<![CDATA[This study aims to develop an effective customer segmentation model for PT Sukses Nusantara Sakti 21 Bali, a large-scale multi-level marketing distributor with over 60,000 members. The proposed approach integrates the Recency, Frequency, Monetary (RFM) model with the Fuzzy C-Means (FCM) algorithm to analyze one year of sales transaction data. The CRISP-DM framework was adopted to ensure a structured process, consisting of business understanding, data understanding, data preparation, modeling, evaluation, and deployment. Customer transaction records were preprocessed to compute normalized RFM scores, which were then clustered using FCM to capture overlapping membership patterns and better reflect behavioral diversity. The segmentation results were validated using the Silhouette Coefficient and Davies–Bouldin Index, achieving scores of 0.6005 and 0.5093, respectively, indicating high-quality cluster compactness and separation. Three distinct customer segments were identified, each providing actionable insights for targeted marketing strategies, including retention, engagement, and reactivation programs. The findings confirm that integrating RFM and FCM offers a robust and flexible approach for customer segmentation in large-scale MLM contexts. Future work may involve real-time segmentation and integration with predictive analytics to further enhance marketing decision-making.]]>
Copyrights © 2025
