计算机应用 ›› 2018, Vol. 38 ›› Issue (7): 1877-1881.DOI: 10.11772/j.issn.1001-9081.2017123066

• 人工智能 • 上一篇    下一篇

结合物品流行度的列表级矩阵因子分解算法

周瑞环, 赵宏宇   

  1. 西南交通大学 信息科学与技术学院, 成都 611756
  • 收稿日期:2018-01-02 修回日期:2018-03-01 出版日期:2018-07-10 发布日期:2018-07-12
  • 通讯作者: 周瑞环
  • 作者简介:周瑞环(1993-),男,浙江温州人,硕士研究生,主要研究方向:个性化推荐算法、机器学习;赵宏宇(1971-),男,重庆人,副教授,博士,主要研究方向:模式识别、人工智能、信息理论与编码。

List-wise matrix factorization algorithm with combination of item popularity

ZHOU Ruihuan, ZHAO Hongyu   

  1. School of Information Science and Technology, Southwest Jiaotong University, Chengdu Sichuan 611756, China
  • Received:2018-01-02 Revised:2018-03-01 Online:2018-07-10 Published:2018-07-12

摘要: 针对变形的奇异值分解(SVD++)算法的评分规则在模型训练和预测两个阶段的不一致问题和列表级矩阵因子分解(ListRank-MF)算法的Top-1排序概率在大量物品评分一样时排序概率一样的问题,提出一种结合物品流行度的列表级矩阵因子分解算法。首先,在评分规则中使用到的用户有过行为的物品集合中去除当前待评分物品;接着结合物品流行度改进Top-1排序概率;然后使用随机梯度下降算法求解目标函数并进行Top-N推荐。基于修正的SVD++评分规则,在MovieLens和Netflix数据集上比较了所提算法与目标函数为点级和列表级的SVD++算法。所提算法与列表级的SVD++算法相比,Top-N推荐准确率指标归一化折损累积增益(NDCG)值在MovieLens数据集上提高了5%~8%,在Netflix数据集上提高了1%左右。实验结果表明,所提算法能够有效提高Top-N推荐准确率。

关键词: 矩阵因子分解, Top-N推荐, 变形的奇异值分解(SVD++)算法, 物品流行度, 随机梯度下降

Abstract: For the difference of transmutative Singular Value Decomposition (SVD++) algorithm's rating rule in two stages of model training and prediction, and the same probability of List-wise Matrix Factorization (ListRank-MF) algorithm's Top-1 ranking probability caused by a large number of same rating items, an algorithm of list-wise matrix factorization combining with item popularity was proposed. Firstly, the current item to be rated was removed from the set of items that the user had used in the rating rule. Secondly, the item popularity was used to improve the Top-1 ranking probability. Then the stochastic gradient descent algorithm was used to solve the objective function and make Top-N recommendation. Based on the modified SVD++ rating rule, the proposed algorithm and the SVD++ algorithms whose objective functions are point-wise and list-wise were compared on MovieLens and Netflix datasets. Compared with the list-wise SVD++ algorithm, the value of Normalized Discounted Cumulative Gain (NDCG) of Top-N recommendation accuracy was increased by 5%-8% on MovieLens datasets and about 1% on Netflix datasets. The experimental results show that the proposed algorithm can effectively improve the Top-N recommendation accuracy.

Key words: matrix factorization, Top-N recommendation, transmutative Singular Value Decomposition (SVD++) algorithm, item popularity, stochastic gradient descent

中图分类号: