Categorization of Qualifying Football Clubs for European Cups with Backpropagating Artificial Neural Networks

Abstract

European cups are the most popular and most profitable football organization in the world. The participation of football clubs in the Champions League and the Europa League is, therefore, a matter of interest to all parts of society. In this respect, this paper uses backpropagating ANNs to understand the capability of categorizing football clubs from Italy, England, and Spain. The sample consists of 10 years of data from Seri A, English Premier League, and La Liga — and teams categorized as qualified and unqualified. As a result of the test, backpropagating ANN classifies the clubs with 92.7 percent accuracy. Our model correctly categorized 40 of 51 qualified teams in our test dataset—that is approximately 78 percent accuracy. However, our backpropagating ANN provides more significant accuracy while predicting unqualified teams, that is approximately 98.5 percent. The probable reason for lower accuracy in the categorization of qualified teams might be underrepresentation in the dataset and lack of variable diversity. The success of ANNs implies that it could be interesting to integrate ANNs into an online betting platform to develop solutions for more complex events by introducing more data. The application of other machine learning approaches will contribute to the literature and provide an opportunity to compare methods.

Keywords

• Machine Learning
• Backpropagated Artificial Neural Networks
• Football

References

1. Joseph A, Fenton NE, Neil M. Predicting football results using Bayesian nets and other machine learning techniques. Knowledge-Based Systems. 2006;19(7):544-53.
2. Rein R, Memmert D. Big data and tactical analysis in elite soccer: future challenges and opportunities for sports science. SpringerPlus. 2016 Dec;5(1):1-3.
3. Berrar D, Lopes P, Dubitzky W. Incorporating domain knowledge in machine learning for soccer outcome prediction. Machine learning. 2019 Jan 15;108(1):97-126. https://doi.org/10.1007/s10994-018-5747-8.
4. Herold M, Goes F, Nopp S, Bauer P, Thompson C, Meyer T. Machine learning in men’s professional football: Current applications and future directions for improving attacking play. International Journal of Sports Science & Coaching. 2019 Dec;14(6):798-817. https://doi.org/10.1177/1747954119879350.
5. Bunker RP, Thabtah F. A machine learning framework for sport result prediction. Applied computing and informatics. 2019 Jan 1;15(1):27-33.
6. Hubáček O, Šourek G, Železný F. Learning to predict soccer results from relational data with gradient boosted trees. Machine Learning. 2019;108(1):29-47. https://doi.org/10.1007/s10994-018-5704-6.
7. Stübinger J, Mangold B, Knoll J. Machine Learning in Football Betting: Prediction of Match Results Based on Player Characteristics. Applied Sciences. 2020;10(1):46. https://doi.org/10.3390/app10010046.
8. Rudrapal D, Boro S, Srivastava J, Singh S. A Deep Learning Approach to Predict Football Match Result. InComputational Intelligence in Data Mining 2020 (pp. 93-99). Springer, Singapore.

9. Fenil E, Manogaran G, Vivekananda GN, Thanjaivadivel T, Jeeva S, Ahilan A. Real time violence detection framework for football stadium comprising of big data analysis and deep learning through bidirectional LSTM. Computer Networks. 2019;151:191-200. https://doi.org/10.1016/j.comnet.2019.01.028.
10. Matesanz, D., Holzmayer, F., Torgler, B., Schmidt, S. L., & Ortega, G. J. (2018). Transfer market activities and sportive performance in European first football leagues: A dynamic network approach. PloS one, 13(12), e0209362.
11. Singh P, Lamba PS. Influence of crowdsourcing, popularity and previous year statistics in market value estimation of football players. Journal of Discrete Mathematical Sciences and Cryptography. 2019 17;22(2):113-26. https://doi.org/10.1080/09720529.2019.1576333.
12. Yıldız BF. Applying Decision Tree Techniques to Classify European Football Teams. Journal of Soft Computing and Artificial Intelligence. 2020; 1(2): 29-35.
13. Cavuto DJ. An exploration and development of current artificial neural network theory and applications with emphasis on artificial life. Unpublished Master of Engineering Thesis. The Cooper Union, Albert Nerken School of Engineering, New York, NY. 1997.
14. Dreyfus SE. Artificial neural networks, back propagation, and the Kelley-Bryson gradient procedure. Journal of guidance, control, and dynamics. 1990;13(5):926-8. https://doi.org/10.2514/3.25422.
15. Basheer IA, Hajmeer M. Artificial neural networks: fundamentals, computing, design, and application. Journal of microbiological methods. 2000 1;43(1):3-1.
16. Günther F, Fritsch S. neuralnet: Training of neural networks. The R journal. 2010 1;2(1):30-8.