Bayesian estimation of in-game home team win probability for National Basketball Association games

TL;DR

This paper adapts and improves a Bayesian model for estimating in-game home team win probabilities specifically for NBA games, comparing its performance with existing methods and demonstrating its application on a real game.

Contribution

It introduces modifications to a previous college basketball model for NBA games and evaluates its performance against other methods and ESPN's estimate.

Findings

Enhanced model shows improved accuracy over previous methods

Model comparison indicates better performance for NBA games

Application to a real game demonstrates practical utility

Abstract

Maddox, et al. (2022) establish a new win probability estimation for college basketball and compared the results with previous methods of Stern (1994), Desphande and Jensen (2016) and Benz (2019). This paper proposes modifications to the approach of Maddox, et al. (2022) for the NBA game and investigates the performance of the model. Enhancements to the model are developed, and the resulting adjusted model is compared with existing methods and to the ESPN counterpart. To illustrate utility, all methods are applied to the November 23, 2019 game between the Chicago Bulls and Charlotte Hornets.