Full Time Result Prediction using Ensemble Techniques

Abstract

Sports Analytics is a growing industry and one of the best real-word applications of Data Science. In this paper, the interest of author and machine learning capabilities were combined to develop a result predictor for football matches. The model proposed is capable of predicting result of any English Premier League Match at the half-time with 75% accuracy. The full-time result predictor is a system based on ensemble of powerful classification algorithms which can predict the odds of winning and draw of both home team and away team on the basis of goals scored at the half time and the current standings in the league. The model learns from the past records of the league and the results of different models are compared in the last section of the paper. Keywords— Data Science, comparative models, result prediction, football analysis