Improving Temporal Recommendation Accuracy and Diversity via Long and Short-Term Preference Transfer and Fusion Models

摘要：

　　Temporal factor plays an important role in products and services recommended process.It is necessary to combine temporal factors with effective methods to improve recommendation performance.In this paper,we present a novel approach to improve personalized recommendation performance with changing user preferences based on temporal dataset.In the approach,we take consideration of different influence of long and short-term user preferences and construct a preference transfer model based on our enhanced Hidden Markov Model.Then we accomplish preference fusion by adopting our Long and Short Term Graph,a graph model modified from Session-based Temporal Graph,to recommend unknown items.Finally,the experimental results show that our approach achieves important improvements compared to some existing approaches in performance.

关键词： HMM Long and short term Graph model Preference transfer Preference fusion

作者: Bei Zhang Yong Feng

作者单位: College of Computer Science,Chongqing University,Chongqing 400030,China;Key Laboratory of Dependable Service Computing in Cyber Physical Society,Ministry of Education,Chongqing University,Chongqing 400030,China

会议类型: 国际会议

会议名称: International Asia-Pacific Web Conference(第18届国际亚太互联网大会)

会议地点: 苏州

会议语种:英文

页码: 174-185

在线出版日期: 2016-09-23（万方平台首次上网日期，不代表论文的发表时间）