Klasterisasi Mahasiswa Berdasarkan Performa Akademik Menggunakan Algoritma K-Means pada RapidMiner: Studi Kasus dengan Dataset Student Academic Performance

Siti Khodijah (Universitas Pamulang)
Athaya Rima Hariyanto (Universitas Pamulang)
Berliani Salsabiilah (Universitas Pamulang)
Winona Septi Aulia (Universitas Pamulang)
Maulana Fanyusri (Universitas Pamulang)

Journal of Information Technology and Informatics Engineering
Vol 1 No 1 (2025): Journal of Information Technology and Informatics Engineering (JITIE)

One of the primary indicators used to convey the effectiveness of the learning process and to create more efficient teaching methods is student academic performance. This study uses the RapidMiner application to use the K-Means Clustering method in order to group students according to their academic performance. The synthetic data, which includes details about student involvement, attendance rates, and academic grades, is taken from the Kaggle platform. This study was carried out in a number of steps, including cluster quality assessment, attribute selection, algorithm application, and data pre-processing.Based on the results, three student groups with characteristics of high, medium, and low academic performance were examined. The Davies-Bouldin Index examination indicated that the clustering results were optimal. These findings are expected to serve as a guide for educational institutions to develop more appropriate and successful teaching strategies.