线性逐步遗忘协同过滤算法的研究

被引:23
作者
郑先荣
曹先彬
机构
[1] 中国科技大学计算机科学与技术系
关键词
协同过滤; 兴趣变化; 线性逐步遗忘;
D O I
暂无
中图分类号
TP301.6 [算法理论];
学科分类号
摘要
协同过滤系统是目前最成功的一种推荐系统,但是传统的协同过滤算法没有考虑用户兴趣变化问题,导致用户兴趣发生变化时的推荐质量较差。该文借鉴心理学遗忘规律,提出了线性逐步遗忘协同过滤算法。该算法依据评价时间线性逐步减小每项评分的重要性。基于MovieLens数据集的实验结果表明,该算法在准确性方面优于传统的协同过滤算法。
引用
收藏
页码:72 / 73+82 +82
页数:3
相关论文
共 10 条
  • [1] A Survey of Personalization Technology. Zeng Chun,,Xing Chunxiao,Zhou Lizhu. Journal of Software . 2002
  • [2] Medical Psychology. Yuan Genqing. . 1995
  • [3] Research on Personalized Recommendation Algorithm for USer‘s Multiple Interests. Yu Li,Liu lu,Li Xuefeng. Computer Integrated Manufacturing Systems . 2004
  • [4] Evaluation of Item-based Top-N Recommendation Algorithms. Karypis G. Dept.of Computer Science,University of Minnesota,Technical Report:#00-046 . 2000
  • [5] Collaborative Filtering. Cai Deng,Lu Zen-xiang,Li Yanda. Computer Science . 2002
  • [6] Drifting Concepts as Hidden Factors in Clinical Studies. Kukar M. Proc of the9th Conf.on Artificial Intelligence in Medicine in Europe . 2003
  • [7] Using Collaborative Filtering to Weave an Information Tapestry. Goldberg D,Nichols D,Oki B M. Communications of the ACM . 1992
  • [8] Item-based Top-N Recommendation Algorithms. Deshpande M,Karypis G. ACM Transactions on Information Systems . 2004
  • [9] Adaptation to Drifting User’s Interests. Koychev I,Schwab I. Proc of ECML’00 . 2000
  • [10] Item-based Collaborative Filtering Recommendation Algorithms. Sarwar B,Karypis G,Konstan J. Proc of the10th International World Wide Web Conference . 2001