A Bayesian Approach to Predict Football Matches with Changed Home Advantage in Spectator-Free Matches after the COVID-19 Break

Abstract

Since the coronavirus disease 2019 (COVID-19) pandemic, most professional sports events have been held without spectators. It is generally believed that home teams deprived of enthusiastic support from their home fans experience reduced benefits of playing on their home fields, thus becoming less likely to win. This study attempts to confirm if this belief is true in four major European football leagues through statistical analysis. This study proposes a Bayesian hierarchical Poisson model to estimate parameters reflecting the home advantage and the change in such advantage. These parameters are used to improve the performance of machine-learning-based prediction models for football matches played after the COVID-19 break. The study describes the statistical analysis on the impact of the COVID-19 pandemic on football match results in terms of the expected score and goal difference. It also shows that estimated parameters from the proposed model reflect the changed home advantage. Finally, the study verifies that these parameters, when included as additional features, enhance the performance of various football match prediction models. The home advantage in European football matches has changed because of the behind-closed-doors policy implemented due to the COVID-19 pandemic. Using parameters reflecting the pandemic’s impact, it is possible to predict more precise results of spectator-free matches after the COVID-19 break.

Influence of Game Indicators on the Ranking of Teams in the Spanish Soccer League

“…In the major European competitions (i.e., Ligue 1, Serie A, LaLiga, the Premier League, and Bundesliga) during the 2019/2020 season, with fans in the stadia (before the restrictions), home teams scored more goals than visitors [7], because the number of dangerous attacks was higher. In contrast, another study [14] comparing the pre-COVID-19 and COVID-19 period in European soccer matches showed a decrease in the goals scored by home teams in ghost matches, which also affected the points and ranking. Another indicator that was affected during the COVID-19 period, in similar studies [9,12,13], was the higher number of fouls committed by home teams which, in turn, resulted in more yellow cards.…”

“…The following data (game indicators) were collected for each team and match played: (1) yellow cards, (2) red cards, (3) ball possession, (4) total shots, (5) shots on goal, (6) shots off goal, (7) free kicks, (8) corners, (9) offsides, (10) goalkeeper saves, (11) fouls committed, (12) attacks, (13) dangerous attacks, (14) total passes, and (15) tackles. These were the dependent variables.…”

“…Moreover, a study on the four major leagues (i.e., Bundesliga, LaLiga, the Premier League, and Serie A), comparing statistics from before and after the COVID-19 pandemic, indicates a decrease in the expected points and goals scored by the home team. The decrease in the home team's advantage is due to the absence of fans in the stadium during the COVID-19 pandemic [14]. In other words, the performance of the home team is halved when the stadium is empty [7].…”

Soccer’s AI transformation: deep learning’s analysis of soccer’s pandemic research evolution

“…On the other hand, research topics emerged that could be approached in the unique context of the COVID-19 pandemic. For example, the scholarly soccer literature explored whether there was still a significant home-advantage effect in soccer matches played away from home during the pandemic ( McCarrick et al, 2021 ; Lee et al, 2022 ). Through this topic, future research directions can be anticipated as areas where comparative approaches can be made considering the current post-COVID-19 situation.…”

“…Using topic modeling to study research trends can provide useful information along with new ideas for future research ( Lee et al, 2021 , 2022 ). These results can be used to form a body of knowledge by quantitatively analyzing a large number of papers and qualitatively interpreting the discovered knowledge structure to find certain patterns in scattered data ( Miyata et al, 2020 ).…”