<![CDATA[Inventory management at multi-SKU distribution companies becomes complex when most products have unstable and intermittent demand patterns. At PT JJA, procurement is still reactive without the use of historical patterns, while the previous approach generally relied on aggregate indicators such as average sales so that it has not been able to comprehensively capture temporal dynamics. This study aims to group products based on temporal demand patterns using K-Means Clustering in 11,988 transactions for the 2020–2025 period which are processed into 261 products through monthly aggregation, with features of average sales, coefficient of variation (CV), zero_month_ratio, Average Demand Interval (ADI), and trends. The results showed four optimal clusters (k = 4) with a Silhouette Score of 0.62 and an unbalanced distribution, where one cluster dominated 240 products. The values of zero_month_ratio (>0.80), ADI up to >12 months, and CV up to >3.5 show intermittent demand patterns and long-tail structures. The study confirms that the integration of temporal features (ADI, zero_month_ratio, CV, and trend) transforms the representation of demand from static aggregates to dynamic structures, while linking segmentation results with more adaptive procurement strategies to reduce the risk of overstock and understock.]]>
Copyrights © 2026
