Bayesian estimation of in-game home team win probability for college basketball

TL;DR

This paper introduces two Bayesian methods for estimating and predicting in-game home team win probabilities in college basketball, demonstrating improved performance over existing approaches and illustrating their utility with a high-profile game application.

Contribution

The paper proposes two novel Bayesian estimation techniques that adapt during the game and combine pre-game and in-game data for better win probability predictions.

Findings

New methods outperform existing models in estimation accuracy

Proposed techniques improve prediction during critical game moments

Application to NCAA final demonstrates practical utility

Abstract

Two new Bayesian methods for estimating and predicting in-game home team win probabilities are proposed. The first method has a prior that adjusts as a function of lead differential and time elapsed. The second is an adjusted version of the first, where the adjustment is a linear combination of the Bayesian estimator with a time-weighted pre-game win probability. The proposed methods are compared to existing methods, showing the new methods perform better for both estimation and prediction. The utility is illustrated via an application to the 2016 NCAA Division 1 Championship game.