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

Authors : Bünyamin Fuat YILDIZ

Pages : 92-99

View : 17 | Download : 12

Publication Date : 2020-12-29

Article Type : Research Paper

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