Beijing Institute of Technology/School of management and economic, Beijing, China

---

Abstract—Collaborative recommendation is a key issue today in e-commerce, which helps users find the information of products which they are interested in from the mass of information. Aiming at the problem in an insufficient personalization of e-commerce recommendation system ， a user preference-oriented network model is established in the paper. Related theories and techniques of clustering are used to analyze the extracted preferences of the users. Finally, combined with the traditional collaborative filtering method, the paper proposed the user preference-oriented collaborative recommendation algorithm. The experimental results show that compared to the traditional collaborative filtering algorithm, user preference-oriented collaborative recommendation algorithm can effectively improve the efficiency of ecommerce recommendation system in ensuring the accuracy of the premise.

Index Terms—collaborative recommendation, user preference, e-commerce, clustering analysis, neural network

[PDF]

Cite: Huiying Gao, Susu Wang, Bofei Yang, Hangzhou Yang, "User Preference-oriented Collaborative Recommendation Algorithm in E-commerce," Journal of Software vol. 9, no. 7, pp. 1886-1893, 2014.