摘要
针对推荐系统中因新项目的加入而造成的冷启动问题,在矩阵分解模型的基础上提出了融合项目图片相似度和类别属性的协同过滤推荐模型USPTMF-CFIA。首先,采用基于用户偏好和时间权重的矩阵分解模型,对评分缺失项进行预测填充;然后,利用VGG16神经网络提取项目图片特征,并结合类别属性计算新项目与历史项目的相似度,得到近邻项目;最后,根据新项目与近邻项目之间的相似度预测用户对新项目的评分,将评分高的前N个项目推荐给对应用户;通过在GroupLens提供的数据集上的实验证明,该模型的推荐准确率比MAP-BPR模型高0.006~0.015,比传统协同过滤模型高0.02~0.028,比没融合图片相似度的USPTMF-CFA模型高0.001~0.003,比ACMF模型高0.001~0.002。
Aiming at the problem of cold start caused by the addition of new item in the recommendation system,this paper proposed a collaborative filtering recommendation model USPTMF-CFIA based on matrix factorization model,which combined the similarity of item image and category attributes .First,it used the matrix factorization model based on users’ preference and time weight to predict and fill the missing item.Then,it used the VGG16 neural network to extract the features of the item images and combined category attributes to calculate the similarity between the new item and the historical items,then got the item’s neighbors.Finally,it predicted the new item based on the similarity between the new item and the neighbors,and the first N items with high score were recommended to the correspond user.The experiment on the dataset provided by GroupLens proved that the proposed accuracy rate of this model.The recommended accuracy of this model is 0.006~0.015 higher than the MAP-BPR model ,0.02~0.028 higher than the traditional collaborative filtering model and 0.001~0.003 higher than that of the USPTMF-CFA model without image similarity 0.001~0.002 higher than ACMF model.
作者
周强
胡燕
Zhou Qiang;Hu Yan(College of Computer Science & Technology,Wuhan University of Technology,Wuhan 430070,China)
出处
《计算机应用研究》
CSCD
北大核心
2019年第8期2378-2382,共5页
Application Research of Computers
基金
湖北省自然科学基金重点类资助项目(2017CFA012)
关键词
协同过滤
矩阵分解
图片特征
新项目冷启动
时间权重
collaborative filtering
matrix factorization
image features
newitem cold-start
time weight
