Applying Decision Tree Techniques to Classify European Football Teams

Abstract

Machine learning techniques are powerful tools used in all aspects of science. However, these techniques are relatively new in sports. This study was carried out to measure the accuracy of decision trees in the classification of football teams. We applied five types of decision tree algorithms to classify elite football teams in Spain, Italy, and England to determine whether decision tree techniques are robust in classifying elite football teams. The findings show that the accuracy rate is above 77 percent for each of the decision trees. The key qualities that cause branching in decision trees may constitute a criterion for the targeting of football authorities. More research is required to determine which machine learning techniques are more efficient in classifying football teams.

Keywords

• machine learning
• decision trees
• football
• classification
• sports

References

1. Baboota R, Kaur H. Predictive analysis and modelling football results using machine learning approach for English Premier League. International Journal of Forecasting. 2019;35(2):741-55.
2. Breiman L. Random forests. Machine learning. 2001;45(1):5-32.
3. Cene E, Parim C, Özkan B. Comparing the performance of basketball players with decision trees and TOPSIS. Data Science and Applications. 2018;1(1):21–8.
4. Han J, Pei J, Kamber M. Data mining: concepts and techniques. Elsevier; 2011.
5. Hornik K, Buchta C, Zeileis A. Open-source machine learning: R meets Weka. Computational Statistics. 2009;24(2):225–32.
6. Horvat T, Havaš L, Srpak D. The Impact of Selecting a Validation Method in Machine Learning on Predicting Basketball Game Outcomes. Symmetry. 2020;12(3):431.
7. Freiman MH. Using random forests and simulated annealing to predict probabilities of election to the Baseball Hall of Fame. Journal of Quantitative Analysis in Sports. 2010;6(2). https://doi.org/10.2202/1559-0410.1245.
8. Folgado H, Duarte R, Marques P, Sampaio J. The effects of congested fixtures period on tactical and physical performance in elite football. Journal of sports sciences. 2015;33(12):1238–47. https://doi.org/10.1080/02640414.2015.1022576 PMID:25765524

9. Joash Fernandes, C., Yakubov, R., Li, Y., Prasad, A. K., & Chan, T. C. (2019). Predicting plays in the National Football League. Journal of Sports Analytics, 1-9.
10. Koseler K, Stephan M. Machine learning applications in baseball: A systematic literature review.Applied Artificial Intelligence. 2017;31(9-10):745–63. https://doi.org/10.1080/08839514.2018.1442991.
11. Kretowski M. Evolutionary Decision Trees in Large-Scale Data Mining. Springer International Publishing; 2019. https://doi.org/10.1007/978-3-030-21851-5.
12. Landwehr N, Hall M, Frank E. Logistic model trees. Machine Learning. 2005;59(1-2):161–205. https://doi.org/10.1007/s10994-005-0466-3.
13. Leicht AS, Gomez MA, Woods CT. Team performance indicators explain outcome during women’s basketball matches at the Olympic Games. Sports. 2017 Dec;5(4):96. https://doi.org/10.3390/sports5040096 PMID:29910456
14. Liaw A, Wiener M. Classification and regression by randomForest. R News. 2002;2(3):18–22.
15. Loh WY. Classification and regression trees. . Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. 2011;1(1):14–23. https://doi.org/10.1002/widm.8.
16. Lorenzo Calvo J, Menéndez García A, Navandar A. Analysis of mismatch after ball screens in Spanish professional basketball. International Journal of Performance Analysis in Sport. 2017;17(4):555–62. https://doi.org/10.1080/24748668.2017.1367999.
17. Michie D, Spiegelhalter DJ, Taylor CC. Machine learning. Neural and Statistical Classification. 1994;13:1–298.
18. Min DK. Contribution analysis of scoring in the soccer game: using decision tree. The Korean Data & Information Science Society. 2019;30(6):1385–97. https://doi.org/10.7465/jkdi.2019.30.6.1385.
19. Mulholland J, Jensen ST. Predicting the draft and career success of tight ends in the National Football League. . Journal of Quantitative Analysis in Sports. 2014;10(4):381–96. https://doi.org/10.1515/jqas-2013-0134.
20. Myers BR. A proposed decision rule for the timing of soccer substitutions. Journal of Quantitative Analysis in Sports. 2012;8(1). https://doi.org/10.1515/1559-0410.1349.
21. Oh Y, Kim H, Yun J, Lee JS. Using Data Mining Techniques to Predict Win-Loss in Korean Professional Baseball Games. Journal of Korean Institute of Industrial Engineers. 2014;40(1):8–17. https://doi.org/10.7232/JKIIE.2014.40.1.008.
22. Quinlan JR. Improved use of continuous attributes in C4. 5. Journal of artificial intelligence research.1996;4:77–90. https://doi.org/10.1613/jair.279.
23. Ripley B. (2019). tree: Classification and Regression Trees. R package version 1.0-40. https://CRAN.R-project.org/package=tree
24. Rokach L, Maimon OZ. Data mining with decision trees: theory and applications. World scientific; 2008.
25. Schauberger G, Groll A. Predicting matches in international football tournaments with random forests. Statistical Modelling. 2018;18(5-6):460–82. https://doi.org/10.1177/1471082X18799934.
26. Tolbert B, Trafalis T. Predicting major league baseball championship winners through data mining. Athens Journal of Sports. 2016;3(4):239–52. https://doi.org/10.30958/ajspo.3.4.1.
27. Therneau T, Atkinson B, Ripley B. (2019). rpart: Recursive Partitioning and Regression Trees. R package version 4.1-15. https://CRAN.R-project.org/package=rpart