计算机应用 ›› 2016, Vol. 36 ›› Issue (4): 1050-1053.DOI: 10.11772/j.issn.1001-9081.2016.04.1050

• 人工智能 • 上一篇    下一篇

基于评分差异度和用户偏好的协同过滤算法

党博, 姜久雷   

  1. 北方民族大学 计算机科学与工程学院, 银川 750021
  • 收稿日期:2015-09-07 修回日期:2015-11-18 出版日期:2016-04-10 发布日期:2016-04-08
  • 通讯作者: 姜久雷
  • 作者简介:党博(1989-),男,山西临汾人,硕士研究生,主要研究方向:推荐算法、信息系统、软件工程; 姜久雷(1972-),男,山东嘉祥人,教授,博士,主要研究方向:服务计算、业务流程建模、软件工程。
  • 基金资助:
    国家自然科学基金资助项目(61462001);北方民族大学NSFC前期培育项目(2012QZP02)。

Collaborative filtering recommendation algorithm based on score difference level and user preference

DANG Bo, JIANG Jiulei   

  1. School of Computer Science and Engineering, Beifang University of Nationalities, Yinchuan Ningxia 750021, China
  • Received:2015-09-07 Revised:2015-11-18 Online:2016-04-10 Published:2016-04-08
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61462001), the NSFC Pre-cultivation Project of Beifang University of Nationality (2012QZP02).

摘要: 针对传统协同过滤推荐算法仅通过使用用户评分数据计算用户相似度以至于推荐精度不高的问题,提出一种改进的协同过滤推荐算法。首先,以用户评分的平均值作为分界点得出用户间的评分差异度,并将其作为权重因子计算基于评分的用户相似度;其次,依据用户项目评分和项目类别信息挖掘用户对项目类别的兴趣度以及用户项目偏好,并以此计算用户偏好相似度;然后,结合上述两种相似度加权产生用户综合相似度;最后,融合传统项目相似度和用户综合相似度进行评分预测及项目推荐。实验结果表明,相对于传统的基于用户评分的协同过滤推荐算法,所提算法在数据集下的平均绝对误差值平均降低了2.4%。该算法可在一定程度上提高推荐算法精度以及推荐质量。

关键词: 协同过滤, 评分差异度, 类别兴趣度, 用户相似度

Abstract: To address the problem that the traditional collaborative filtering algorithms only use user's rating data to compute the user similarity, which leads to a poor recommendation precision, an improved collaborative filtering recommendation algorithm was put forward. Firstly, the user's score difference level was obtained by using user's average score as the boundary point, which was considered as a weighting factor in the user's similarity. Secondly, according to the user's rating data and the item category information, the user's interest level for the item category and the users item preference were mined to calculate the user's preference similarity. Thirdly, the above two similarities were combined to get the intergrated similarity between users. Finally, the traditional item similarity and the intergrated similarity between users were fusioned to predict score and recommend items. The experimental results show that, compared with the traditional user-based collaborative filtering recommendation algorithm, the Mean Absolute Error (MAE) of the proposed algorithm is reduced by 2.4% on average. The new algorithm can effectively improve the accuracy and quality of the recommendation algorithm.

Key words: collaborative filtering, score difference level, category interest level, user similarity

中图分类号: