Answers are grounded in this paper and cite their sources.
Accurate customer segmentation supports more personalized e-commerce marketing. However, the Recency, Frequency, Monetary (RFM) model focuses on transaction history and may not fully capture shopping motivation or the share of a consumer’s spending allocated to e-commerce (Share of Wallet/SoW). This study aims to cluster e-commerce users based on transaction profiles and consumer behavior using the K-Prototypes algorithm. Data were collected from 198 e-commerce users in Palembang, Indonesia. The clustering variables included RFM, SoW, shopping motivation, and product-category preferences, while age category was used for follow-up analysis. The Elbow Method and Silhouette Score supported a four-cluster solution. The resulting personas were High-Value Promo Hunters, Routine Pragmatic Shoppers, Passive Micro-Spenders, and Urgent Big-Ticket Buyers. The Chi-square test indicated a significant association between age category and persona, with Cramér’s V of 0.274. This suggests that age is associated with shopping patterns but does not fully determine consumer profiles. The findings can inform more targeted promotions and user-experience design. The study is limited to 198 respondents from Palembang, so the findings may not represent e-commerce users in other regions.
No takes yet. Share an insight, caveat, or question.
Akbar et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: