龚黎旰,顾 坤,明心铭,等.基于校园一卡通大数据的高校学生消费行为分析[J].深圳大学学报理工版,2020,37(增刊1):150-154.[doi:10.3724/SP.J.1249.2020.99150]
GONG Ligan,GU Kun,MING Xinming,et al.Analysis of college students' consumption behavior based on campus card data[J].Journal of Shenzhen University Science and Engineering,2020,37(Suppl.1):150-154.[doi:10.3724/SP.J.1249.2020.99150]
点击复制
基于校园一卡通大数据的高校学生消费行为分析
龚黎旰1,顾 坤2,明心铭3,徐 明1,秦 斌1

1)深圳大学信息中心,广东深圳 518060; 2)深圳大学电子与信息工程学院,广东深圳 518060; 3)深圳大学机电与控制工程学院,广东深圳 518060

计算机应用; 校园一卡通; 消费行为分析; 教育大数据; 教育数据挖掘; Spark

Analysis of college students' consumption behavior based on campus card data
GONG Ligan1, GU Kun2, MING Xinming3, XU Ming1, and QIN Bin1

1)Information Center, Shenzhen University, Shenzhen 518060, Guangdong Province, P.R.China2)College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, Guangdong Province, P.R.China3)College of Mechatronics and Control Enginee

computer application; campus card; consumer behavior analysis; educational big data; educational data mining; Spark

DOI: 10.3724/SP.J.1249.2020.99150

备注

为进一步提升高校的智慧管理水平,以某高校校园一卡通消费记录为数据基础,利用大数据和数据挖掘技术对其展开分析研究,挖掘学生消费行为背后的隐藏信息.通过对提取数据进行预处理和特征工程,统计分析学生的消费水平和消费习惯; 采用聚类算法圈选出具有不同消费行为的学生群体,深度分析不同群体的消费组成结构和消费行为特征; 通过构建学生共现网络,研究学生社交关系并发现学生群体中的孤独者.结果表明,利用聚类算法辅助学校资助部门开展精准助学工作是可行的,构建学生共现网络也为高校心理辅导工作提供一定参考依据.

In order to further improve the intelligent management level of universities, we use big data and data mining technology to analyze the data including a university's campus card consumption records. Firstly, through the preprocessing and feature engineering of the extracted data, we analyze students' consumption level, consumption habits and other laws. Then, we cluster students into different groups with different consumption behaviors, and analyze the consumption structure and consumption behavior characteristics for the different groups in depth. Finally, by constructing a student co-occurrence network, we study the social relationships of students and find the lonely persons. The experimental results show that our clustering algorithm can assist the accurate student aid work, and the construction of the student co-occurrence network can also provide a certain reference for the psychological counseling work.

·