BANKRUPTCY PREDICTION BY USING SUPPORT VECTOR MACHINES AND GENETIC ALGORITHMS

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.