<![CDATA[Managing fresh vegetable inventory requires accurate decision-making because of its limited shelf life and variations in unit prices and sales volumes. This study aims to segment vegetable sales transactions at D2 Vegetables, a vegetable supplier, using K-Means Clustering based on unit price and sales volume; evaluate cluster quality; and develop operational recommendations based on the characteristics of each segment. The dataset consists of 1,016 vegetable sales transactions recorded from June 25, 2024, to June 23, 2025. The analytical procedures included data preprocessing, standardization, determination of the optimal number of clusters using the Elbow Method, evaluation using the Silhouette Coefficient and Davies-Bouldin Index, K-Means clustering, and comparison with Agglomerative Hierarchical Clustering. Internal evaluation indicated that K = 2 achieved the highest Silhouette Coefficient (0.6114) and the lowest Davies-Bouldin Index (0.5156). However, K = 3 was selected by considering the Elbow pattern, cluster structure quality, and interpretability of the resulting three transaction segments. At K = 3, K-Means achieved a Silhouette Coefficient of 0.5719 and a Davies-Bouldin Index of 0.6029, outperforming Agglomerative Clustering, which achieved scores of 0.5031 and 0.6595, respectively. The resulting segmentation comprised 682 Standard transactions (67.13%), 235 Bulk transactions (23.13%), and 99 Premium transactions (9.74%). The Bulk segment had the highest total sales volume, the Standard segment had the largest number of transactions and the greatest diversity of vegetable types, while the Premium segment had the highest average unit price and relatively low sales volume. The segmentation results can serve as a decision-support basis for procurement planning, inventory management, storage allocation, and segment-specific promotional strategies, enabling operational decisions to be aligned with the characteristics of each transaction segment.]]>
Copyrights © 2026
