A Bayesian approach to predict performance in football: a case study.

Abstract

Football is the most practiced sport in the world and can be said to be unpredictable, i.e., it sometimes presents surprising results, such as a weaker team overcoming a stronger one. As an illustration, the Brazilian Championship Series A (Brasileirão) has historically been shown to be one of the most outstanding examples of this unpredictability, presenting a large number of unexpected outcomes (perhaps given its high competitiveness). This study unraveled attack and defense patterns that may help predict match results for the 2022 Brazilian Championship Series A, using data-driven models considering 10 variations of the Poisson countable regression model (including hierarchy, overdispersion, time-varying parameters, or informative priors). As informative priors, the 2021 Brazilian Championship Series A's information from the previous season was adopted for each team's attack and defense advantage estimations. The proposed methodology is not only helpful for match prediction but also beneficial for quantifying each team's attack and defense dynamic performances. To assess the quality of the forecasts, the de Finetti measure was used, in addition to comparing the goodness-of-fit using the leave-one-out cross-validation metric, in which the models presented satisfactory results. According to most of the metrics used to compare the methods, the dynamic Poisson model with zero inflation provided the best results, and, to the best of our knowledge, this is the first time this model has been used in a subjective football match context. An online framework was developed, providing interactive access to the results obtained in this study in a Shiny app.