The Role of Performance Metrics in Estimating Market Values of Footballers in Europe's Top Five Leagues

Abstract

The transfer economy in football is a multi-billion-dollar industry, where accurate valuation of players is crucial for clubs' financial sustainability and competitive success. This study investigates the role of performance metrics in estimating the market values of football players in Europe's top five leagues (Spain's La Liga, France's Ligue 1, England's Premier League, Italy's Serie A, and Germany's Bundesliga). The study collected 28 performance metrics (e.g., goals, shots per game, assists, and pass success percentage) for 1508 players from the Whoscored platform. Additionally, the players' positions and the leagues they play in were also included as features. These data were combined with market values from the Transfermarkt platform, resulting in a comprehensive dataset. Two main analytical methods were employed: regression and classification. In the regression analysis, seven models (Adaboost, Decision Tree, Gradient Boosting, K Nearest Neighbors, Random Forest, Ridge Regression, and Support Vector Machine) predicted players' market values. The highest accuracy was achieved with the Random Forest algorithm (R-squared: 0.90). In the classification analysis, players' market values were categorized into four classes (low, lower-mid, upper-mid, and high), and their class memberships were predicted based on performance metrics. The CNN algorithm achieved the highest accuracy, with a success rate of 97%. The results indicate that performance metrics significantly contribute to estimating football players' market values, and models based on these metrics can assist clubs in making more informed, data-driven decisions during transfers.

Keywords

• Football player valuation
• Performance metrics
• Transfer market analysis
• Machine learning in sports

References

1. Agresti, A. (2012). Categorical Data Analysis. John Wiley & Sons.
2. Al-Asadi, M. A., & Taşdemir, Ş. (2022). Predict The Value of Football Players Using Fifa Video Game Data And Machine Learning Techniques. IEEE Access, 10, 22631–22645. https://doi.org/10.1109/ACCESS.2022.3154767
3. Arrul, V. S., Subramanian, P., & Mafas, R. (2022, April). Predicting The Football Players’ Market Value Using Neural Network Model: A Data-Driven Approach. In 2022 IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE) (pp. 1–7). IEEE. https://doi.org/10.1109/ICDCECE53908.2022.9792860
4. Aydemir, A. E., Taskaya Temizel, T., & Temizel, A. (2022). A Machine Learning Ensembling Approach to Predicting Transfer Values. SN Computer Science, 3(3), 201. https://doi.org/10.1007/s42979-022-01095-z
5. BBC Sport. (2012). Rangers Football Club Enters Administration. BBC Sport. Retrieved June 10, 2024, from https://www.bbc.com/news/uk-scotland-glasgow-west-17026172
6. Behravan, I., & Razavi, S. M. (2021). A novel machine learning method for estimating football players’ value in the transfer market. Soft Computing, 25(3), 2499–2511. https://doi.org/10.1007/s00500-020-05319-3
7. Bida, M., & Mirzoyan, A. (2023). Factors Influencing Transfer Policy of Football Clubs. Journal of the New Economic Association, 58(1), 66–88. https://doi.org/10.31737/22212264_2023_1_66
8. Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324

9. Carling, C., Williams, A. M., & Reilly, T. (2005). Handbook of soccer match analysis: A systematic approach to improving performance. Routledge.
10. Chai, T., & Draxler, R. R. (2014). Root Mean Square Error (Rmse) or Mean Absolute Error (Mae)? Arguments Against Avoiding Rmse in The Literature. Geoscientific Model Development, 7(3), 1247–1250. https://doi.org/10.5194/gmd-7-1247-2014
11. Deloitte. (2021). Football Money League 2021. Retrieved May 12, 2024, from https://www2.deloitte.com/cn/en/pages/international-business-support/articles/deloitte-football-money-league-2021.html
12. Deloitte. (2024). Football Money League 2024. Retrieved May 20, 2024, from https://www.deloitte.com/uk/en/services/financial-advisory/analysis/deloitte-football-money-league.html
13. Draper, N. R., & Smith, H. (1998). Applied Regression Analysis (3rd ed.). John Wiley & Sons.
14. Fawcett, T. (2006). An Introduction to Roc Analysis. Pattern Recognition Letters, 27(8), 861-874.
15. Franceschi, M., Brocard, J. F., Follert, F., & Gouguet, J. J. (2024). Determinants of football players’ valuation: A systematic review. Journal of Economic Surveys, 38(3), 577-600. https://doi.org/10.1111/joes.12552
16. Friedman, J. H. (2001). Greedy Function Approximation: A Gradient Boosting Machine. Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451
17. Gareth, J., Daniela, W., Trevor, H., & Robert, T. (2013). An introduction to statistical learning: with applications in R. Spinger.
18. Gazzetta dello Sport. (2015). Parma Officially Bankrupt: All Employees Sacked. Retrieved May, 20, 2024 from https://www.gazzetta.it/Calcio/Serie-A/Parma/11-02-2015/ecco-voragine-conti-parma-96-milioni-debiti-100846743143.shtml
19. Giulianotti, R. (1999). Football: A Sociology of The Global Game. Polity Press.
20. Goldblatt, D. (2006). The Ball is Round: A Global History of Soccer. Riverhead Books.
21. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
22. Han, J., Kamber, M., & Pei, J. (2011). Data Mining: Concepts and Techniques (3rd ed.). Elsevier.
23. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd ed.). Springer.
24. Herm, S., Callsen-Bracker, H. M., & Kreis, H. (2014). When The Crowd Evaluates Soccer Players’ Market Values: Accuracy and Evaluation Attributes of an Online Community. Sport Management Review, 17(4), 484-492. https://doi.org/10.1016/j.smr.2013.12.006
25. Hudl, S. (2019). Wyscout Forum: The Ultimate Football Network. Retrieved June 1, 2024 from https://www.hudl.com/blog/wyscout-forum-the-worlds-1-event-in-football-for-transfer-negotiations
26. Inan, T., & Cavas, L. (2021). Estimation Of Market Values of Football Players Through Artificial Neural Network: A Model Study from The Turkish Super League. Applied Artificial Intelligence, 35(13), 1022-1042. https://doi.org/10.1080/08839514.2021.1966884
27. Jain, A. K., Duin, R. P. W., & Mao, J. (2000). Statistical Pattern Recognition: A Review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(1), 4-37. https://doi.org/10.1109/34.824819
28. Kologlu, Y., Birinci, H., Kanalmaz, S. I., & Ozyilmaz, B. (2018). A Multiple Linear Regression Approach for Estimating The Market Value Of Football Players In Forward Position. Arxiv Preprint arXiv:1807.01104.
29. LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-Based Learning Applied To Document Recognition. Proceedings of the IEEE, 86(11), 2278-2324. https://doi.org/ 10.1109/5.726791
30. Lee, H., Tama, B. A., & Cha, M. (2022). Prediction of football player value using Bayesian ensemble approach. arXiv Preprint, arXiv:2206.13246.
31. Leifheit, N., & Follert, F. (2023). Financial Player Valuation from The Perspective of The Club: The Case of Football. Managing Sport and Leisure, 28(6), 618-637. https://doi.org/10.1080/23750472.2021.1944821
32. Li, C., Kampakis, S., & Treleaven, P. (2022). Machine Learning Modeling to Evaluate The Value Of Football Players. arXiv Preprint arXiv:2207.11361.
33. Liaw, A., & Wiener, M. (2002). Classification And Regression By randomForest. R News, 2(3), 18-22.
34. Mann, D. L., Dehghansai, N., & Baker, J. (2017). Searching For the Elusive Gift: Advances In Talent Identification In Sport. Current Opinion in Psychology, 16, 128-133. https://doi.org/10.1016/j.copsyc.2017.04.016
35. Manning, C. D., Raghavan, P., & Schütze, H. (2008). Introduction to Information Retrieval. Cambridge University Press.
36. Montgomery, D. C., Peck, E. A., & Vining, G. G. (2012). Introduction To Linear Regression Analysis (5th ed.). John Wiley & Sons.
37. Morgans, R., Adams, D., Mullen, R., McLellan, C., McNaughton, L., & Williams, M. (2014). A Comparison of Physical And Technical Match Performance of A Team Competing In The English Championship League And Then Promoted To The English Premier League. International Journal of Sports Science & Coaching, 9(5), 1101-1114. https://doi.org/10.1260/1747-9541.10.2-3.543
38. Murray, B. (1994). The World's Game: A History of Soccer. University of Illinois Press.
39. Pariath, R., Shah, S., Surve, A., & Mittal, J. (2018, March). Player Performance Prediction İn Football Game. In 2018 Second International Conference on Electronics, Communication and Aerospace Technology (ICECA) (pp. 1148-1153). IEEE. https://doi.org/10.1109/ICECA.2018.8474750
40. Powers, D. M. W. (2011). Evaluation: From Precision, Recall And F-Measure To Roc, İnformedness, Markedness And Correlation. Journal of Machine Learning Technologies, 2(1), 37-63. https://doi.org/10.48550/arXiv.2010.16061
41. Sokolova, M., & Lapalme, G. (2009). A Systematic Analysis of Performance Measures For Classification Tasks. Information Processing & Management, 45(4), 427-437. https://doi.org/10.1016/j.ipm.2009.03.002
42. Transfermarkt. (2024). Market Values. Retrieved June 3, 2024, from https://www.transfermarkt.com/navigation/marktwerte
43. Whoscored. (2024). Player Statistics. Retrieved May 20, 2024, from https://www.whoscored.com/Statistics