<![CDATA[ The expansion of the retail business requires business operators to accurately group best-selling and slow-moving products in order to optimize inventory adjustment strategies. This study aims to cluster sales transaction data and determine the optimal number of clusters using the K-Means algorithm. A secondary dataset consisting of 7,373 transaction records was analyzed based on the attributes of transaction count and total sales. The best cluster number was determined using the Elbow method based on the Sum of Squared Errors and validated using the Davies-Bouldin Index. The test results show that both methods consistently produced an optimal number of clusters, k, equal to 4, with a Davies-Bouldin Index value of 0.47. This value indicates a very well-separated cluster structure. The final clustering resulted in four product performance categories: 2 “best-selling” products, 20 “selling well” products, 171 “moderately selling” products, and 7,180 “poorly selling” products. This evaluation demonstrates that the combination of K-Means, the Elbow method, and the Davies-Bouldin Index effectively provides data-driven insights to support inventory management decision-making in the retail business.]]>
Copyrights © 2026
