Proceedings of the 2018 4th Annual International Conference on Modern Education and Social Science (MESS 2018)

A Study on Academic Early-Warning System Based on Machine Learning

Authors
Zi-Jun BAI, Gang-Quan CAI
Corresponding Author
Zi-Jun BAI
Available Online April 2018.
DOI
https://doi.org/10.2991/mess-18.2018.47How to use a DOI?
Keywords
academic early-warning system, machine learning, informatization
Abstract
With the expansion of college enrollment, college students' academic problem increasingly prominent. Universities have established effective preventive mechanisms to solve the problems. The most representative measure is academic early-warning system. Take Xiamen University of Technology as an example, this paper tries to put forward the idea of improving the existing academic warning system, and builds up the mathematical model based on machine learning, focusing on the algorithm of the model and validating the model. Finally, discusses the current situation and challenge of colleges and universities. In this paper, the daily teaching management and information system are combined, and the effectiveness and feasibility of computer are used to provide valuable reference for education reform in universities.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
2018 4th Annual International Conference on Modern Education and Social Science (MESS 2018)
Part of series
Advances in Social Science, Education and Humanities Research
Publication Date
April 2018
ISBN
978-94-6252-526-9
ISSN
2352-5398
DOI
https://doi.org/10.2991/mess-18.2018.47How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Zi-Jun BAI
AU  - Gang-Quan CAI
PY  - 2018/04
DA  - 2018/04
TI  - A Study on Academic Early-Warning System Based on Machine Learning
BT  - 2018 4th Annual International Conference on Modern Education and Social Science (MESS 2018)
PB  - Atlantis Press
SN  - 2352-5398
UR  - https://doi.org/10.2991/mess-18.2018.47
DO  - https://doi.org/10.2991/mess-18.2018.47
ID  - BAI2018/04
ER  -