Can Locomotor Performance Predict the Final Result of a Football Match? A Machine Learning Approach

The aim of this study was to predict the match outcome using locomotor-performance-related data from teams in both Spanish professional leagues. All matches from the first and second Spanish divisions (LaLiga and LaLiga2, respectively) across two consecutive seasons were used. The locomotor variables were as follows: total distance (TD) and distance covered at >21 km·h^-1 (HSR), distinguishing between different game moments (in-possession, out-of-possession, and ball stopping). Match outcomes (win/lose) were predicted using a LASSO-regularized logistic regression based on standardized locomotor variables. Model performance was evaluated through accuracy, precision, recall, F1-scores, and AUC-ROC, demonstrating strong discriminative capacity and balanced classification across outcomes. The LASSO-regularized logistic regression model achieved strong predictive accuracy (76.8%) and balanced classification performance (F1 = 0.77; AUC = 0.85). TDnoPosmin, TD21posmin, TD21min, and TDoffmin emerged as key positive predictors of victory, whereas TD21noPosmin, TDmin, and TDposmin were negatively associated with winning. LASSO regularization confirmed the stability and robustness of these predictors, indicating limited overfitting and consistency. Match outcomes were accurately predicted from locomotor variables, with high-intensity activity out of possession emerging as the key determinant of success. Match success was primarily linked to high-intensity activity during the defensive phase, highlighting the need for further research on these critical phases of play.