摘要
针对传统的电子商务协同过滤推荐算法难以准确定位目标用户的最近邻居社区且推荐质量和准确性不高的问题,设计了一种基于用户偏好挖掘的电子商务协同过滤推荐算法。该算法利用用户偏好挖掘技术进行用户显性偏好知识和隐性偏好知识的挖掘分析,实现基于用户偏好知识的最近邻居社区构建和智能推荐。实验结果表明,该算法取得了较理想的预期效果,显著提高了协同过滤推荐的质量和准确性。
To address the low accuracy of identifying nearest neighbors and bad recommendation performance in traditional collaborative filtering algorithm, an E-commerce collaborative filtering recommendation algorithm based on user preference mining is proposed. The algorithm uses user preference mining technology to mine user preference knowledge including explicit preference knowledge and tacit preference knowledge, realizing the nearest neighbor community construction and intelligent recommendation. Experimental results suggest that this algorithm achieved a good anticipative effect. It improves the accuracy and efficiency of collaborative filtering recommendation dramatically.
出处
《情报科学》
CSSCI
北大核心
2013年第12期38-42,共5页
Information Science
关键词
协同过滤推荐
用户偏好挖掘
电子商务
collaborative filtering recommendation
user preference mining
E-commerce
