Prediction of Match Outcomes with Multivariate Statistical Methods for the Group Stage in the UEFA Champions League

Abstract

Abstract The aim of this study was to analyse the win, draw, and loss outcomes of soccer matches with situational variables and performance indicators. Data from group stage matches spanning the ten years between the 2010/2011 and 2019/2020 seasons in the European Champions League, were used. One-way analysis of variance (ANOVA) and Tukey HSD (honestly significant difference) tests indicated performance indicators which affected the outcome of matches. K-mean clustering, with statistically significant variables, categorized the quality of the opposition into three clusters: weak, balanced, and strong. Multidimensional scaling (MDS) and decision tree analysis were applied to each of these clusters, highlighting that performance indicators of the teams differed according to the quality of their opponent. Furthermore, according to the decision tree analysis, certain performance indicators, including scoring first and shots on target, increased the chances of winning regardless of the quality of the opposition. Finally, particular performance indicators increased the chance of winning, while others decreased this, in accordance with the quality of the opposition. These findings can help coaches develop different strategies, before or during the match, based on the quality of opponents, situational variables, and performance indicators.