摘要
针对协同过滤中的数据稀疏问题,提出了一种基于粗集的协同过滤算法.首先通过自动填补空缺评分降低数据稀疏性;然后采用分类近似质量计算用户间的相似性形成最近邻居,产生推荐预测.实验结果表明,该算法有效地解决了数据稀疏问题,提高了推荐的质量.
Aiming at the problem of data sparsity for collaborative filtering, a novel rough set-based collaborative filtering algorithm is proposed. This algorithm addresses the issue by automet.ically filling vacant ratings, uses the quality of approximation of classification to compute user similarity and form nearest neighborhood, and then generates recommendations. The experiment results argue that the algorithm efficiently improves sparsity of rating data, and promises to make recommendations more accurately than conventional CF algorithms.
出处
《小型微型计算机系统》
CSCD
北大核心
2005年第11期1971-1974,共4页
Journal of Chinese Computer Systems
基金
国家自然基金(70371004)资助
关键词
协同过滤
数据稀疏
粗集
分类近似质量
collaborative filtering
data sparsity
rough set
quality of approximation of classification
