An algorithmic framework for performing collaborative filtering

被引:1300
作者
Herlocker, JL [1 ]
Konstan, JA [1 ]
Borchers, A [1 ]
Riedl, J [1 ]
机构
[1] Univ Minnesota, Dept Comp Sci & Engn, Minneapolis, MN 55455 USA
来源
SIGIR'99: PROCEEDINGS OF 22ND INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL | 1999年
关键词
D O I
10.1145/312624.312682
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Automated collaborative filtering is quickly becoming a popular technique for reducing information overload often as a technique to complement content-based information filtering systems. In this paper we present an algorithmic framework for performing collaborative filtering and new algorithmic elements that increase the accuracy of collaborative prediction algorithms. We then present a set of recommendations on selection of the right collaborative filtering algorithmic components.
引用
收藏
页码:230 / 237
页数:8
相关论文
共 26 条
[1]  
*ACM, 1992, COMMUNICATION ACM, V35
[2]  
[Anonymous], 1994, P 17 ANN INT ACM SIG
[3]  
[Anonymous], 1987, COMMUNICATIONS ACM
[4]  
[Anonymous], STATISTICS
[5]  
[Anonymous], 1986, NUMERICAL RECIPES C
[6]   Fab: Content-based, collaborative recommendation [J].
Balabanovic, M ;
Shoham, Y .
COMMUNICATIONS OF THE ACM, 1997, 40 (03) :66-72
[7]  
BASU C, 1998, P 1998 WORKSH REC SY, P11
[8]  
BILLSUS D, 1998, P 1998 WORKSH REC SY
[9]  
Breese J. S., 1998, UAI, P43, DOI 10.5555/2074094.2074100
[10]  
Dahlen B. J., 1998, 98017 TR U MINN