摘要
个性化推荐系统采用知识发现技术给用户提供准确、合理的信息从而赢得客户。基于用户群组特征的推荐方式是当前在研究和实用两方面都取得一定成功的一种模式,但是这种算法的复杂度随着用户数量的增加而急剧增长,因此在实际的应用中,面对着数以万计的用户,服务系统要承担大负荷的计算量,从而导致推荐效率的下降。该文提出了一种基于特征项的推荐算法来解决基于用户的推荐算法所面临的可扩展性差的问题。实验表明,使用基于特征项的推荐算法能够在提高推荐效率的同时,达到或者超越基于用户的推荐算法的推荐性能。
Individuation information recommendation service systems apply knowledge discovery techniques to the problem of making personalized recommendations for information.These systems ,especially the user -based system,are achieving widespread success on Web.However,the amount of work increases with the number of users in the system.New technologies are needed that can quickly produce high quality recommendations,even for very large scale problems.This paper introduces different item-based recommendation generation algorithms.The experiments suggest that item-based algorithms provide dramatically better performance than user-based algorithms ,while providing better quality that user-based algorithms.
出处
《计算机工程与应用》
CSCD
北大核心
2004年第15期4-5,181,共3页
Computer Engineering and Applications
基金
国家863高技术研究发展计划项目资助(编号:2002AA117010-07)