ANALYSIS OF HIERARCHICAL CLUSTERING AND K-MEAN METHODS WITH LRFMP MODEL ON CUSTOMER SEGMENTATION ASEP MUHIDIN ABSTRACT Customer is something valuable and important, if all customers are similar, business will be so simple. The problem of heterogeneity and the large number of customers is a challenge to be faced in determining potential customer segmentation. Companies must be able to plan, create and implement strategies for treating heterogeneous consumer traits. RFM Model Approach, which is a segmentation model based on the attributes of Recency, Frequency, and Monetary. Model RFM is a segmentation model commonly used in companies. In this research, customer segmentation process begins with preprocessing process, analytic hierarchy process (AHP), search for the best value of all Hierarchical Clustering methods by comparing the Bouldien-Index value. Furthermore, the value of K is chosen to be the initial value in K-Mean Clustering. The clustering result is used to segment the RFM model to get the consumer class. The addition of Payment parameter (LRFMP) can increase the value of customer loyalty to the company. Based on the research results, the single linkage method is the best method to find the value of K. Segmentation of the k-mean model with the addition of the P (LRFMP) parameter can increase the DBI value compared to the weighted RFM model or not. But the DBI value of the single linkage segmentation method is still better than the k-mean segmentation. Keywords : CRM, data mining, preprocessing, Hierarchical Clustering, Bouldien-Index, clustering, segmentation, RFM, LRFMP, Customer.