RECOMMENDATION SYSTEM RESEARCH FOR BTOC COMMERCE SITE

摘要

Web-based BtoC commerce applications with a large variety of users suffer from the inability to satisfy heterogeneous needs. A remedy for the negative effects of the traditional "one-size-fits-all" approach is to build a recommendation system at commerce site to customize the interaction with users. We discuss a recommendation system architecture that works at three layers including some function modules to produce multiple models of users and items and derive right recommendation for a user. And web data mining technology, AI and statistic technology are applied in it.