Application of Genetic Algorithm in Development of Bankruptcy Predication Theory Case Study: Companies Listed on Tehran Stock Exchange

Abstract

The bankruptcy prediction models have long been proposed<br />as a key subject in finance. The present study, therefore, makes an<br />effort to examine the corporate bankruptcy prediction through employment<br />of the genetic algorithm model. Furthermore, it attempts to evaluate<br />the strategies to overcome the drawbacks of ordinary methods for<br />bankruptcy prediction through application of genetic algorithms. The<br />sample under investigation in this research includes 70 pairs of bankrupt<br />and non-bankrupt companies during 2001-2011. Having examined the<br />obtained data from financial statements of the companies under study,<br />5 financial independent variables were identified so as to be used in the<br />model. The results indicated that employment of genetic algorithm in predicting financial bankruptcy is highly effective, to the extent it managed<br />to correctly predict the financial bankruptcy of companies two<br />years before the base year, one year before the base year and the base<br />year at accuracies of 96.44, 97.94 and 95.53, respectively.