• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 高性能计算 • 上一篇    下一篇

基于标签自适应选择的矩阵分解推荐算法

宋威1,2,李雪松1   

  1. (1.北方工业大学计算机学院,北京 100144;2.大规模流数据集成与分析技术北京市重点实验室,北京 100144)
  • 收稿日期:2018-05-11 修回日期:2018-07-18 出版日期:2018-10-25 发布日期:2018-10-25
  • 基金资助:

    北京市自然科学基金(4162022);北京市科技计划项目(D161100005216002);北京市优秀人才青年拔尖个人项目(2015000026833ZK04)

A matrix factorization recommendation algorithm
based on adaptive tag selection

SONG Wei1,2,LI Xuesong1   

  1. (1.College of Computer Science and Technology,North China University of Technology,Beijing 100144;
    2.Beijing Key Laboratory on Integration and Analysis of LargeScale Stream Data,Beijing 100144,China)
     
  • Received:2018-05-11 Revised:2018-07-18 Online:2018-10-25 Published:2018-10-25

摘要:

将标签融入矩阵分解方法是当前推荐系统研究的热点。提出了一种基于标签自适应选择的矩阵分解推荐算法。首先,提出了标签评分稀疏系数,较好地平衡了推荐过程中潜在特征与标签的使用问题。其次,利用标签的次数来计算标签向量,体现了标签的不同频率对不同物品的影响。最后,给出了算法的总体描述。实验结果表明,算法具有较高的推荐精度和较快的收敛速度。

关键词: 推荐系统, 矩阵分解, 隐语义模型, 标签自适应选择, 标签评分稀疏系数

Abstract:

Incorporating tags into matrix factorization is a hot topic in the field of recommender system. Based on adaptive tag selection, we propose a new matrix factorization recommendation algorithm. Firstly, we put forward a tagrating sparsity factor, which balances the usage of latent factors and tags in recommendation. Secondly, tag vectors are computed by the number of tags, which reflects the influence of different frequencies of tags on different items. Finally, the overall description of the proposed algorithm is illustrated. Experimental results show that the proposed algorithm has high recommedation accuracy and high convergence speed.
 

Key words: recommendation system, matrix factorization, latent factor model, adaptive tag selection, tag-rating sparsity coefficient