Can We Really Predict Which Football Players Will Succeed?

Jonathan Feldman

2025

Abstract

Predicting whether a football player will achieve their projected career potential is a key challenge for clubs and scouts. This study analyzes the career outcomes of 8,770 players from the European Soccer Database (2008–2016), using FIFA video game potential ratings as a proxy for projected potential. To account for the increasing difficulty of skill improvements at higher levels, we apply logarithmic scaling when calculating achievement ratios. Predictive models were trained on two cohorts: players with complete career data and those with early-career data (up to age 21). Early-career models achieved moderate predictive performance (ROC AUC = 0.79), reflecting the challenge of identifying long-term success based on limited early observations. SHAP analysis shows that growth trajectory features, including early improvement and development patterns, contribute more to success predictions than static physical or technical attributes. We define success as fulfilling projected potential according to the FIFA rating system – a standardized but subjective benchmark. While this does not capture all real-world outcomes, it enables large-scale analysis of developmental trajectories. These results suggest that tracking player development over time provides better guidance for talent decisions than relying solely on early physical assessments.

Paper Citation

in Harvard Style

Feldman J. (2025). Can We Really Predict Which Football Players Will Succeed?. In Proceedings of the 13th International Conference on Sport Sciences Research and Technology Support - Volume 1: icSPORTS; ISBN 978-989-758-771-9, SciTePress, pages 38-49. DOI: 10.5220/0013671000003988

in Bibtex Style

@conference{icsports25,
author={Jonathan Feldman},
title={Can We Really Predict Which Football Players Will Succeed?},
booktitle={Proceedings of the 13th International Conference on Sport Sciences Research and Technology Support - Volume 1: icSPORTS},
year={2025},
pages={38-49},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013671000003988},
isbn={978-989-758-771-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Sport Sciences Research and Technology Support - Volume 1: icSPORTS
TI - Can We Really Predict Which Football Players Will Succeed?
SN - 978-989-758-771-9
AU - Feldman J.
PY - 2025
SP - 38
EP - 49
DO - 10.5220/0013671000003988
PB - SciTePress