Proceedings of the 2015 International Conference on Social Science and Technology Education

Research of the enterprise financial risk based on support vector machine

Authors
Lin Yan
Corresponding Author
Lin Yan
Available Online April 2015.
DOI
10.2991/icsste-15.2015.231How to use a DOI?
Keywords
Support vector machine; Financial crisis; Warning model
Abstract

For comparing the prediction accuracy of company financial crisis prediction models, the support vector machine model was introduced in this paper to predict that whether there exists financial crisis in a company or not. Through the acquisition of a large number of samples for training and testing, the specific example’s results demonstrate that the financial crisis warning model based on support vector machine can effectively predict the financial crisis. The forecast accuracy of the training samples and testing sample respectively are 94.5% and 93.9%, which is better than the neural network model.

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)

Volume Title
Proceedings of the 2015 International Conference on Social Science and Technology Education
Series
Advances in Social Science, Education and Humanities Research
Publication Date
April 2015
ISBN
10.2991/icsste-15.2015.231
ISSN
2352-5398
DOI
10.2991/icsste-15.2015.231How to use a DOI?
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/).

Cite this article

TY  - CONF
AU  - Lin Yan
PY  - 2015/04
DA  - 2015/04
TI  - Research of the enterprise financial risk based on support vector machine
BT  - Proceedings of the 2015 International Conference on Social Science and Technology Education
PB  - Atlantis Press
SP  - 918
EP  - 921
SN  - 2352-5398
UR  - https://doi.org/10.2991/icsste-15.2015.231
DO  - 10.2991/icsste-15.2015.231
ID  - Yan2015/04
ER  -