Prediction Model of English Major Enrollment in Jiangsu University of Science and Technology
Download as PDF
DOI: 10.23977/ICEMBE2022.024
Author(s)
Xia Zhang, Jing Zhang
Corresponding Author
Xia Zhang
ABSTRACT
Enrollment is an important way to improve the quality of college students. COVID-19 has brought great challenges to college enrollment. This article uses the enrollment data of the School of Foreign Languages of Jiangsu University of Science and Technology as reference data. Support vector regression (SVR) is used to comprehensively analyze the previous enrollment data, and the computer data modeling method is used to predict the future enrollment situation. Since the parameter setting of support vector regression (SVR) directly affects the modeling effect, particle swarm optimization algorithm (PSO) is used to optimize the parameters c (penalty factor) and g (radial basis kernel parameter) of SVR, and the optimized model is used to predict the enrollment of students and compared with the SVR model. The experimental results show that both SVR and PSO-SVR are suitable for enrollment prediction, and PSO-SVR has a higher prediction accuracy, which provides an effective basis for admissions office to make future enrollment plan.
KEYWORDS
English major, enrollment, data modeling