摘要
0 引言
电子商务系统随着Internet和WWW的发展而蓬勃兴起,1997年零售业的在线交易是20多亿美元,而预计到2001年有望达到170亿美元[1].电子商务的发展对推荐系统也提出了更高的要求,用于电子商务网站的推荐系统能实时地向顾客提供商品推荐服务,而推荐何种商品则往往取决于该商品的购买率、人口统计学原理及对该顾客过去该网站购物成交记录的分析.这些因素的考虑使这些商业网站具有了个性化色彩,因为对于不同的用户,具有推荐系统的商业网站表现出了一定的自适应性.
Recommender Systems provide the user with the items that they might wish to purchase.The most well known approaches are collaborative filtering approach,knowledge-based approach and a hybrid one which integrates two methods above together. Each of them has their own weaknesses and strengths. The common problems of the current recommender systems and their corresponding counter-measures are discussed in this paper to make the recommender system more adaptive and more effective.
出处
《计算机科学》
CSCD
北大核心
2001年第4期122-124,共3页
Computer Science
基金
国家留学基金
