BANKRUPTCY PREDICTION BY USING SUPPORT VECTOR MACHINES AND GENETIC ALGORITHMS

Salehi Mahdi and Rostami Neda
Additional contact information
Salehi Mahdi: Ferdowsi University of Mashhad, Iran
Rostami Neda: Islamic Azad University Science and Research Khorasan-e-Razavi Brancha

Studies in Business and Economics, 2013, vol. 8, issue 1, 104-114

Abstract: The original purpose of this study is comparing of Support Vector Machine and Genetic Algorithm and impact of financial ratios on accuracy of bankruptcy prediction. In according to some limitations in traditional statistical models, we used two models of Support Vector Machine and Genetic Algorithm. One of findings in this research is impact of financial ratios on accuracy of bankruptcy predicting and it shows that improper selection of financial ratios do not have high resolutions. Besides, they can decreases accuracy of prediction and may wrong introduce results of the research. Moreover, Support Vector Machine was more powerful than Genetic Algorithm in year’s t. However, it cannot be introduced which of them is better. Identifying of the most effective financial ratios as predictor variables and create a more powerful models, which can improve accuracy of prediction and reduce bankruptcy risk and its heavy cost will be decreased. This research focuses on identifying the most effective ¬financial ratios and the most powerful model for predicting of ¬bankruptcy.

Keywords: Bankruptcy predicting; Support Vector Machine; Genetic Algorithm; financial ratios (search for similar items in EconPapers)
Date: 2013
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://eccsf.ulbsibiu.ro/RePEc/blg/journl/8111salehi&rostami.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:blg:journl:v:8:y:2013:i:1:p:104-114

Access Statistics for this article

More articles in Studies in Business and Economics from Lucian Blaga University of Sibiu, Faculty of Economic Sciences Lucian Blaga University of Sibiu, Faculty of Economic Sciences Dumbravii Avenue, No 17, postal code 550324, Sibiu, Romania. Contact information at EDIRC.
Bibliographic data for series maintained by Mihaela Herciu ().