Exploring the correlation among student engagement, self-regulated learning, and academic performance through analysis of the Open University Learning Analytics Dataset (OULAD). This dataset covers course details, learner information and their interactions with the VLE. It records interactions such as resource clicks, course notes, discussions, and quizzes. Online student data was analyzed using educational data mining and three clustering algorithms: K-means, EM and Agglomerative Clustering. The results show a positive correlation between student engagement and academic performance, highlighting that greater interaction with learning resources results in better academic outcomes and shows a self-regulated approach to learning.