Research On The Collaborative Filtering Algorithm Based On The Item Clustering

With the increasing of the Internet and the development of E-Commerce, the structures of E-Commerce web sites become more and more complex. Therefore,it is hard for consumers to find the products and services wanted. To address this issue, recommendation systems have been proposed to suggest products and helpful information for consumers. Recommendation systems can enhance E-Commerce sales by converting browsers into buyers, increasing cross-sell and building loyalty to prevent user losing. Recommendation systems have gradually become an important part in E-Commerce. More and more research papers about recommendation systems of E-Commerce appear in many kinds of conferences and journals. Though recommendation systems of E-Commerce have been very successful in both research and practice, challenging research problems remain. Aimed at the main challenges of recommendation systems of E-Commerce, this thesis studies some key techniques of recommendation systems of E-Commerce. The main research work in this thesis includes the research of recommendation algorithm, and the research on the structure of recommendation systems. The thesis introduces E-commence recommendation systems and the typical technologies that are implemented in them, the recommendation system based on association rule and the collaborative filtering based on user. In large E-Commerce systems, the real-time requirement of recommendation system is hard to be satisfied. To address this issue, we propose a collaborative filtering recommendation algorithm based on item clustering. This approach first clusters items by the users' rating on items, based on the similarity between target item and cluster centers, the most similar clusters are selected as the search space, in which to search the nearest neighbor of target item. We theoretically analyze the new approach and prove its feasibility. Finally, we summarize the thesis and point out the future research work.