RFM Weight Analysis for Customer Segmentation in Coffee Sector

This study proposed a method using the Analytic Hierarchy Process (AHP) to derive RFM weights suitable for the characteristics of each industry, and compared and analyzed this with the existing traditional RFM weighting method using customer data from CompWany C, an actual coffee franchise company. AHP has the advantage of being able to calculate weights based on the subjective judgment of evaluators, so it can quantitatively express quatlitative factors. Since evaluators belong to the industry, it can effectively reflect the characteristics of the industry. In this study, customers were subdivided through the K-Means Clustering algorithm using the RFM score, and the quality of the cluster according to the two weighting methods was compared. As a result of the study, it was confirmed that the proposed weight derivation method showed higher cluster quality than the existing traditional method, and that the segmentation suitable for the coffee industry was made. Future research requires empirical research through quantitative expansion of customer data, advancement of the preprocessing process for RFM variables, improvement of the AHP stage, and application of various machine learning techniques