Recommender Systems Based on Doubly Structural Network

摘要：

In the context of recommender systems, there are two important entities: users and items, and three relationships: users relationship, items connection and interactions between users and items. In most literature, one or more of these entities and relationships are used to predict users preference. In this paper, we proposed a novel approach which incorporates these two entities and three relationships into one framework based on doubly structural network (DSN) and built a dynamic prediction model for users preference over time. And we have proved that the new approach can give a good performance for recommender systems through experiment.

关键词： Recommender system Doubly structural network Dynamic prediction model

作者: Na Chang Takao Terano

作者单位: Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology,Tokyo, Japan, 2268502

会议类型: 国际会议

会议名称: The 8th International Conference on Innovation and Management(第八届创新与管理国际会议 ICIM 2011)

会议地点: 日本福冈

会议语种:英文

页码: 975-981

在线出版日期: 2011-11-30（万方平台首次上网日期，不代表论文的发表时间）