Predicting Football Matches Results using Bayesian Networks for English Premier League (EPL)

International Research and Innovation Summit 2017

Razali, Nazim^1 ; Mustapha, Aida^1 ; Yatim, Faiz Ahmad^2 ; Ab Aziz, Ruhaya^1

Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor, Batu Pahat

86400, Malaysia^1

Co-Operative College of Malaysia, 103 Jalan Templer, Selangor, Petaling Jaya

46700, Malaysia^2

关键词: Bayesian approaches;    Bayesian Networks (bns);    Football predictions;    K fold cross validations;    Machine learning approaches;    Prediction model;    Predictive accuracy;    Statistical approach;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/226/1/012099/pdf
DOI  :  10.1088/1757-899X/226/1/012099

来源: IOP

【 摘 要 】

The issues of modeling asscoiation football prediction model has become increasingly popular in the last few years and many different approaches of prediction models have been proposed with the point of evaluating the attributes that lead a football team to lose, draw or win the match. There are three types of approaches has been considered for predicting football matches results which include statistical approaches, machine learning approaches and Bayesian approaches. Lately, many studies regarding football prediction models has been produced using Bayesian approaches. This paper proposes a Bayesian Networks (BNs) to predict the results of football matches in term of home win (H), away win (A) and draw (D). The English Premier League (EPL) for three seasons of 2010-2011, 2011-2012 and 2012-2013 has been selected and reviewed. K-fold cross validation has been used for testing the accuracy of prediction model. The required information about the football data is sourced from a legitimate site at http://www.football-data.co.UK. BNs achieved predictive accuracy of 75.09% in average across three seasons. It is hoped that the results could be used as the benchmark output for future research in predicting football matches results.