Exploring the Impact of Artificial Intelligence in Predicting English Premier League Football Matches

Oladapo, Taiwo Mubarak (2024) Exploring the Impact of Artificial Intelligence in Predicting English Premier League Football Matches. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (5MB) | Preview

Abstract

Sports analytics, particularly in football match predictions, faces challenges due to the complex structure of the game. The variety of factors impacting match results is frequently too complicated for conventional methods to completely understand. By utilizing artificial intelligence (AI) techniques to improve prediction accuracy, this investigation seeks to close this gap. The significance lies in its potential to completely change how the sports sector makes strategic decisions across three distinct classes (home win, away win, and draw) and in identifying complex patterns and correlations in football match data. Accurate match predictions are advantageous not just to sports fans but also to sports betting markets, team management, and the whole sports analytics field. By utilizing five different machine learning models: Random Forest, Logistic Regression, Decision Tree, Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost), the study presents a thorough methodology. The novel aspect is how these models are compared with five metrics including accuracy, precision, f1-score, recall, and confusion matrix, with an emphasis on handling the complexity included in EPL match predictions. With an accuracy of 49.6%, XGBoost was the most effective model implemented. This demonstrates how AI can predict the results of EPL matches and how machine learning has the potential to perform better than more conventional techniques. While this research contributes to our understanding of artificial intelligence in sports analytics, certain issues remain, such as the exploration of real-time data integration, implementation of other algorithms, feature engineering, model building and the ongoing optimization required to improve multi-class prediction accuracy.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mulwa, Catherine UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science G Geography. Anthropology. Recreation > GV Recreation Leisure > Sports > Soccer Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	20 May 2025 12:44
Last Modified:	20 May 2025 12:44
URI:	https://norma.ncirl.ie/id/eprint/7582

Actions (login required)

View Item