An Analysis of Students� Academic Performance Using K-Means Clustering Algorithm

• Main Authors: Ahmad, M., Arshad, N.I.B., Sarlan, A.B.
• Format: Article
• Published: Springer Science and Business Media Deutschland GmbH 2022
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85127887124&doi=10.1007%2f978-3-030-98741-1_26&partnerID=40&md5=2d990d26b08daddb1b1c45680d3d452a; http://eprints.utp.edu.my/33265/

A massive amount of data is often used to evaluate the academic performance of students in higher education. Analysis can solve this challenge through various strategies and methods. Due to the spread of the pandemic Covid-19, traditional modes of education have shifted to include online learning. This study aims to analyze the academic performance of students through data mining techniques. The objective aims to investigate the academic performance of business students at a private university in Malaysia using Educational Data Mining techniques. Students� academic performance data of a private university in Malaysia is used to analyze students� performance using demographic and academic attributes. This study used students� academic performance in the learning method to identify the patterns before and during Covid-19 using the K-Means data mining clustering technique. The results of the k-means clustering analysis showed that students were achieving higher CGPA during Covid-19 online learning compared to before Covid-19. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.