Clusters of Success: Unpacking Academic Trends with K-Means Clustering in Education

Abstract

Integrating Educational Data Mining (EDM) into the sector of education has heralded a new era, profoundly impacting learning outcomes by analyzing student performance and preventing academic disengagement. Using the K-Means clustering approach, this study carefully examines the academic accomplishments of students at Mehran University of Engineering and Technology and offers a sophisticated view of student performance patterns through the rigorous analysis of their learning data. A dataset comprising of the academic data of three student batches of the Department of Software Engineering was broken down into the subject categories of Computer Core, General, and Mathematics. The approach of clustering was then applied to find distinct performance patterns across the three subject categories. The findings of the research reveal that students have the highest performance in the computer core category, followed by mathematics, while the weakest overall performance across all three batches was exhibited in the general subject category. The study highlights the disparities in academic performance across distinct clusters and adds to our understanding of academic success while also illuminating the complex interactions between student characteristics and educational outcomes, providing useful information for educators and policymakers.