<![CDATA[This study aims to implement the K-Means Clustering algorithm to classify inventory items at PT. Deli Farm Indonesia in order to improve inventory management efficiency and support managerial decision-making based on sales data patterns. This research employed a data mining approach using the Knowledge Discovery in Databases (KDD) framework. The research stages consisted of data collection, preprocessing, data transformation, clustering using the K-Means algorithm, and evaluation of clustering results. The implementation process was carried out using RapidMiner software with inventory transaction data obtained from PT. Deli Farm Indonesia. The implementation of the K-Means Clustering algorithm successfully classified inventory items into several clusters according to their sales characteristics and stock movement. The clustering results provide useful information for identifying fast-moving and slow-moving products, enabling the company to optimize inventory control, reduce excess stock, and improve inventory planning efficiency. The K-Means Clustering algorithm can be effectively applied to inventory management by providing meaningful classifications of inventory items. The resulting clusters can support strategic decision-making in warehouse management and contribute to more efficient inventory control at PT. Deli Farm Indonesia.]]>
Copyrights © 2026
