Implementasi Algoritma K-Means untuk Pemetaan Tingkat Kelulusan Mahasiswa Berdasarkan Parameter Akademik Awal
Keywords:
Data Mining, K-Means, StudentsAbstract
This study aims to classify students based on their academic performance during the first four semesters in order to map their potential for on-time graduation. Using the K-Means algorithm, the data were processed into three clusters: High, Medium, and Low. The results indicate that second-semester GPA and the number of credits taken are the dominant factors influencing the clustering. The model achieves a clustering accuracy of 71%, which can be utilized by academic programs as an early warning system.
References
Artawan, I. G. N. (2024). Penerapan algoritma K-Means dalam pengelompokan tingkat kelulusan mahasiswa. Jurnal Ilmiah Teknologi dan Komputer, 5(1).
Han, J., Kamber, M., & Pei, J. (2022). Data mining: Concepts and techniques (4th ed.). Morgan Kaufmann.
Mitchell, R. (2023). Machine learning with Python: A practical guide for data scientists (2nd ed.). O’Reilly Media.
Rahayu, T. (2023). Implementasi penambangan data untuk prediksi masa studi mahasiswa berbasis atribut akademik. Jurnal Teknologi Informasi dan Komunikasi, 12(3), 45–52.
Setiawan, A. B., & Pratama, R. (2024). Analisis pola kelulusan mahasiswa teknik informatika menggunakan algoritma unsupervised learning. Jurnal Informatika dan Sistem Informasi, 7(2), 112–119.
