Clustering Student Performance Data Using k-Means Algorithms

• Main Authors: Sultan Alalawi, Sultan Juma, Mohd Shaharanee, Izwan Nizal, Mohd Jamil, Jastini
• Format: Article
• Language: English
• Published: UUM Press 2023
• Subjects: QA75 Electronic computers. Computer science
• Online Access: https://repo.uum.edu.my/id/eprint/29743/1/JCIA%2002%2001%202023%2041-55.pdf; https://doi.org/10.32890/jcia2023.2.1.3; https://repo.uum.edu.my/id/eprint/29743/; https://e-journal.uum.edu.my/index.php/jcia/article/view/16696; https://doi.org/10.32890/jcia2023.2.1.3

Education institutions store large amounts of data regarding students, such as demographics, academic-related data, and student activities. These data were recorded and stored in many ways, including different filing systems and database formats. By having these data, education institutions have a better way to manage and understand their students. In addition, information related to their students can easily be accessed and extracted. As more data is recorded and stored, this could allow the educational institution to make more informed decisions and give educators good insight into the educational system. The research approach known as educational data mining (EDM) focuses on using data mining techniques to extract massive data from the educational context and transform it into knowledge that can improve educational systems and decisions. Clustering, an unsupervised learning technique, is one of the most powerful machine- learning tools for discovering patterns and unseen data. This work aims to provide insights into the data obtained from Oman Education Portal (OEP) related to the student’s performance by manipulating the k-means algorithm.