Student Achievement Prediction Based on Factor Analysis and BP Neural Network

DOI

10.2991/icmmita-16.2016.186How to use a DOI?

Keywords

Student Achievement Prediction; Factor Analysis; BP Neural Network

Abstract

The study proposed in this paper analyses the problems existing in the college course score prediction methodologies. Because of diversity and multiple choices in course selection, the analysis of college students' course score can be quite complex. This paper proposes a student achievement prediction method based on factor analysis (FA) and Back-Propagation (BP) neural network. Our method is based on the improvement of FA algorithm. Firstly, special factors will be added to complement the equation of common factor score. Secondly, the initial equation of common factor score will be improved. Thirdly, a new equation intended to give an estimation of the special factors mentioned in the first point will be proposed. Finally, an improvement on the common factor loading matrix will be made. We use the improved equation of common factor score to calculate the score of each common factor. Then we use these scores as the input vector of the BP neural network. The output of the neural network is brought into the final equation to get the final prediction result. The experimental results show that the prediction accuracy is very high and the prediction model can be used for most of the college courses. The error on the prediction result is reduced by using the prediction model proposed in this paper. Therefore, the model developed in this paper is very effective and has high application value.

Copyright

© 2017, 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  - Hongchen Guo
AU  - Junsheng Liang
AU  - Zhiqiang Li
PY  - 2017/01
DA  - 2017/01
TI  - Student Achievement Prediction Based on Factor Analysis and BP Neural Network
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications
PB  - Atlantis Press
SP  - 1013
EP  - 1020
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmita-16.2016.186
DO  - 10.2991/icmmita-16.2016.186
ID  - Guo2017/01
ER  -