基于用户属性的协同滤波混合推荐系统研究  

A Hybrid Recommender Based on User Attribute Collaborative Filtering

作　　者：廖晓雅 刘传才[1] 徐晓峰[1] 彭甫镕[1] LIAO Xiaoya;LIU Chuancai;XU Xiaofeng;PENG Furong(Nanjing Unversity of Science and Technology,Nanjing 210094)

机构地区：[1]南京理工大学

出　　处：《计算机与数字工程》2019年第6期1377-1381,1431,共6页Computer & Digital Engineering

摘　　要：协同滤波(Collaborative Filtering,CF)是推荐系统(Recommender System,RS)中最广泛使用的方法之一。而基于用户属性信息的协同滤波方法常用来解决用户冷启动问题。论文中提出了一种混合方法,将基于用户属性信息的协同滤波与传统协同滤波的结果均匀混合为最终的结果。实验表明,混合系统与传统方法相比较,性能得到了明显的提升,且较为稳定。Collaborative Filtering(CF)is widely used in recommender system. The collaborative filtering method based on user attribute information is often used to solve the problem of user cold start. In this paper,a hybrid method is proposed,which combines the user attribute information with the traditional way. The experimental results show that the performance of the hybrid system is significantly improved and stable compared with the traditional method.

关 键 词：协同滤波 用户属性 混合推荐 

分 类 号：N941.5[自然科学总论—系统科学]