Article Per Year (5 Year)
p-Index From 2020 - 2025
1.182
P-Index
This Author published in this journals
All Journal TRANSBORDERS: International Relations Journal JURNAL PENDIDIKAN TAMBUSAI Jurnal Lentera Pendidikan Pusat Penelitian LPPM UM Metro Journal of Informatics Management and Information Technology Innovative: Journal Of Social Science Research Paradigma Journal of Administration Jurnal Penelitian dan Pengabdian Masyarakat
Salsabila, Amanda
Unknown Affiliation
Arts Humanities Computer Science & IT Decision Sciences, Operations Research & Management Education Engineering Law, Crime, Criminology & Criminal Justice Public Health Social Sciences Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Journal of Informatics Management and Information Technology

 1 
Metode Hybrid Dalam Pengelompokkan Kemampuan Calistung Siswa Berbasis Machine Learning Salsabila, Amanda; Andri Anto Tri Susilo; Nelly Khairani Daulay
Journal of Informatics Management and Information Technology Vol. 5 No. 2 (2025): April 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jimat.v5i2.500

Abstract

Students reading, writing, and arithmetic abilities (reading, writing, and arithmetic) are an important foundation in the academic development of elementary school students. This study aims to group students' reading, writing, and arithmetic abilities using a hybrid method based on machine learning, with grade data from two Elementary Schools in Lubuklinggau City. The method applied combines the K-Means Clustering algorithm for initial grouping and K-Nearest Neighbors (KNN) for classification. The analysis process includes data preprocessing, application of K-Means, cluster validation using Silhouette Score, and classification with KNN to ensure accuracy. As a result, K-Means successfully grouped students into three clusters: Middle (0), Low (1), and High (2). The KNN model with k = 3 which has the highest accuracy of 95% provides very good accuracy in testing the K-Nearest Neighbors (KNN) classification model with an accuracy of 97%, with very good precision, recall, and F1-score values for all clusters. These findings indicate that this hybrid approach is effective in classifying students' reading, writing and arithmetic abilities, which has implications for the development of more targeted learning strategies based on the characteristics of each group of students.
Co-Authors Abdul Syahid Andri Anto Tri Susilo, Andri Anto Aulia, Norin Nur A’yun, Nada Qurrota Fitrian, Novia Hafidzudin, Hasan Hendry Putra, Hendry Julia Kusumaningrum, Tria Angela L, Resti Amelinda I. Meilyani, Annisa Metra, Pol Nanda, Marisa Shermia Nelly Khairani Daulay Nurkaidah, Nurkaidah Oktara, Ridho Qomariah, Zaitun Riandityo, MHD Malzi Syamsul Bahri Zumiyati, Zumiyati