Journal of Computer Applications ›› 2015, Vol. 35 ›› Issue (7): 1988-1992.DOI: 10.11772/j.issn.1001-9081.2015.07.1988

Previous Articles     Next Articles

Collaborative filtering recommendation system based on multi-attribute utility

DENG Feng1,2, ZHANG Yongan1   

  1. 1. College of Economics and Management, Beijing University of Technology, Beijing 100124, China;
    2. Physical Education College, Zhengzhou University, Zhengzhou Henan 450044, China
  • Received:2015-01-22 Revised:2015-03-22 Online:2015-07-10 Published:2015-07-17

基于多属性效用的协同过滤推荐系统

邓峰1,2, 张永安1   

  1. 1. 北京工业大学 经济与管理学院, 北京 100124;
    2. 郑州大学 体育学院, 郑州 450044
  • 通讯作者: 邓峰(1977-),女,河南登封人,副教授,博士研究生,主要研究方向:管理决策、推荐系统,dfx7799@sina.com
  • 作者简介:张永安(1957-),男,陕西咸阳人,教授,博士生导师,主要研究方向:管理决策、管理信息系统。
  • 基金资助:

    河南省高等学校哲学社会科学创新团队支持计划项目(2014-CXTD-10)。

Abstract:

Focusing on user remarkable burden and high dimension of Multi-Criteria Collaborative Filtering (MC-CF) recommendation system, the recommendation system of Multi-Attribute Utility Collaborative Filtering (MAU-CF) was proposed. Firstly, attribute weight and attribute-value utility were extracted by user browsing behavior, and user's multi-attribute utility function was built to achieve implicit rating of items. Secondly, attribute-value collection according to user preference was constructed based on Genetic Algorithm (GA). Thirdly, the nearest neighborhood was looked for by attribute weight and attribute-value similarity of attribute-value collection. Finally, utilities of items which the nearest neighborhood had browed and bought would be predicted for user by similarity, and the high-utility items would be recommended to user. In the comparison experiments with MC-CF, the explicit utility was replaced by the implicit utility calculated by MAU-CF, calculation dimension decreased by 44.16%, time expense decreased by 27.36%, and Mean Absolute Error (MAE) decreased by 5.69%, and user satisfaction increased by 13.44%. The experimental results show MAU-CF recommendation system outperforms MC-CF recommendation system on user burden, calculation dimension, and recommendation quality.

Key words: recommendation system, multi-attribute utility, collaborative filtering, implicit rating, Genetic Algorithm (GA)

摘要:

针对基于多标准的协同过滤(MC-CF)推荐系统中用户负担重、超高维问题,提出了基于多属性效用的协同过滤(MAU-CF)推荐系统。首先,依据用户浏览行为挖掘属性权重和属性值效用,构造用户的多属性效用函数,获取用户对项目的隐式评分;其次,采用遗传算法(GA)寻找用户偏好的属性值集合;然后,根据属性值集合中属性权重和属性值效用的相似度,寻找最近邻;最后,根据相似度预测最近邻浏览或购买过的项目对目标用户的效用,向目标用户推荐效用大的项目。通过比较实验发现,相对于MC-CF,MAU-CF挖掘的隐式效用能够替代显式效用,计算维度减少了44.16%,时间消耗减少了27.36%,平均绝对误差(MAE)减少了5.69%,用户满意度提高了13.44%。实验结果表明,MAU-CF推荐系统在减少用户负担和计算维度、提高推荐质量方面比MC-CF推荐系统表现得更优越。

关键词: 推荐系统, 多属性效用, 协同过滤, 隐式评分, 遗传算法

CLC Number: