🐻⬇️🏀

2017-2018 NCAAMD2 Model Performance

Season
2026-2027 2025-2026 2024-2025 2023-2024 2022-2023 2021-2022 2020-2021 2019-2020 2018-2019 2017-2018 2016-2017 2015-2016 2014-2015 2013-2014 2012-2013

Every ranked model predicted the same 44 games (2017-12-10 to 2018-03-24, 15 weekly windows) out of sample: each week's games were predicted by models fit only on the season's earlier games.

Model Catalog · Player models

Model Performance Leaderboard

Ranked by full-season AUC. The final week is the season's last 7 played days (4 games, 2018-03-18 to 2018-03-24), predicted from every earlier game: a small sample that shows the latest form.

# Model AUC Acc Brier LogLoss AUC final wk Acc final wk
1 Home Team Baseline Home Team Baseline Always favor the home team with a fixed prior. More → 0.725 72.7% 0.215 0.621 1.000 100.0%
- Adjusted Context Blend Adjusted Context Blend Chronologically trained component blend with rest and signed venue context. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 100.0%
- Adjusted Efficiency Adjusted Efficiency Opponent-adjusted efficiency model with separate offensive and defensive components. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 75.0%
- Avg Margin Baseline Avg Margin Baseline Predict from simple average scoring margin in the training window. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 75.0%
- Bradley-Terry Bradley-Terry Static logistic paired-comparison model with one team strength parameter. More →
not compared: predicted 16 of 44 games
 - - - - 0.250 50.0%
- Bradley-Terry Recency Bradley-Terry Recency Static Bradley-Terry with exponential recency weights on newer games. More →
not compared: predicted 16 of 44 games
 - - - - 0.250 50.0%
- Core Ensemble Core Ensemble Equal-logit blend of Elo, recency BT, recency margin, log-adjusted pyth, and points off/def. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 75.0%
- Dynamic Bradley-Terry Dynamic Bradley-Terry Time-evolving paired-comparison model with latent team strength drift. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 100.0%
- Elo Elo Streaming paired-comparison rating with recency baked into sequential updates. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 100.0%
- Log Adjusted Log Adjusted Log-scale adjusted efficiency model that downweights blowout leverage. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 75.0%
- Margin Margin Linear team-strength model fit on point differential instead of binary wins. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 75.0%
- Margin Recency Margin Recency Margin regression with exponential recency weights on newer games. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 75.0%
- Points Off/Def Points Off/Def Raw points regression with separate offensive and defensive team parameters. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 100.0%
- Points Off/Def Recency Points Off/Def Recency Off/def points regression with exponential recency weights. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 100.0%
- Pythagorean Pythagorean Pythagorean win expectation from raw points scored and allowed. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 75.0%
- Recency Ensemble Recency Ensemble Equal-logit blend of Elo, recency BT, recency margin, log-adjusted pyth, and recency points off/def. More →
not compared: predicted 16 of 44 games
 - - - - 1.000 75.0%

Methodology

Out-of-sample windows

  • The season is split into 7-day windows ending on its last played day
  • Each window is predicted by models refit on all earlier games of the season
  • The first window starts after 21 days of games
  • Every model is scored on the same games; a model that cannot predict most of them is listed as not compared

Elo / Bradley-Terry

  • Elo: the published league Elo (preseason priors and carryover where configured), frozen at the window start
  • Bradley-Terry: static logistic fit on the earlier games
  • Recency variants weight games with a 120-day half-life in NCAA leagues (keeping the non-conference games that link conferences) and a 30-day half-life in pro leagues

Pythagorean and margin models

  • Raw, adjusted and log-adjusted Pythagorean from scores; efficiency from box-score possessions
  • Margin: ridge regression on point margin with a learned home advantage
  • Ensembles average the log-odds of five families

Baselines

  • Home Team: the home team wins 60% (50% at neutral sites)
  • Avg Margin: the higher average margin so far wins
  • Models should beat these to add value