<![CDATA[Aisyah Catering is a Micro, Small, and Medium Enterprise (MSME) in the catering service sector that has conventionally recorded order transactions manually. Consequently, the business owner faces difficulties in comprehensively understanding customer order patterns to formulate targeted marketing strategies. This study aims to segment Aisyah Catering's customers based on order volume using the K-Means algorithm. The research methodology follows the CRISP-DM framework, initiating with the collection of 197 transaction records digitized from physical receipts, followed by data preprocessing using Altair AI Studio to yield 187 valid records. In the modeling phase, K-Means was applied to the order quantity (number of portions) attribute as the sole quantitative variable in the clustering process. The determination of the optimal number of clusters was conducted through the evaluation of values from the Elbow Method and the Davies-Bouldin Index (DBI). The results demonstrate that k=3k=3 was selected as the optimal number of clusters with a DBI value of 0.449. The three resulting segments are: the small-scale segment (49.2% of customers, averaging 360.11 portions), the medium-scale segment (33.7% of customers, averaging 717.78 portions), and the large-scale segment (17.1% of customers, averaging 1,045.31 portions). A notable finding emerges regarding volume contribution: the large-scale segment, despite having the fewest members, accounts for 29.9% of the total order volume—nearly equal to the contribution of the small-scale segment which has nearly three times as many members. Thus, the results of this segmentation serve as a foundational basis for Aisyah Catering in designing marketing strategies, raw material procurement planning, and tailored service delivery aligned with the characteristics of each customer segment.]]>
Copyrights © 2026
