Predicting Football Match Outcomes with Machine Learning Approaches

Citation

Chua, Sook Ling and Foo, Lee Kien and Choi, Bing Shen (2023) Predicting Football Match Outcomes with Machine Learning Approaches. MENDEL, 29 (2). pp. 229-236. ISSN 1803-3814

[img] Text
3.pdf - Published Version
Restricted to Repository staff only

Download (886kB)

Abstract

The increasing use of data-driven approaches has led to the development of mod-els to predict football match outcomes. However, predicting match outcomesaccurately remains a challenge due to the sport’s inherent unpredictability. Inthis study, we have investigated the usage of different machine learning models inpredicting the outcome of English Premier League matches. We assessed the per-formance of random forest, logistic regression, linear support vector classifier andextreme gradient boosting models for binary and multiclass classification. Thesemodels are trained with datasets obtained using different sampling techniques.The result showed that the models performed better when trained with datasetobtained using a balanced sampling technique for binary classification. Addition-ally, the models’ predictions were evaluated by conducting simulation on footballbetting profits based on the 2022-2023 EPL season. The model achieved the high-est accuracy is the binary class random forest, but the model provided the highestfootball betting profit is the binary class logistic regression.

Item Type: Article
Uncontrolled Keywords: Classification, Machine Learning, Sampling Techniques, Multiclass,Binary, Football Prediction
Subjects: Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 21 Feb 2024 04:18
Last Modified: 21 Feb 2024 04:18
URII: http://shdl.mmu.edu.my/id/eprint/12082

Downloads

Downloads per month over past year

View ItemEdit (login required)