摘要
用户网购偏好发现是用户挖掘、电商营销以及用户个性化推荐的关键,该文基于校园网流量,提出了一种基于Map Reduce的校园网用户网购偏好分析方法,结合深度包检测(Deep Packet Inspection,DPI)与网络爬虫等技术,对校园网用户网购行为进行了特征提取和识别.以淘宝、天猫、京东三家电商网站为例,对电商网站用户转化率进行了统计分析,并分别对三个节假日校园网用户网购偏好进行了细致的分析.
A method for online shopping preference analysis based on MapReduce is proposed in this paper. The campus network traffic is analysed using MapReduce model, in which the features of users online shopping behavior is extracted by four MapReduce jobs combined with deep packet inspection （DPI）. Making use of those features occuring in different E-commercial websites and with the help of the product information database established by a web crawler, user online shopping conversion rates of E-commercial websites and category of purchased product are analysed and preference analysis results are presented.
出处
《计算机系统应用》
2015年第10期222-226,共5页
Computer Systems & Applications
基金
重庆市应用开发计划(cstc2013yykf A40006)
2013重庆高校创新团队建设计划(KJTD201312)
