JOURNAL OF SCIENCE AND SOCIAL RESEARCH
Vol 8, No 2 (2025): May 2025

PENERAPAN DATA MINING UNTUK PEMETAAN KINERJA AKADEMIK MAHASISWA DENGAN METODE K-MEANS

G, Katrina Flomina (Unknown)
Rosman, Edwar (Unknown)
Nasution, Muhammad Ibrahim (Unknown)
Febrina, Yerri Kurnia (Unknown)
Hasibuan, Rajimar Suhal (Unknown)



Article Info

Publish Date
25 May 2025

Abstract

Abstract: Implementation of the K-Means clustering algorithm in this study aims to group students based on academic performance in the D3 Teknik Komputer PSDKU Solok Selatan. Clustering is performed based on course grades over 3 semesters, GPA from semester 1 to 3, and student attendance. Data was taken from 27 students who have completed their studies over 3 semesters with a dataset of 29 attributes that will be used in this research. 1 attribute as an identity, 27 attributes underwent a normalization process using MIN-Max Scaler. The clustering process using the Elbow Method and Silhouette Score obtained an optimal cluster k=3, where cluster 0 consists of 10 students, cluster 1 has 8 students, and cluster 2 has 9 students. Cluster 1 shows students with very good academic performance, cluster 2 with diverse academic performance, and cluster 0 with low or poor performance. Principal Component Analysis (PCA) analysis shows good clustering results without overlap. Keyword: Data mining, K-Means clustering, Elbow Method, Silhouette Score, Academic               Performance Abstrak: Implementasi algoritma K-Means clustering  di penelitian ini bertujuan mengelompokkan mahasiswa berdasarkan kinerja akademik pada Program Studi D3 Teknik Komputer PSDKU Solok Selatan. Clustering dilakukan berdasarkan nilai matakuliah selama 3 semester, IP semester 1 sampai 3 dan absensi kehadiran mahasiswa. Data diambil dari 27 mahasiswa yang telah menyelesaikan perkuliahan selama 3 semester dengan 29 atribut datashet yang akan digunakan pada penelitian ini. 1 atribut sebagai identitas, 27 atribut dilakukan proses normalisasi menggunakan MIN-Max Scaler. Proses clustering dengan Metode Elbow dan Silhouette Score mendapatkan klaster optimal k=3, dimana klaster 0 terdiri dari 10 mahasiswa, klaster 1 terdapat 8 mahasiswa dan klaster 2 terdapat 9 mahasiswa. Klaster 1 menunjukkan mahasiswa dengan kinerja akademik yang sangat baik, klaster 2 dengan kinerja akademik yang beragam dan klaster 0 dengan kinerja yang rendah atau kurang. Analisis Principal Component Analysis (PCA)memnampilkan hasil klastering yang baik tanpa tumpang tindih. Kata kunci: Data mining, K-Means clustering, Elbow Method, Silhoutte Score, Kinerja                    Akademik  

Copyrights © 2025






Journal Info

Abbrev

JSSR

Publisher

Subject

Computer Science & IT Economics, Econometrics & Finance Education Social Sciences

Description

Journal of Science and Social Research is accepts research works from academicians in their respective expertise of studies. Journal of Science and Social Research is platform to disclose the research abilities and promote quality and excellence of young researchers and experienced thoughts towards ...