Machine Learning for the Prediction of Football Players’ Market Value in Five European Leagues

European football has become a massive business. Keeping football clubs financially viable depends on accurate player valuations, which underpin balancing incoming and outgoing transfers, contract negotiations, and other expenses. Players’ market values are generally available on public platforms. Still, clubs and analysts increasingly rely on data-driven approaches to enable consistent valuation across leagues, to assess the main drivers of players’ market value, and to early identify the most promising players. This study attempts to predict and interpret football players’ market value in five major European football leagues (England, Spain, Italy, Germany, and France) using match-derived performance statistics and players’ general information. The dataset analyzed comprises about 14,000 player–season observations available through the worldfootballR package, which aggregates data from FBref and Transfermarkt. Five regression algorithms were evaluated within a unified machine learning framework. Model performance was assessed on a test set using RMSE and R2 metrics. Results show that non-linear machine learning models outperform the linear ones. Gradient boosting and neural networks recorded the best predictive performance. Model interpretation techniques reveal playing-time exposure and player age as the main determinants of predicted market value, highlighting the importance of match involvement and career stage in the valuation of football players.