Article: Football results prediction and machine learning techniques Journal: International Journal of Business and Systems Research (IJBSR) 2023 Vol.17 No.5 pp.565 - 586 Abstract: In the past, machine learning techniques used to predict the outcome of professional team-based sports matches have used the number of points or goals scored as the primary metric for performance evaluation in their prediction models. However, this approach is considered outdated by industry statisticians. The final outcome of each match can fluctuate wildly from the expected outcome based on events and changes of circumstances occurring within the games. The aim of this project is to compare and contrast the effectiveness and performance of various machine learning models when predicting the outcome of football matches in the English Premier League, both to each other and other benchmarks, including bookmakers' models and random chance. In this research, the 'expected goals' metric was explored as the base of the machine learning algorithms instead of the traditional 'goals scored' metric. This was used to build a Poisson distribution probabilistic classifier to predict the results of matches in the future, achieving an accuracy of 52.3% with regard to matches that occurred during the 2020-2021 Premier League season. Inderscience Publishers - linking academia, business and industry through research

Title: Football results prediction and machine learning techniques

Authors: Victor Chang; Karl Hall; Le Minh Thao Doan

Addresses: Department of Operations and Information Management, Aston University, Birmingham, UK ' Cybersecurity, Information Systems and AI Research Group, School of Computing, Engineering and Digital Technologies, Teesside University, Middlesbrough, UK ' Cybersecurity, Information Systems and AI Research Group, School of Computing, Engineering and Digital Technologies, Teesside University, Middlesbrough, UK

Abstract: In the past, machine learning techniques used to predict the outcome of professional team-based sports matches have used the number of points or goals scored as the primary metric for performance evaluation in their prediction models. However, this approach is considered outdated by industry statisticians. The final outcome of each match can fluctuate wildly from the expected outcome based on events and changes of circumstances occurring within the games. The aim of this project is to compare and contrast the effectiveness and performance of various machine learning models when predicting the outcome of football matches in the English Premier League, both to each other and other benchmarks, including bookmakers' models and random chance. In this research, the 'expected goals' metric was explored as the base of the machine learning algorithms instead of the traditional 'goals scored' metric. This was used to build a Poisson distribution probabilistic classifier to predict the results of matches in the future, achieving an accuracy of 52.3% with regard to matches that occurred during the 2020-2021 Premier League season.

Keywords: machine learning; ML; football results prediction; predictive simulations.

DOI: 10.1504/IJBSR.2023.133178

International Journal of Business and Systems Research, 2023 Vol.17 No.5, pp.565 - 586

Received: 17 Sep 2021
Accepted: 20 Sep 2021
Published online: 01 Sep 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Football results prediction and machine learning techniques

Keep up-to-date