Using machine learning to determine the positions of professional soccer players in terms of biomechanical variables

Abstract

This study aimed to predict professional soccer players’ positions with machine learning according to certain locomotor demands. Data from 20 male professional soccer players (five defenders, eight midfielders, and seven attackers) from the same team were tracked daily with a global navigation satellite system. A total of 1910 individual training sessions were recorded. The 10-fold cross-validation method was used. Soccer player positions were predicted using predictive models created with random forest (RF), gradient boosting tree, bagging classification, and regression trees algorithms, and the results were evaluated with comprehensive performance measures. Ratios and an importance plot were used to analyze the importance of the variables according to their contributions to the estimation. The findings show that the RF model achieved 100% accuracy, which means that RF can predict all player positions (100%). Running distance (26.5%), total distance (17.2%), and player load (15.8%) were the three variables that contributed the most to the estimation of the RF model and were the most important factor in distinguishing player positions. Consequently, our proposed machine learning approach (RF model) can reduce false alarms and player mispositioning.