<![CDATA[Purpose – Student attendance data in vocational schools are often collected digitally but remain underutilized for managerial decision-making. This study aims to apply the K-Means Clustering algorithm to identify student discipline patterns based on attendance behavior and support objective, data-driven intervention planning. Methods – This study employed a quantitative computational experiment using attendance data from 23 students at SMK Negeri 1 Bolango Utara over 33 effective school days. Student identities were anonymized using subject codes. Two variables were analyzed: on-time attendance frequency and tardiness frequency. The number of clusters was set to K=3 based on managerial discipline categories and validated using the Elbow Method through Within-Cluster Sum of Squares analysis. Findings – The results classified students into three discipline profiles. Cluster 1 consisted of 13 students categorized as highly disciplined, Cluster 3 consisted of 5 students categorized as moderately disciplined, and Cluster 2 consisted of 5 students categorized as less disciplined. The less disciplined cluster showed a critical pattern, with an average tardiness frequency of 16.80, exceeding its average on-time attendance frequency of 16.20. Research implications – The findings indicate that K-Means clustering can transform passive attendance records into actionable discipline profiles. However, the study was limited to one school, 23 students, and two attendance variables. Originality – This study contributes a simple computational framework for developing an attendance-based early warning system for student discipline management in vocational education.]]>
Copyrights © 2026
