<![CDATA[On-time graduation rate is an important indicator in higher education. This study uses the K-Means Clustering algorithm to cluster students based on academic attributes, such as length of study, number of credits, Semester Achievement Index (IPS), and Cumulative Achievement Index (IPK). The dataset used consists of 4483 student data from the Informatics Study Program. The clustering results show three main groups: (1) high-achieving students with an average GPA of 3.77 and the shortest length of study, (2) students with stable performance (average GPA of 3.51), and (3) at-risk students with an average GPA of 3.20 and the longest length of study. Evaluation with Silhouette Score produces a value of 0.1972, indicating weak cluster separation, but providing insight into graduation patterns. This study is expected to help educational institutions develop data-based intervention strategies to improve student graduation rates.]]>
Copyrights © 2024
