagorean win expectation from raw points scored and allowed. More → PENDING
receipt required
- - - - -
- Efficiency Efficiency Tempo-adjusted efficiency version of Pythagorean ratings. More → PENDING
receipt required
- - - - -
- Adjusted Efficiency Adjusted Efficiency Opponent-adjusted efficiency model with separate offensive and defensive components. More → PENDING
receipt required
- - - - -
- Log Adjusted Log Adjusted Log-scale adjusted efficiency model that downweights blowout leverage. More → PENDING
receipt required
- - - - -
- Points Off/Def Points Off/Def Raw points regression with separate offensive and defensive team parameters. More → PENDING
receipt required
- - - - -
- Points Off/Def Recency Points Off/Def Recency Off/def points regression with exponential recency weights. More → PENDING
receipt required
- - - - -
- Core Ensemble Core Ensemble Equal-logit blend of Elo, recency BT, recency margin, log-adjusted pyth, and points off/def. More → PENDING
receipt required
- - - - -
- Recency Ensemble Recency Ensemble Equal-logit blend of Elo, recency BT, recency margin, log-adjusted pyth, and recency points off/def. More → PENDING
receipt required
- - - - -
- Home Team Baseline Home Team Baseline Always favor the home team with a fixed prior. More → PENDING
receipt required
- - - - -
- Avg Margin Baseline Avg Margin Baseline Predict from simple average scoring margin in the training window. More → PENDING
receipt required
- - - - -
- Dynamic Bradley-Terry Dynamic Bradley-Terry Time-evolving paired-comparison model with latent team strength drift. More → PENDING
receipt required
- - - - -
- Adjusted Context Blend Adjusted Context Blend Experimental context-heavy win model blending strong team components with rest and venue context. More → PENDING
receipt required
- - - - -

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