Prediction of the football match results with using machine learning algorithms

In this thesis, prediction results of the Spanish La Liga football matches were obtained by using three machine learning algorithms. The dataset includes four season match statistics and the results of these matches. In addition, this thesis investigated which performance parameters of the football game statistics affected the game results. Feature selection techniques were used to reduce the number of attributes. Three different classifiers which are artificial neural network, support vector machine and k- nearest neighborhood were used for prediction. Support vector machine classifier reached better results than the other classifiers when applied for the chosen fifteen attributes in the dataset.