Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Dhea Nurul Utami
Universitas Royal Asahan Sumatera Utara
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
METODE K-MEANS UNTUK KLASIFIKASI PENJUALAN DI TOKO SINAR FASHION DAN BANANA BABY SHOP DI KOTA KISARAN Dhea Nurul Utami; Dewi Anggraeni; Mardalius
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 1 (2026): Januari
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i1.6620

Abstract

Sinar Fashion and Banana Baby Shop are businesses that sell children's supplies with a wide variety of products. However, the problem they face is suboptimal inventory management due to the lack of an accurate sales classification system. This makes it difficult to understand consumer preferences and determine efficient procurement strategies. This study aims to apply a web-based K-Means Clustering algorithm to automatically group children's product sales based on characteristics and sales volume. The research methodology includes six stages: data collection, problem identification, literature review, system design using UML, system development using PHP and Sublime Text, and system implementation. Sales data from February to May 2025 was used as training data for the clustering process. The system is designed to group products into several clusters, such as best-selling, less popular, and non-selling products. The results of the study indicate that the K-Means method is effective in identifying similar sales patterns between products. The quality of the clustering was evaluated using two metrics, namely the silhouette score and the Davies-Bouldin Index. A silhouette score of 0.74 indicates good clustering quality, while the Davies-Bouldin Index of 0.42 shows a fairly clear separation between clusters. The combination of these two metrics reinforces the validity of the clustering results. The application of this system helps store owners make more informed decisions, such as inventory planning, promotional strategies, and distribution efficiency.
Co-Authors Dewi Anggraeni Mardalius