<![CDATA[Harto Joyo Store faces challenges in inventory management due to manual recording processes. The main issue in managing sales data lies in the difficulty of grouping products based on sales patterns to support marketing strategies. This research aims to design and develop a web-based system capable of clustering products using the K-Means Clustering algorithm. The system was developed using the System Development Life Cycle (SDLC) with the Waterfall model, utilizing a dataset of 1,630 sales records from February 2023 to January 2024. The data was processed through the Knowledge Discovery in Databases (KDD) stages, which include Data Selection, Data Preprocessing, Data Transformation, Data Mining, and Knowledge Interpretation/Evaluation. The clustering process resulted in three data groups (Cluster 1 with 9 records, Cluster 2 with 191 records, and Cluster 3 with 28 records), with the number of clusters determined using the Elbow method. Cluster 1 represents best-selling products that require a high stock level, Cluster 2 includes low-demand products with minimal stock needs, and Cluster 3 consists of moderately-selling products that require a balanced inventory level. Evaluation using the Davies-Bouldin Index (DBI) yielded a DBI score of 0.356 for K=3, indicating optimal clustering results as it approaches zero. Initial testing shows that the system accurately classifies products into several sales clusters and can be used as a basis for business decision-making. This research contributes by providing a sales analysis system that can be integrated with the company’s information system. The analysis reveals that low-selling products dominate the data, suggesting that Harto Joyo Store should implement marketing strategies such as discounts or promotions to boost sales.]]>
Copyrights © 2025
