Comparison of Individualized and Group-Based Machine Learning Approaches to Predict Rate of Perceived Exertion of Professional Football Players

Monitoring fatigue in sport is critical to achieve elite performance and may benefit from machine learning techniques that are liable to predict changes in fatigue state. In this paper we present and compare different machine learning models to predict the Rate of Perceived Exertion (RPE) of training or game sessions for professional football (soccer) players. We compare different approaches to train predictive models in a supervised setting (regression) with a focus on individualized and group-based approaches, i.e. training a specific model for each player or predefined groups of players (full team or clusters defined using unsupervised learning). Both player-informed and player-agnostic models are compared in the group-based approach, i.e. providing or not player id as feature during training and inference. Compared models have been trained on real data collected during a full season of professional football players, and using among others, anthropometric, running activity, heart rate and weather data. The best results are obtained using a player-informed team-based approach with a Random Forest regressor (0.793 MAE, 1.033 RMSE). Results obtained are competitive with the best reported in the literature for this predictive task in elite Football players.