Abstract—Machine learning is a subset of artificial intelligence (AI) that allows computers to learn and improvise on their own without having to be explicitly programmed. Machine learning deals with the creation of computer programs that can access data and learn on their own. Sports prediction is one of the rapidly-growing fields in good predictive accuracy since it involves a large sum of money in betting. The capability to apply algorithms and use that knowledge to try to forecast the outcome of future games based on this data is a particularly important aspect of machine learning in football. Sports match results can be difficult to forecast, with unexpected outcomes frequently occurring. Football is a good example since matches have a set length (as opposed to racket sports like tennis, where the game is played until one player wins). In this study, Machine Learning techniques are used to predict the winning team in the English Premier League (EPL). The goal is to predict a football match's full-time result (FTR) accurately, which determines the winning team. For training the data, we use algorithms like Support Vector Machines, XGBoost, and Logistic Regression, and the one with the highest and best accuracy is used to forecast the winning team. The data for previous seasons is obtained from .
Keywords—Football, Soccer Analytics, Prediction, Machine Learning, Support Vector Machine (SVM), XGBoost
| DOI: 10.17148/IJARCCE.2022.11489