UTHM Institutional Repository

A comparative study of data mining techniques on football match prediction

Che Mohd Rosli, Che Mohamad Firdaus and Saringat, Mohd Zainuri and Razali, Nazim and Mustapha, Aida (2017) A comparative study of data mining techniques on football match prediction. In: 1st International Conference on Computing, Technology, Science and Management in Sports (ICoTSM) 2017, 25–27 November 2017, Kuching, Sarawak, Malaysia.

Full text not available from this repository.

Abstract

Data prediction have become a trend in today's business or organization. This paper is set to predict match outcomes for association football from the perspective of football club managers and coaches. This paper explored different data mining techniques used for predicting the match outcomes where the target class is win, draw and lose. The main objective of this research is to find the most accurate data mining technique that fits the nature of football data. The techniques tested are Decision Trees, Neural Networks, Bayesian Network, and k- Nearest Neighbors. The results from the comparative experiments showed that Decision Trees produced the highest average prediction accuracy in the domain of football match prediction by 99.56%.

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Faculty of Computer Science and Information Technology > Department of Software Engineering
Depositing User: Mr. Mohammad Shaifulrip Ithnin
Date Deposited: 29 Aug 2019 03:46
Last Modified: 29 Aug 2019 03:46
URI: http://eprints.uthm.edu.my/id/eprint/11514
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item