Mining association rules using RFM scoring method for personalized u-commerce recommendation system in emerging data

Abstract

This paper proposes a new mining technique using RFM (Recency, Frequency, Monetary) scoring method for personalized u-commerce recommendation system in emerging data under ubiquitous computing environment which is required by real time accessibility and agility. In this paper, using a implicit method without onerous question and answer to the users to reduce customers' search effort, it is necessary for us to keep the analysis of RFM scoring method to reflect the attributes of the item and to generate association rules based on the most frequently purchased data extracted from the whole data with the item RFM score to recommend the items with high purchasability according to the threshold for creative association rules with support, confidence and lift. To verify improved performance, we make experiments with dataset collected in a cosmetic internet shopping mall. © 2012 Springer-Verlag Berlin Heidelberg.