What should clubs monitor to predict the future value of football players?

Abstract

Huge amounts of money are invested every year by football clubs on transfers. For both growth and survival, it is crucial for recruiting departments to make smart choices when targeting players. Therefore, it is important to identify the right parameters to monitor to predict market value. The following paper aims at determining the relevant features that successfully forecast the future value for football players. Success is measured against their market value from TransferMarkt. In particular, we perform this prediction separately for each position on the pitch, acknowledging the different characteristics and criteria relevant for each role on the pitch. To select prominent features, we use Lasso regressions and Random Forest algorithms. Some obvious variables are selected but we also observe some subtle dependencies between features and future market value. Notably, the median league market value is uncovered to have a strong predictive power. Finally, we rank the Golden Boy nominees using our forecasts and show our methodology can successfully compare football players based on their quality.