Lasso Multinomial Performance Indicators for in-play Basketball Data
Argyro Damoulaki, Ioannis Ntzoufras, Konstantinos Pelechrinis

TL;DR
This paper introduces a new multinomial logistic regression-based performance indicator for basketball players, called wEPTS, which outperforms existing plus-minus methods by utilizing detailed play-by-play data and regularized models.
Contribution
It develops a novel weighted expected points (wEPTS) measure using multinomial logistic regression, improving accuracy over traditional RAPM indicators with detailed possession data.
Findings
wEPTS outperforms other RAPM measures in predictive accuracy
Lasso regularization yields better performance than ridge regression
Multinomial logistic regression captures discrete scoring outcomes effectively
Abstract
A typical approach to quantify the contribution of each player in basketball uses the plus-minus method. The ratings obtained by such a method are estimated using simple regression models and their regularized variants, with response variable being either the points scored or the point differences. To capture more precisely the effect of each player, detailed possession-based play-by-play data may be used. This is the direction we take in this article, in which we investigate the performance of regularized adjusted plus-minus (RAPM) indicators estimated by different regularized models having as a response the number of points scored in each possession. Therefore, we use possession play-by-play data from all NBA games for the season 2021-22 (322,852 possessions). We initially present simple regression model-based indices starting from the implementation of ridge regression which is the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSports Analytics and Performance · Sports Performance and Training
