Campus Economic Analysis Based on K-Means Clustering and Hotspot Mining

Xiuzhang Yang (Guizhou Vocational College of Economics and Business School of Information, Guizhou University of Finance and Economics)
Shuai Wu (School of Information, Guizhou University of Finance and Economics)
Huan Xia (School of Information, Guizhou University of Finance and Economics Key Laboratory of Economics System Simulation, Guizhou University of Finance and Economics)
Yuanbo Li (Guizhou Vocational College of Economics and Business)
Xin Li (Guizhou Vocational College of Economics and Business)


With the advent of the era of big data and the development and construction of smart campuses, the campus is gradually moving towards digitalization, networking and informationization. The campus card is an important part of the construction of a smart campus, and the massive data it generates can indirectly reflect the living conditions of students at school. In the face of the campus card, how to quickly and accurately obtain the information required by users from the massive data sets has become an urgent problem that needs to be solved. This paper proposes a data mining algorithm based on K-Means clustering and time series. It analyzes the consumption data of a college student’s card to deeply mine and analyze the daily life consumer behavior habits of students, and to make an accurate judgment on the specific life consumer behavior. The algorithm proposed in this paper provides a practical reference for the construction of smart campuses in universities, and has important theoretical and application values.


Machine learning; K-Means clustering; Data mining; Consumer behavior; Campus economy; Economic regionalization

Full Text:



Chen Feng. Analysis and data mining of dining consumption behavior of college users based on campus card system [J]. China Education Informationization, 2014, (09): 47-49.

Lu Sifeng, He Naiming. Analysis and guidance of college students' consumption behavior. Journal of Beijing Technology and Business University, 2003 (18): 62-65.

Xu Juan. Investigation and Analysis of Students' Consumption View in Higher Vocational Colleges [J] .Journal of Chongqing College of Electric Power, 2019,24 (01): 57-59.

Zhang Chunhua, Wen Lu. An Empirical Study of Online Game Consumption Behavior and Its Influencing Factors——Based on the Differential Analysis of College Students' Gender and Education [J] .Jiangsu Social Science, 2018 (06): 50-58.

Liu Shangjun, Liu Jun, Jiang Zhihui.Analysis of the Consumption Behavior of Liquid Milk among College Students——Based on a Survey of Students in Tarim University [J] .Journal of Tarim University, 2017,29 (03): 79-85.

Ren Jinhua. Study on the Law of Student Campus Consumption Based on Card Data [D] .Huazhong Normal University, 2018.

Liu Jian. Research on tumor gene expression profile data analysis method based on machine learning [D] .China University of Mining and Technology, 2018.

Li Jianwei, Su Zhanyu, Huang Yiru.Research on Risk Prediction of Online Learning Based on Big Data Learning Analysis [J] .Modern Educational Technology, 2018,28 (08): 78-84.

Ye Yu, Zhang Lingzhu, Yan Wentao, Zeng Wei.Humanistic perspective measurement framework for street greening quality: large-scale analysis based on Baidu streetscape data and machine learning [J] .Landscape Architecture, 2018,25 (08): 24- 29.

An Qiangqiang, Li Zhaoxing, Zhang Feng, Zhang Yaqiong. Unstructured big data analysis algorithm of communication network based on machine learning [J] .Electronic Design Engineering, 2018,26 (14): 53-56.

Qi Xuedan. Classification of Alzheimer's disease based on brain MRI and machine learning [D] .Shanxi Medical University, 2018.

Anil K. Jain. Data clustering: 50 years beyond K-means [J]. Pattern Recognition Letters, 2009,31 (8).

Wang Pengfei.Coupling Development of Beijing-Tianjin-Hebei Circulation Industry and Regional Economy: Theory and Empirical [J] .Commercial Economic Research, 2019 (09): 153-155.

Wu Shuai, Yang Xiuyi, Xia Huan, Tian Guijiang, Zhao Ziru, Liu Xifeng, Gao Tong. Maximum Likelihood Estimation Based on Normal Distribution [J]. South Agricultural Machinery, 2019, 50 (19): 20-21.

Wu Shuai, Xia Huan, Yang Xiuyi, Yu Xiaomin, Zhao Ziru, Dou Yueqi. Discussion on the protection of ancient buildings based on sentiment analysis of Notre Dame fire [J]. Information Technology and Information Technology, 2019 (08): 154-159.

[12]Wu Shuai, Xia Huan, Yang Xiuyi, Zhao Ziru, Dou Yueqi, Liu Xifeng. Analysis of O2O offline store crowdfunding expansion business model based on knowledge map [J]. Mall Modernization, 2019 (15): 9-10.



  • There are currently no refbacks.