Modelling Sport Events with Supervised Machine Learning

Authors : İrem BARMAN, İbrahim DEMİR

Pages : 232-244

Doi:10.33401/fujma.951665

View : 22 | Download : 7

Publication Date : 2021-12-01

Article Type : Research Paper

Abstract :It has been very important to understand the change of multivariable systems to make predictions accordingly. The goal of supervised machine learning is to build a model of changing classes of observations depending on various variables and to make predictions about the coming situations. Due to the fact that sports are followed by the whole world modelling sports events and studies about predicting the results of future matches have gained importance. In this study, match statistics of the teams in the Turkey Super League were used, and it was examined how successfully the outcome of the match was predicted using a decision tree, random forest, k-nearest neighbor, naive Bayes, support vector machine. According to the tests done in Turkey Super League, the support vector machine performs the best.
Keywords : Decision tree, k nearest neighbor, Modelling sport events, Naive Bayes, Random forest, Supervised machine learning, Support vector machines