Machine learning-based identification of the strongest predictive features of scoring penalty kick in football

Abstract

In football, the penalty is the situation that has one of the highest chances of scoring a goal. However, the success of a penalty kick highly depends on many kinds of attributes, including the penalty-takers’ abilities, the amount of fan pressure, the minute of the match, and the current score. In this paper, 16 features were extracted from penalty kick positions, penalty-takers’ information, and match-day preferences, and machine learning was used to predict penalty kick outcomes. Moreover, we revealed the most important feature combination that significantly affected the success of a penalty kick. The proposed method was trained with 120 and tested with 50 penalty kicks from the Turkish Super League in terms of classification accuracy and polygon area metric. We concluded that the result of a penalty kick can be predicted with an average classification accuracy and average polygon area metric rates of 79.80% and 0.60 using the k-nearest neighbor classifier.

Keywords

• Football
• machine learning
• penalty kick
• polygon area metric
• classification

Futbolda başarılı penaltı atışı için en güçlü belirleyici özniteliklerin makine öğrenimi tabanlı tespiti

Öz

Penaltı, futbolda gol atma şansının en yüksek olduğu durumlardan bir tanesidir. Bir penaltı vuruşunun başarısı penaltıyı kullananların yetenekleri, taraftar baskısının seviyesi, maçın dakikası ve mevcut skor dahil olmak üzere birçok etkene bağlı değişkenlik gösterir. Bu makalede, penaltı pozisyonlarından, penaltıyı kullananların bilgilerinden ve maç günü tercihlerinden 16 öznitelik çıkarılmıştır. Çıkarılan öznitelikler, makine öğrenimi aracılığıyla penaltı vuruşu sonucunu tahmin etmek için kullanılmıştır. Ayrıca bir penaltı vuruşunun başarısını büyük ölçüde etkileyen en önemli öznitelik kombinasyonu elde edilmiştir. Önerilen yöntem, Türkiye Süper Ligi'nden 120 penaltı vuruşu ile eğitilirken 50 penaltı vuruşu ile sınıflandırma doğruluğu ve poligon alanı metriği açısından test edilmiştir. Penaltı vuruşu sonucunun, k-en yakın komşu sınıflandırıcısı kullanılarak %79.80 ortalama sınıflandırma doğruluğu ve 0.60 ortalama poligon alanı metriği oranlarıyla tahmin edilebileceği sonucuna varılmıştır.

Anahtar Kelimeler

• Futbol
• makine öğrenmesi
• penaltı atışı
• poligon alan metriği
• sınıflandırma

Kaynakça

1. J. A. Brown, A. Cuzzocrea, M. Kresta, K. D. Kristjanson, C. K. Leung and T. W. A. Tebinka, Machine learning tool for supporting advanced knowledge discovery from chess game data. 16th IEEE International Conference on Machine Learning and Applications (ICMLA), 649-654, 2017. https://doi.org/10.1109/ICMLA.2017.00-87.
2. M. R. Albuquerque, P. H. C. Mesquita, T. Herrera-Valenzuela, D. Detanico and E. Franchini, Predicting taekwondo winners in high-level competition using ranking scores and country performance scores: an analysis of the 2019 World Taekwondo Championship. Ido Movement for Culture. Journal of Martial Arts Anthropology, 21(2), 2021. https://doi.org/ 10.14589/ido.21.2.4.
3. M. H. Zhong, J. C. Hung, Y. C. Yang and C. P. Huang, GA-SVM classifying method applied to dynamic evaluation of taekwondo. International Conference on Advanced Materials for Science and Engineering, 534-537, 2016. https://doi.org/10.1109/ICAMSE.2016.7840191.
4. B. Emad, O. Atef, Y. Shams, A. El-Kerdany, N. Shorim, A. Nabil and A. Atia, Ikarate: Improving karate kata. Procedia Computer Science. 170, 466-473, 2020. https://doi.org/10.1016/j.procs.2020.03.090.
5. T. Chellatamilan, M. M. Ravichandran and K. Kamalakkannan, Modern Machine Learning Approach for Volleyball Winning Outcome prediction. Global Journal of Multidisciplinary Studies, 4(12), 63-71, 2015.
6. S. Wenninger, D. Link and M. Lames, Performance of machine learning models in application to beach volleyball data. International Journal of Computer Science in Sport, 19(1), 24-36, 2020. https://doi.org/10.2478/ijcss-2020-0002.
7. J. Van Haaren, H. B. Shitrit, J. Davis and P. Fua, Analyzing volleyball match data from the 2014 world championships using machine learning techniques. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 627-634, 2016. https://doi.org/10.1145/2939672.2939725.
8. X. Dai and S. Li, Volleyball data analysis system and method based on machine learning. Wireless Communications and Mobile Computing, 1-11, 2021. https://doi.org/10.1155/2021/9943067.

9. A.K. Holatka, H. Suwa and K. Yasumoto, Volleyball setting technique assessment using a single point sensor. IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 567-572, 2019. https://doi.org/10.1109/PERCOMW.2019.8730811.
10. V. Y. Kulkarni and P. K. Sinha, Pruning of random forest classifiers: A survey and future directions. International Conference on Data Science & Engineering (ICDSE), 64-68, 2012. https://doi.org/ 10.1109/ICDSE.2012.6282329.
11. T. Xu and L. Tang, Adoption of machine learning algorithm-based intelligent basketball training robot in athlete injury prevention. Frontiers in Neurorobotics, 14, 620378, 2021. https://doi.org/10.3389/fnbot.2020.620378.
12. A. W. de Leeuw, S. V. der Zwaard, R. V. Baar and A. Knobbe, Personalized machine learning approach to injury monitoring in elite volleyball players. European journal of sport science, 22(4), 511-520, 2022. https://doi.org/10.1080/17461391.2021.1887369.
13. Z. Mahmood, A. Daud, R. A. Abbasi, Using machine learning techniques for rising star prediction in basketball. Knowledge-Based Systems, 211. 106506, 2021. https://doi.org/10.1016/j.knosys.2020.106506.
14. M. Migliorati, Detecting drivers of basketball successful games: an exploratory study with machine learning algorithms. Electronic Journal of Applied Statistical Analysis, 13(2), 454-473, 2020. https://doi.org/10.1285/i20705948v13n2p454.
15. S. W. Wang and W. W. Hsieh, Performance analysis of basketball referees by machine learning techniques. In International Congress on Sport Sciences Research and Technology Support, 2, 165-170, 2016.
16. R. Baboota and H. Kaur, Predictive analysis and modelling football results using machine learning approach for English Premier League. International Journal of Forecasting, 35(2), 741-755, 2019. https://doi.org/10.1016/j.ijforecast.2018.01.003.
17. A. Joseph, N. E. Fenton and M. Neil, Predicting football results using Bayesian nets and other machine learning techniques. Knowledge-Based Systems, 19(7), 544-553, 2006. https://doi.org/ 10.1016/j.knosys.2006.04.011.
18. F. Thabtah, L. Zhang and N. Abdelhamid, NBA game result prediction using feature analysis and machine learning. Annals of Data Science, 6(1), 103-116, 2019. https://doi.org/ 10.1007/s40745-018-00189-x.
19. J.L. Oliver, F. Ayala, M. B. D. S. Croix, R. S. Lloyd, G. D. Myer and P. J. Read, Using machine learning to improve our understanding of injury risk and prediction in elite male youth football players. Journal of science and medicine in sport, 23(11), 1044-1048, 2020. https://doi.org/10.1016/j.jsams.2020.04.021. Y. Liang, Sports Injury Prediction Model based on Machine Learning. Economic Management and Big Data Application, 969-981, 2024. https://doi.org/10.1142/9789811270277_0086.
20. M. Herold, F. Goes, S. Nopp, P. Bauer, C. Thompson and T. Meyer, 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, 2019. https://doi.org/10.1177/1747954119879350.
21. M. Frey, E. Murina, J. Rohrbach, M. Walser, P. Haas and M. Dettling, Machine learning for position detection in football. 6th Swiss Conference on Data Science (SDS), 111-112, 2019. https://doi.org/10.1109/SDS.2019.00009.
22. A. Garcia-Aliaga, M. Marquina, J. Coteron, A. R. Gonzales and S. L. Sanchez, In-game behaviour analysis of football players using machine learning techniques based on player statistics. International Journal of Sports Science & Coaching, 16(1), 148-157, 2021. https://doi.org/10.1177/1747954120959762.
23. A. Mohandas, M. Ahsan and J. Haider, Tactically Maximize Game Advantage by Predicting Football Substitutions Using Machine Learning. Big Data Cogn. Comput., 7, 117, 2023. DOI:10.3390/bdcc7020117.
24. I. Behravan and S. M. Razavi, A novel machine learning method for estimating football players’ value in the transfer market. Soft Computing, 25(3), 2499-2511, 2021. https://doi.org/10.1007/s00500-020-05319-3.
25. D. Abidin, A case study on player selection and team formation in football with machine learning. Turkish Journal of Electrical Engineering and Computer Sciences, 29(3), 1672-169, 2021. https://doi.org/10.3906/elk-2005-27.
26. J. Almulla and T. Alam, Machine learning models reveal key performance metrics of football players to win matches in qatar stars league. IEEE Access, 8, 213695-213705, 2020. https://doi.org/ 10.1109/ACCESS.2020.3038601.
27. S. Kampakis, Comparison of Machine Learning Methods for Predicting the Recovery Time of Professional Football Players After an Undiagnosed Injury. MLSA@ PKDD/ECML. 1969, 58-68, 2013.
28. S. Chawla, J. Estephan, J. Gudmundsson and M. Horton, Classification of passes in football matches using spatiotemporal data. ACM Transactions on Spatial Algorithms and Systems (TSAS). 3(2), 1-30, 2017. https://doi.org/10.1145/3105576.
29. S. Terekli and H. O. Çobanoğlu, Developing economic values in football: Example of Turkish Football Federation. Open Access Library Journal, 5(2), 1-14, 2018. https://doi.org/10.4236/oalib.1104263.
30. M. A. Timmis, A. Piras and K. N. Van Paridon, Keep your eye on the ball; the impact of an anticipatory fixation during successful and unsuccessful soccer penalty kicks. Frontiers in psychology, 9, 2058, 2018. https://doi.org/10.3389/fpsyg.2018.02058.
31. L. Ellis and P. Ward, The effect of a high-pressure protocol on penalty shooting performance, psychological, and psychophysiological response in professional football: A mixed methods study. Journal of Sports Sciences, 40(1), 3-15, 2022. https://doi.org/ 10.1080/02640414.2021.1957344.
32. M. Ferraresi and G. Gucciardi, Who chokes on a penalty kick? Social environment and individual performance during Covid-19 times. Economics Letters, 203, 109868, 2021. https://doi.org/10.1016/j.econlet.2021.109868.
33. A. Chakma, A. Z. M. Faridee, N. Roy and H. S. Hossain, Shoot like ronaldo: Predict soccer penalty outcome with wearables. IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 1-6, 2020. https://doi.org/ 10.1109/PerComWorkshops48775.2020.9156244.
34. J. L. Bloeche, J. Audiffren, T. Le Naour, A. Alli, D. Simoni, G. Wüthrich and J. P. Bresciani, It’s not all in your feet: Improving penalty kick performance with human-avatar interaction and machine learning. The Innovation, 5(2), 100584, 2024. https://doi.org/10.1016/j.xinn.2024.100584.
35. O. Aydemir, A new performance evaluation metric for classifiers: polygon area metric. Journal of Classification, 38, 16-26, 2021. https://doi.org/10.1007/s00357-020-09362-5.
36. Transfermarkt, Football player and match statistics, https://www.transfermarkt.com/, Accessed 16 May 2024.
37. Turkish football federation official website, Match statistics, https://www.tff.org/, Accessed 16 May 2024.
38. B. R. Patel and K. K. Rana, A survey on decision tree algorithm for classification. International Journal of Engineering Development and Research, 2(1), 1-5, 2014.
39. C. H. Park and H. Park, A comparison of generalized linear discriminant analysis algorithms. Pattern Recognition, 41(3). 1083-1097, 2008. https://doi.org/ 10.1016/j.patcog.2007.07.022.