Research on Prediction of College Students’ Performance Based on Support Vector Machine

DOI

10.2991/assehr.k.200727.021How to use a DOI?

Keywords

Support vector machine, college entrance examination results, professional course results, prediction, cross validation

Abstract

Using college entrance examination results to make accurate predictions of university course results can help students determine their efforts and help colleges and universities take effective measures to improve teaching quality. Based on the 2016 undergraduate college entrance examination results and university course scores of a general undergraduate college in China, a support vector machine was used to establish a college course performance prediction model, and cross-validation methods were used to obtain the best parameters and a reliable and stable model. Finally, in 2017 the model was applied to the college of computer science and technology major and communication engineering major performance forecast, the prediction accuracy rate reached 73.6%. The prediction results show that the support vector machine can accurately predict college course performance based on the college entrance examination results.

Copyright

© 2020, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Peng Wang
AU  - Yinshan Jia
PY  - 2020
DA  - 2020/07/28
TI  - Research on Prediction of College Students’ Performance Based on Support Vector Machine
BT  - Proceedings of the 2020 International Conference on Advanced Education, Management and Information Technology (AEMIT 2020)
PB  - Atlantis Press
SP  - 92
EP  - 95
SN  - 2352-5398
UR  - https://doi.org/10.2991/assehr.k.200727.021
DO  - 10.2991/assehr.k.200727.021
ID  - Wang2020
ER  -