Analisis Clustering Data Mahasiswa Berdasarkan Nilai Akademik Menggunakan K-Means

Muhammad Aliq Aulia (Universitas Kusuma Husada Surakarta)
Kresno Ario Tri Wibowo (Universitas Kusuma Husada Surakarta)
Irfan Nugraha (Universitas Kusuma Husada Surakarta)
Ilham Wahyu Analta (Universitas Kusuma Husada Surakarta)

Journal of Students‘ Research in Computer Science (JSRCS)
Vol. 7 No. 1 (2026): Mei 2026

Academic data in higher education are mainly used for administrative purposes, rather than for meaningful insights. Yet, analyzing student grade data can reveal patterns that help institutions evaluate and improve development strategies. This study grouped student data by academic grades using the K-Means Clustering method. Grades from core courses underwent data collection, preprocessing, cluster number selection, and Clustering using K-Means. The results showed K-Means successfully clustered students by performance level. Each cluster reflected a category of academic ability: high, medium, or low. These results can help institutions monitor progress and design better academic guidance. Thus, applying K-Means may be effective for analyzing student academic data in higher education.