Inventory Information System Using the DBSCAN Clustering Method for Stock Optimization at Mami Fashion Store

Abstract

Advances in information technology are encouraging retail businesses to manage inventory more effectively and efficiently. Mami Fashion, a clothing retailer, faces challenges in inventory management, such as the accumulation of less-demanded items and the out-of-stock of high-selling products. This study aims to design and build an inventory information system using the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) method to optimize inventory management. The DBSCAN method is used to group sales data based on density and purchasing patterns, thus identifying fast-selling, medium-selling, and slow-selling products, as well as detecting data anomalies. The system was developed web-based to facilitate the process of recording, monitoring, and analyzing inventory in real time. The results show that implementing the DBSCAN method in the inventory system can improve the accuracy of product grouping, assist in procurement decision-making, and reduce the risk of overstock and stockouts. Thus, the system can support operational efficiency and increase the profitability of Mami Fashion.