TÜRKİYE SÜPER LİGİ MAÇ SONUÇ TAHMİNLERİNDE MAKİNE ÖĞRENME YÖNTEMLERİNİN PERFORMANS KARŞILAŞTIRILMASI

Year 2024, , 59 - 72, 30.07.2024

Duygu Topcu , Özgül Vupa Çilengiroğlu

https://doi.org/10.33689/spormetre.1381602

Abstract

Bu çalışmanın amacı, Türkiye Süper Ligi'nde oynanan maçların sonuçlarının tahmin edilmesinde en etkili değişkenlerin oluşturduğu modellerin performanslarını makine öğrenmesi yöntemlerini kullanarak belirlemek, incelemek, yorumlamak ve karşılaştırmaktır. Bu amaçla Türkiye Futbol Süper Liginde 2018-2021 sezonlarındaki veriler kullanılarak 23 takımın 743 maçı incelenmiştir. Takımların kazanma ve kaybetme durumları, lojistik regresyon, karar ağaçları ve rassal orman gibi makine öğrenme yöntemleri kullanılarak modellenmiştir. Modellerin performansları duyarlılık, seçicilik, doğruluk ve F-puanı kriterlerine göre karşılaştırılmıştır. Makine öğrenme yöntemleri ve modelleri karşılaştırıldığında “rakip takımın olumlu pas yüzdesi”, “ev sahibi takımın hücum gücü” ve “rakip takımın savunma gücü” değişkenleri ile sınıflandırma ve regresyon ağaçları (CART) %67.4 doğrulukla en iyi model olarak belirlenmiştir.

Keywords

Lojistik regresyon, karar ağaçları, rassal orman, savunma gücü, hücum gücü

PERFORMANCE COMPARISON OF MACHINE LEARNING METHODS IN TURKISH SUPER LEAGUE MATCH RESULT PREDICTIONS

Abstract

The aim of this study is to determine, examine, interpret and compare the performances of the models formed by the most effective variables in predicting the results of the matches played in the Turkish Super League, using machine learning methods. For this purpose, 743 matches of 23 teams in the Turkish Football Super League were examined using data from the 2018-2021 seasons. The winning and losing situations of the teams were modeled using machine learning methods such as logistic regression, decision trees and random forest. The performances of the models were compared according to sensitivity, specificity, accuracy and F-score criteria. When the machine learning methods and models were compared, it was determined that the best model with 67.4% accuracy was the classification and regression trees (CART) with the variables "pozitive passing percentage of the opponent team", "offensive power of the home team" and "defensive power of the opponent team".

Keywords

Logistic regression, decision trees, random forest, offensive power, defensive power

References

• Ajgaonkar, Y., Bhoyar, K., Patil, A., & Shah, J. (2021). Prediction of winning team using machine learning. I. J. of Engineering Research&Technology (IJERT) Special Issue, 3(3), 461-466.
• Alfredo, Y. F., & Isa, S. M. (2019). Football match prediction with tree based model classification. International Journal of Intelligent Systems and Applications, 11(7), 20-28. https://doi.org/10.5815/ijisa.2019.07.03
• Andrews, S. K., Narayanan, K. L., Balasubadra, K., & Josephine, M. S. (2021, July). Analysis on sports data match result prediction using machine learning libraries. In Journal of Physics: Conference Series (Vol. 1964, No. 4, p. 042085). IOP Publishing. Barron, D., Ball, G., Robins, M., & Sunderland, C. (2020). Identifying playing talent in professional football using artificial neural networks. Journal of Sports Sciences, 38(11-12), 1211-1220. https://doi.org/10.1080/02640414.2019.1708036
• Bilek, G., & Ulas, E. (2019). Predicting match outcome according to the quality of opponent in the English premier league using situational variables and team performance indicators. International Journal of Performance Analysis in Sport, 19(6), 930-941. https://doi.org/ 10.1080/24748668.2019.1684773
• Bunker, R., & Susnjak, T. (2022). The application of machine learning techniques for predicting match results in team sport: A review. Journal of Artificial Intelligence Research, 73, 1285-1322. https://doi.org/10.48550/arXiv.1912.11762
• Carloni, L., De Angelis, A., Sansonetti, G., & Micarelli, A. (2021). A machine learning approach to football match result prediction. In HCI International 2021-Posters: 23rd HCI International Conference, HCII 2021, Virtual Event, July 24–29, 2021, Proceedings, Part II 23 (pp. 473-480). Springer International Publishing. https://doi.org/10.1007/978-3-030-78642-7_63
• Coşkuner, Z., Büyükçelebi, H., & Kurak, K. (2020). Analysis of in-game variables in Turkish Super League. The J. of Germenica Physical Education and Sports Science, 1(1), 46-54.
• C´wiklinski, B., Giełczyk, A., & Choras, M. (2021). Who will score? A machine learning approach to supporting football team building and transfers. Entropy, 23(90), 1-12. https://doi.org/10.3390/e23010090
• Çali, A., Gelecek, N., & Subasi, S. S. (2013). Non-specific low back pain in male professional football players in the Turkish super league. Science & Sports, 28(4), e93-e98.
• Çimen, E.A. (2019). Prediction of the football match results wiıth using machine learning algorithms. Ms Thesis, Çankaya University, Computer Engineering Department.
• Díaz-Pérez, F. M., & Bethencourt-Cejas, M. (2016). CHAID algorithm as an appropriate analytical method for tourism market segmentation. Journal of Destination Marketing & Management, 5(3), 275-282. https://doi.org/10.1016/j.jdmm.2016.01.006
• Freund, Y., & Schapire, R. (1996). Experiments with a new boosting algorithm. Machine learning: Proceedings of the Thirteenth International Conference, pp.148-156.
• Ganesan, A., & Harini, M. (2018). English football prediction using machine learning classifiers. I. J. of Pure and Applied Mathematics, 118(22), 533-536.
• Haruna, U., Maitama, J. Z., Mohammed, M., & Raj, R. G. (2021, November). Predicting the outcomes of football matches using machine learning approach. In International Conference on Informatics and Intelligent Applications (pp. 92-104). Cham: Springer International Publishing.
• Herbinet, C. (2018). Predicting football results using machine learning techniques. Individual Project Report, Imperial College, Department of Computing Imperıal College of Science, Technology and Medicine, London.
• Herold, M., Goes, F., Nopp, S., Bauer, P., Thompson, C., & Meyer, T. (2019). Machine learning in men’s professional football: Current applications and future directions for improving attacking play. International Journal of Sports Science & Coaching, 14(6), 798-817. https://doi.org/ 10.1177/1747954119879350
• Horvat, T., & Job, J. (2020). The use of machine learning in sport outcome prediction: A review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(5), e1380. https://doi.org/10.1002/widm.1380
• Hu, S., & Fu, M. (2022, August). Football match results predicting by machine learning techniques. In 2022 International Conference on Data Analytics, Computing and Artificial Intelligence (ICDACAI) (pp. 72-76). IEEE.
• Hucaljuk, J., & Rakipović, A. (2011, May). Predicting football scores using machine learning techniques. In 2011 Proceedings of the 34th International Convention MIPRO (pp. 1623-1627). IEEE.
• Igiri, R., Peace, C., Nwachukwu, A., & Okechukwu, E. (2014). An improved prediction system for football a match result. IOSR journal of Engineering, 4(12), 12-20.
• Jawade, I., Jadhav, R., Vaz, M. J., & Yamgekar, V. (2021). Predicting football match results using machine learning. International Research Journal of Engineering and Technology (IRJET), 8(7), 177-180.
• Karaoğlu, B. (2015). Modelling sports games using machine learning. TMMOB Elektrik Mühendisleri Odası, 5(9), 1-5.
• Kuzey, C. (2012). Measuring the effect of knowledge workers on organization performance by using support vector machines and decision trees in data mining and an application. Phd Thesis, İstanbul University, İstanbul.
• Lotfi, S., & Rebbouj, M. (2021). Machine learning for sport results prediction using algorithms. International Journal of Information Technology and Applied Sciences. International Journal of Information Technology, 3(3), 148-155. https://doi.org/10.52502/ijitas.v3i3.114
• Manish, S., Bhagat, V., & Pramila, R. (2021). Prediction of football players performance using machine learning and deep learning algorithms. 2nd International Conference for Emerging Technology (INCET), IEEE, pp.1-5.
• Özdemir, E., & Ballı, S. (2020). Prediction of Turkish Men’s Basketball Super League game results with machine learning methods. Journal of Engineering Sciences and Design, 8(3), 740-752. https://doi.org/10.21923/jesd.723109
• Prasetio, D. (2016, August). Predicting football match results with logistic regression. In 2016 International Conference On Advanced Informatics: Concepts, Theory And Application (ICAICTA) (pp. 1-5). IEEE. https://doi.org/10.1109/ICAICTA.2016.7803111
• Rodrigues, F., & Pinto, Â. (2022). Prediction of football match results with Machine Learning. Procedia Computer Science, 204, 463-470. https://doi.org/10.1016/j.procs.2022.08.057
• Samba, S. (2019). Football result prediction by deep learning algorithms. Ms Thesis, Tilburg University, School of Humanities and Digital Sciences Department of Cognitive Science & Artificial Intelligence, The Netherlands.
• Singla, R., & Singh, A. (2020). Sports prediction using machine learning. Journal of Emerging Technologies and Innovative Research (JETIR), 7(10), 2759-2465.
• Tewari, A., Parwani, T., Phanse, A., Sharma, A., & Shetty, A. (2019). Soccer analytics using machine learning. International Journal of Computer Applications, 181(50), 54–56. https://doi.org/10.5120/ijca2019918773
• TFF, (2022). Turkish Football Federation Official Site. https://www.tff.org/
• Taşpınar, Y. S., Çınar, İ., & Koklu, M. (2021). Improvement of Football Match Score Prediction by Selecting Effective Features for Italy Serie A League. MANAS Journal of Engineering, 9(1), 1-9. https://doi.org/10.51354/mjen.802818
• Tüfekci, P. (2016). Prediction of football match results in turkish super league games. In Proceedings of the Second International Afro-European Conference for Industrial Advancement AECIA 2015 (pp. 515-526). Springer International Publishing.
• Ulmer, B., Fernandez, M., & Peterson, M. (2013). Predicting soccer match results in the english premier league. Doctoral dissertation, Doctoral dissertation, Ph. D. dissertation, Stanford.
• Vaidya, S., Sanghavi, H., & Gevario, K. (2016). Football match winner prediction. International Journal of Computer Applications, 154(3), 31-33.
• Witten, I. H., & Frank, E. (2005). Data mining, practical machine learning tools and techniques. Second Edition. Elsevier. ISBN: 9780080477022
• Wu, X., & Kumar, V. (2009). CART: Classification and regression trees, top ten algorithms in data mining. First Edition. New York: Chapman and Hall.
• Vupa Çilengiroğlu, Ö., & Yavuz, A. (2020). Comparison of predictive performance of logistic regression and CART methods for life satisfaction data. European J Sci Tec, 18, 719-727. https://doi.org/10.31590/ejosat.691215
• Yezus, A. (2014). Predicting outcome of soccer matches using machine learning. Mathematics and Mechanics Faculty Term Paper, Saint-Petersburg State University.
• Yıldız, B. F. (2020). Applying decision tree techniques to classify European Football Teams. Journal of Soft Computing and Artificial Intelligence, 1(2), 86-91.
• Zaveri, N., Shah, U., Tiwari, S., Shinde, P., & Teli, L. K. (2018). Prediction of football match score and decision making process. International Journal on Recent and Innovation Trends in Computing and Communication, 6(2), 162-165.