Forecast of Student Achievement Variation Trend Based on C4.5 Decision Tree

DOI

10.2991/aiie-15.2015.105How to use a DOI?

Keywords

data mining; student achievement; C4.5 decision tree; prediction model

Abstract

In the work of educational management, student achievement is one of the most important evidences to evaluate the quality of a student. With respect to many factors that may affect student achievement, a new method based on C4.5 decision tree is proposed to predict student achievement variation trend. Firstly, reasonable attributes from student historical data of campus activities are selected. Secondly, the samples which have few records of campus activities are removed, and the attributes of remainder are discretized. Finally, a prediction model is established by C4.5 decision tree method to predict the variation trend of student achievement. The simulation results demonstrate that the prediction accuracy achieves 80.84%. As a result, the prediction model can effectively help educational management departments find the bad behavior of students and offer guidance to the students in time.

Copyright

© 2015, 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  - L. Li
AU  - S.M. Yao
AU  - Z. Ou
AU  - Q.J. Chen
PY  - 2015/07
DA  - 2015/07
TI  - Forecast of Student Achievement Variation Trend Based on C4.5 Decision Tree
BT  - Proceedings of the 2015 International Conference on Artificial Intelligence and Industrial Engineering
PB  - Atlantis Press
SP  - 383
EP  - 386
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-15.2015.105
DO  - 10.2991/aiie-15.2015.105
ID  - Li2015/07
ER  -