Personalized product recommendation in e-commerce

The purpose is to analyze customers´ purchasing behaviors based on product features from transaction records and product feature databases. Customers´ preferences toward particular features of products are analyzed and then rules of customer interest profiles are thus derived in order to recommend customer products that have potential attraction with customers. The approach of this paper has its strength to be able to recommend to customers brand new products or rarely purchased products as long as they fit customer interest profiles. This research also derives customers´ interest profiles that can explain recommendation results. The interests on particular features of products can be referenced for product development.