首页 | 本学科首页   官方微博 | 高级检索  
     

结合用户背景信息的协同过滤推荐算法
引用本文:吴一帆,王浩然.结合用户背景信息的协同过滤推荐算法[J].计算机应用,2008,28(11):2972-2974.
作者姓名:吴一帆  王浩然
作者单位:南京大学软件学院,南京,210093
摘    要:针对个性化推荐系统中协同过滤算法面对的数据稀疏问题,提出了一种结合用户背景信息的推荐算法。该算法充分利用已有的用户数据和领域知识,对用户背景信息的相似度建模,在进行协同过滤前预先填充用户-项评分矩阵。实验表明该方法能够有效地提高推荐精度,并且不会带来性能上的瓶颈。

关 键 词:个性化推荐  协同过滤  用户背景信息  相似度建模
收稿时间:2008-05-20
修稿时间:2008-07-28

Collaborative filtering algorithm using user background information
WU Yi-fan,WANG Hao-ran.Collaborative filtering algorithm using user background information[J].journal of Computer Applications,2008,28(11):2972-2974.
Authors:WU Yi-fan  WANG Hao-ran
Affiliation:WU Yi-fan,WANG Hao-ran(Software Institute,Nanjing University,Nanjing Jiangsu 210093,China)
Abstract:Aiming at the difficulty of data sparsity in personalized recommendation systems, a new collaborative filtering algorithm using user background information was presented. The algorithm took full advantage of user data and domain knowledge in hand, modeled user similarity based on user background information and filled in the user-item rating matrix in advance before the traditional collaborative filtering. The experimental results show that the new algorithm can improve the recommendation accuracy efficiently and will not cause bottleneck on performance.
Keywords:personalized recommendation  collaborative filtering  user background information  similarity modeling
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机应用》浏览原始摘要信息
点击此处可从《计算机应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号