Optimize the WEB personalized recommender model using market mechanism

摘要：

Based on the analysis of the current hybrid recommender systems, this paper proposes a new recommender system framework to overcome the disadvantage of these hybridization technologies. In the new system, various WEB personalized recommending methods are integrated into a market model. It is capable of producing recommendations for the unregistered users. And a finely reasonable auction process is designed to do the markets job and the key procedures are detailed. This model is able to serve unregistered users with high-quality recommendations continuously under the effect of the markets positive feedback. The preliminary experiments show the feasibility and effectiveness of the optimization approach.

关键词： Web personalized Recommendation Hybrid Recommender System Market Mechanism

作者: Yi-dan Su Hui-lin Guo

作者单位: School of comp.& elec.info.Guangxi University Nanning, China

会议类型: 国际会议

会议名称: 第四届国际计算机新科技与教育学术会议(2009 4th International Conference on Computer Science & Education)

会议地点: 南京

会议语种:英文

页码: 1272-1277

在线出版日期: 2009-07-25（万方平台首次上网日期，不代表论文的发表时间）