The Value of Players in the Top Five Football Leagues for the 24-25 Season Based on Multiple Factors
DOI:
https://doi.org/10.61173/p15km722Keywords:
Top Five Football Leagues, Multiple Fac-tors, XGBoostAbstract
The top five football leagues, as one of the most high-profile sporting events, entail enormous commercial value, making player valuation in these leagues a focal point. Analyzing the influencing factors of transfer values helps clubs formulate strategies and promotes the development of the football market. This study leverages descriptive statistics and the XGBoost regression model, analyzing a Kaggle dataset of 2024-25 season player performance. Key findings show 20-28-year-olds command higher transfer values, with a general decline after 30. The Premier League leads in player valuation, with other leagues 40-60% lower. Attacking positions far outpace defensive roles in market price. The eXtreme Gradient Boosting (XGBoost) weight analysis for four positions—forwards, midfielders, defenders, and goalkeepers—reveals that offensive-type data tailored to each position (such as scoring opportunities created for forwards, average carrying distance for defenders, etc.) are critical determinants of player transfer values. Specifically, defensive players now require offensive integration to achieve high valuation, with key factors including forward ball carries and long-pass organization. Traditional defensive metrics have lost weight in valuation models, while offensive attributes have emerged as primary value drivers.
References
[1] Yue Quan, Cheng Cheng, Chen Zhihong. The Influence of the Team’s Market Value on Sports Performance Based on Least Absolute Deviations Regression and Its Management Implications—Data from the 2020 UEFA European Football Championship. Journal of Sichuan Vocational and Technical College, 2022, 32(6): 112-117.
[2] Yunus Koloğlu, Hasan Birinci, Sevde Ilgaz Kanalmaz, Burhan Özyılmaz. A Multiple Linear Regression Approach for Estimating the Market Value of Football Players in Forward Position. 2018.
[3] Ma Rui. Research on the Market Value of Professional Football Players and Its Influencing Factors. Tianjin University of Finance and Economics, 2020.
[4] Liao Bin, Wang Zhining, Li Min, Sun Ruina. A Method for Predicting the Market Value of Football Players and Analyzing Their Characteristics by Integrating the XGBoost and SHAP Models. Computer Science, 2022, 49(12): 691-702.
[5] Rehemujiang Repukati. A Study on the Correlation between the Relative Age Effect of Football Players and Their Market Value—Taking the Men’s Youth Football Teams of 39 Countries as an Example. Beijing Sport University, 2021.
[6] Xu Zhong. Analysis of the Factors Influencing the Commercial Value of Outstanding Athletes in China. Journal of Sports Adult Education, 2014, 30(5): 50-52.
[7] Claudio Lucifora, Rob Simmons. Superstar effect in sport Evidence from Italian soccer. Journal of Sports Economics, 2003, 1(4):35 - 55.
[8] Zhang Lei. A Study on the Current Situation and Development Countermeasures of Domestic Transfers of Players in the Chinese Professional Football League. Beijing Sport University, 2009; Zheng Lu. A Study on the Transfer System of Chinese Professional Football Players. Sports World (Academic Edition), 2010, (5): 104-106.
[9] Shen Qijie. Predicting the value of football players: machine learning techniques and sensitivity analysis based on FIFA and real-world statistical datasets. Applied Intelligence. 2025, 55.
[10] Hubert. Sidorowicz. Players_data-2024_2025(Dataset). 2025-4-25. 2025-4-18. https://www.kaggle.com/datasets/ hubertsidorowicz/football-players-stats-2024-2025/data
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.

This work is licensed under a Creative Commons Attribution 4.0 International License.
