Analysis of Excess Consumption in College Students by KPAG Method During the COVID-19 Pandemic

Xia Jiang¹ & Bin Zhao^2*

¹Hubei University of Technology, Hospital, University in Wuhan, P.R. China
²School of Science, Hubei University of Technology, University in Wuhan, P.R. China

Dr. Bin Zhao, School of Science, Hubei University of Technology, University in Wuhan, P.R. China.

Keywords: Data Science in Education; Consumption Risk; KPAG Algorithm; Early-Warning Model

Abstract

With the arrival of COVID-19, some areas are under closed management, bringing about changes in the way people consume. It also leads to the excessive consumption of some people, especially college students. In order to give early warning to unreasonable consumption behavior, this study designed KPAG algorithm to give early warning to consumption risk. Using particle swarm optimization (PSO) kernel principal component analysis (KPCA) parameter optimization, optimal polynomial kernel to delete data information, and ant colony genetic algorithm (association) clustering analysis of data dimensionality reduction, according to the consumption behavior of college students are divided into three categories, for the consumption behavior of college students to build an early warning model. Through the classification and verification experiment of real data, the results show that compared with the traditional PCA data fitting method, the accuracy of the model in this paper can reach 90%, which is more reliable than the traditional algorithm, and the accuracy of the model is improved by nearly 20%, which can be used for effective early warning.

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).