In this study, the teams that qualified for the next round as a result of two-legged matchups are predicted using the data collected from the UEFA (Union of European Football Associations) Champions League group stage matches. The study contributes to the literature in terms of variety of methods used and content of the dataset compared to other studies conducted on football data. It is also a pioneering study to predict the outcome of a two-legged matchup. The data are collected from the matches played in the Champions League organizations held between 2010-2018. Classification methods as Artificial Neural Network, K-Nearest Neighbors, Logistic Regression Analysis, Naive Bayes Classifier, Random Forest and Support Vector Machine are used for the prediction. Two applications are carried out to test the successes of the classification models. In the first application, the most successful method is naive bayes classifier (86.66%) and in the second application, the most successful method is random forest (74.81%).
data classification football data mining match result prediction Machine learning
Birincil Dil | İngilizce |
---|---|
Konular | İstatistik |
Bölüm | Natural Sciences |
Yazarlar | |
Yayımlanma Tarihi | 29 Aralık 2020 |
Gönderilme Tarihi | 14 Ağustos 2020 |
Kabul Tarihi | 18 Kasım 2020 |
Yayımlandığı Sayı | Yıl 2020 |