计算机工程 ›› 2018, Vol. 44 ›› Issue (6): 13-17,23.doi: 10.19678/j.issn.1000-3428.0047313

• 先进计算与数据处理 • 上一篇    下一篇

基于项目评分与类型评分聚类的推荐算法

段元波,高茂庭   

  1. 上海海事大学 信息工程学院,上海 201306
  • 收稿日期:2017-05-22 出版日期:2018-06-15 发布日期:2018-06-15
  • 作者简介:段元波(1993—),男,硕士研究生,主研方向为数据挖掘;高茂庭,教授、博士。
  • 基金项目:

    国家自然科学基金(61202022)。

Recommendation Algorithm Based on Clusterings of Item Rating and Type Rating

DUAN Yuanbo,GAO Maoting   

  1. College of Information Engineering,Shanghai Maritime University,Shanghai 201306,China
  • Received:2017-05-22 Online:2018-06-15 Published:2018-06-15

摘要:

针对用户聚类时部分近邻被遗漏和近邻用户选取依据单一的问题,通过对项目评分和类型评分进行聚类,提出一种新的推荐算法。结合用户对项目的评分记录生成用户-项目评分矩阵和用户-项目类型评分矩阵,基于此对用户进行模糊C均值聚类,同时改进距离度量方法,根据聚类生成的隶属度矩阵在隶属度高的簇中选取对应最近邻,并通过加权生成预测评分,最终产生推荐。在MovieLens数据集上的对比结果表明,该算法能够真实地反映用户评分,有效提高推荐系统的预测准确性。

关键词: 协同过滤, 模糊C均值聚类, 隶属度, 推荐算法, 项目评分, 类型评分

Abstract:

To solve the problems that some similar users will be missed and the basis for selecting nearest neighbors is single while user clustering,a recommendation algorithm based on clusterings of item rating and type rating is proposed.The user-item rating matrix and the user-item type rating matrix according to user’s rating records are firstly generated.The fuzzy C-means clustering is carried out by using the above two matrices and the improved the distance measurement method.Then,the nearest neighbor is selected according to the membership degree matrix generated by the clustering.Finally,the prediction rating is generated by the parameter weighting.Experimental results on MovieLens dataset show that the proposed algorithm can reflect the user’s rating accurately and improve the accuracy of the recommendation system effectively.

Key words: collaborative filtering, fuzzy C-means clustering, membership degree, recommendation algorithm, item rating, type rating

中图分类号: