Customer Segmentation and Precision Marketing for E-commerce FMCG Brands Based on Clustering Analysis A Case Study of Bluemoon
Tao Lin
Advances in Humanities and Modern Education Research Vol. 5 / No. 1 / pp. 88-94 / August 24, 2026
Tao Lin
Advances in Humanities and Modern Education Research Vol. 5 / No. 1 / pp. 88-94 / August 24, 2026
E-commerce FMCG brands face rising costs and low repurchase rates, yet traditional RFM models ignore cyclical consumption patterns. Using Bluemoon's 2021-2024 data (1,500 customers, 27,165 orders), this study adds two temporal features—purchase-interval CV and future purchase window—to RFM. K-Means clustering (K=3, Silhouette=0.14) yields three segments: Stockpile Routiners (29.7%), Lifecycle-Sensitive (38.2%), and Scenario Buyers (32.1%). Differentiated time-triggered and scenario-based strategies are designed. Monte Carlo simulations show churn drops 66.7% (to 4.0% vs. RFM's 6.73%) and ROI rises 45.0% (47.12 vs. 39.98), confirming temporal features' value in FMCG precision marketing.
Keywords
Precision E-commerce Marketing / Customer Segmentation / Temporal Feature Clustering / FMCG Marketing / Purchase Cycle