Indah Nur Qoriah
Universitas Binaniaga Indonesia

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

Found 1 Documents
Search

Penerapan Metode K-Nearest Neighbor untuk Prediksi Penjualan Sparepart Mobil pada Gudang Marketplace Indah Nur Qoriah; Leny Tritanto Ningrum
Jurnal SAINTEKOM (Sains dan Teknologi Komputasi) Vol 2 No 3 (2026): September 2026
Publisher : Lembaga Penelitian, Pengembangan, dan Pengabdian Kepada Masyarakat (LP3M) – Universitas Binaniaga Indonesia (UNBIN)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36350/jskom.v2i3.124

Abstract

This study focuses on predicting car spare parts sales in a marketplace warehouse by employing the K-Nearest Neighbor (K-NN) algorithm. K-NN is utilized as an effective data mining technique for classification in order to construct an accurate predictive model. The dataset used in this research consists of key attributes, including spare part name, sales volume, quantity, price, condition, and brand. A web-based prototype was developed using PHP, enabling accessibility across devices and providing itemset predictions through Euclidean distance analysis. To assess model performance, evaluation was carried out using a confusion matrix, which produced an accuracy of 72%, precision of 86%, and recall of 100%. Furthermore, a feasibility test of the system achieved a perfect score of 100%, while user testing resulted in 83.03%, both of which indicate that the system is highly feasible and user-friendly. The research findings confirm that the K-NN method can deliver effective and reliable predictions of car spare parts sales. Beyond its theoretical contribution in expanding insights into K-NN applications, this study also offers practical value by supporting inventory management efficiency and assisting company management in making strategic business decisions.