Adaptive Clustering of Merchandise Code for Recommender System with an Immediate Effect

摘要

This paper proposes recommending method with an immediate effect through adaptive clustering method based on segmented merchandise code in e-commerce. Using an implicit method without onerous question and answer to the users, it is necessary for us to do the task of clustering using merchandise code in purchase data extracted from whole data, to join customer's data, to keep the analysis of RFM (Recency, Frequency, and Monetary) in order to segment merchandise with an immediate effect by Bayesian suggestion to consider frequently changing customer's preference. We reflect the importance of attribute for merchandise code and then take adaptive clustering of merchandise code customer prefer to forecast frequently changing customer's preference of merchandise code efficiently. We carry out experiments with data set of internet cosmetic shopping mall to measure its performance. We report some of the experimental results.