The Estimation of German Football League (Bundesliga) Team Ranking via Artificial Neural Network Model

Abstract

This study was conducted to estimate the places of teams in league ranking by the analysis of the time intervals of the scored and conceded goals in football using Artificial Neural Network (ANN). In the study, the data of the minutes of the scored and conceded goals (0-15, 16-30, 31-45, 46-60, 61-75, 76-90) in total 918 matches played in 3 seasons (2015/2016, 2016/2017, 2017/2018) in German Soccer League (Bundesliga) were used. Total 12 input values (scored and conceded goals) and 1 output (league ranking) value was obtained. 4 different models were determined. 3 seasons league rankings were estimated by training the first 2 season data. All data were separated randomly for training and testing. League ranking was obtained by normalizing between the range of 0,1 – 0,9. Since the produced value in the range of 0 – 1, it was multiplied with 100 for a trained network and the league ranking was obtained. It was determined that the model developed according to our findings estimated the league ranking with above 99% accuracy for many teams (test data set) according to the minutes of the scored and conceded goals. The lowest mean square error (MSE) value was obtained as 0.00004. As a consequence, it was determined that the minutes of scored and conceded goals in soccer affect the league ranking of the teams. Obtained ANN prediction model can be a guide for coaches to determine the offensive and defensive organizations.

Keywords

• Artificial neural network
• ranking
• prediction
• soccer league

References

1. Aka H, Aktuğ, ZB, Kılıç F. Türkiye Süper Lig sezon sonu takım sıralamasının geliştirilen yapay sinir ağları modeli ile tahmin edilmesi. Spor ve Performans Araştırmaları Dergisi, 2020; 11(3): 258-268.
2. Aka H, Aktuğ ZB, Kılıç F. Estimating the England Premier League ranking with artificial neural network. Applied Artificial Intelligence, 2021; 35(5): 393-402.
3. Arabzad A, Araghi M, Soheil S. Football match results prediction using artificial neural networks: the case of Iran Pro League. International Journal of Applied Research on Industrial Engineering, 2014; 1(3): 159-179.
4. Ayyıldız E. Estimation of American Basketball League (NBA) match results by artificial neural networks. Gaziantep University Journal of Sports Science, 2018; 3(1): 40-53.
5. Baacke H. Voleybol Antrenmanı Üst Düzey Takımlar İçin El Kitabı 2. İstanbul: Çağrı Baskı, 2005.
6. Brito de Souza D, López-Del Campo R, Blanco-Pita H, Resta R, Del Coso J. An extensive comparative analysis of successful and unsuccessful football teams in La Liga. Frontiers in Psychology, 2019; 10(25661): 1-8.
7. Carling C, Williams A, Reilly T. Handbook of Soccer Match Analysis: A Systematic Approach to Improving Performance. New York, USA: Routledge, 2007: 164.
8. Fernandez-Echeverria C, Mesquita I, González-Silva J, Claver F, Moreno MP. Match analysis within the coaching process: a critical tool to improve coach efficacy. International Journal of Performance Analysis in Sport, 2017; 17(1-2): 149-163.

9. Harper DJ, Carling C, Kiely J. High-intensity acceleration and deceleration demands in elite team sports competitive match play: a systematic review and meta-analysis of observational studies. Sports Medicine, 2019; 49(12): 1923-1947.
10. Igiri CP, Nwachukwu EO. An improved prediction system for football a match result. IOSR Journal of Engineering, 2014; 4: 12-20.
11. Ivankovic Z, Rackovic M, Markoski B, Radosav D, Ivankovic M. Analysis of basketball games using neural networks. In Computational Intelligence and Informatics (CINTI) 11th International Symposium, Obuda University Budapest, Hungary, 2010: 251-256.
12. Kahn J. Neural Network Prediction of NFL Football Games. World Wide Web Electronic Publication. 2003.
13. Karaatli M, Helvacioğlu ÖC, Ömürbek N, Tokgöz G. Yapay sinir ağları yöntemi ile otomobil satış tahmini. Uluslararası Yönetim İktisat ve İşletme Dergisi, 2012; 8(17): 87-100.
14. Kılıç F, Aka H, Aktuğ ZB. Futbolda yapay sinir ağları modeli ile lig sıralaması tahmini. International Journal of Contemporary Educational Studies, 2020; 6(2): 379-391.
15. McCabe A, Trevathan J. Artificial intelligence in sports prediction. In information technology: New generations, 2008. ITNG 2008 Fifth International Conference, Las Vegas, 2008: 1194-1197.
16. Menet F, Berthier P, Gagnon M, Fernandez JM. Spartan networks: Self-feature-squeezing neural networks for increased robustness in adversarial settings. Computers & Security, 2020; 88: 1-17.
17. Özden S, Kılıç F. Performance evaluation of GSA, SOS, ABC and ANN algorithms on linear and quadratic modelling of eggplant drying kinetic. Food Science and Technology, 2020; 40(3): 635-643.
18. Öztemel E. Yapay Sinir Ağları. Türkiye: Papatya Yayınevi, 2003.
19. Palao J, Hernández-Hernández E. Game statistical system and criteria used by Spanish volleyball coaches. International Journal of Performance Analysis in Sport, 2014; 4(2): 564-573.
20. Rampinini E, Impellizzeri FM, Castagna C, Coutts AJ, Wisløff U. Technical performance during soccer matches of the Italian Serie A League: effect of fatigue and competitive level. Journal of Science and Medicine in Sport, 2009; 12(1): 227-233.
21. Sağıroğlu Ş, Beşdok E, Erler M. Mühendislikte Yapay Zeka Uygulamaları - 1: Yapay Sinir Ağları. Kayseri: Ufuk Kitap Kırtasiye–Yayıncılık Tic. Ltd. Şti, 2003: 299-426.
22. Sarmento H, Anguera MT, Pereira A, Araújo D. Talent identification and development in male football: a systematic review. Sports Medicine, 2018; 48(4): 907-931.
23. Sözen A, Arcaklioğlu E, Özkaymak M. Turkey’s net energy consumption. Applied Energy, 2005; 81(2): 209-221.
24. Tümer AE, Koçer S. Prediction of team league’s rankings in volleyball by artificial neural network method. International Journal of Performance Analysis in Sport, 2017; 17(3): 202-211.