Title: Prediction of university students' academic level based on linear regression model
Authors: Chao Dong; Yan Guo
Addresses: Academic Affairs Office, Ningbo University of Finance and Economics, Ningbo 315175, China ' Ningbo Institute of Technology, Zhejiang University, Ningbo 315100, China
Abstract: Aiming at the problems of the prediction results by using the existing methods for university students' academic level prediction, such as large error and long time-consuming prediction, this paper proposes a method based on linear regression model to predict the academic level of university students. In order to improve the accuracy and real-time of prediction, Firstly, the students' academic related information is denoised, and then the denoised academic level information is classified. Finally, the linear regression model is used to predict the academic level of university students. The experimental results show that compared with other methods, the prediction error rate of the proposed method varies from 1% to 8%, and the prediction accuracy rate is higher. The predicted duration of the students academic level is in the range of 1 minute to 5 minutes, and the prediction speed is faster.
Keywords: academic level; prediction; linear regression.
DOI: 10.1504/IJCEELL.2020.106341
International Journal of Continuing Engineering Education and Life-Long Learning, 2020 Vol.30 No.2, pp.204 - 218
Received: 29 Mar 2019
Accepted: 03 Jun 2019
Published online: 02 Apr 2020 *