<![CDATA[In the digital era, the integration of technology in education has become essential, particularly in managing student academic data. This study developed an automated student grouping system based on academic performance using Principal Component Analysis (PCA) and K-Means Clustering at SMK Negeri 8 Kabupaten Tangerang. Traditional grouping methods conducted by teachers are time-consuming and prone to subjectivity, whereas the proposed system improves time efficiency by over 80% with more objective and consistent results. PCA is employed to reduce the dimensionality of academic data such as attendance, assignment scores, midterm exams, and final exams, allowing for faster clustering without significant information loss. The K-Means Clustering algorithm then classifies students into high, medium, and low academic performance groups. The system was developed using the Waterfall model, involving stages of requirement analysis, system design, implementation, testing, and maintenance. Final testing shows that the application is user-friendly and provides valuable outputs to support academic decision-making. This research contributes to enhancing the teaching and learning process by integrating machine learning technology into the school’s academic system.]]>
Copyrights © 2025
