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

The bankruptcy prediction models have long been proposedas a key subject in finance. The present study, therefore, makes aneffort to examine the corporate bankruptcy prediction through employmentof the genetic algorithm model. Furthermore, it attempts to evaluatethe strategies to overcome the drawbacks of ordinary methods forbankruptcy prediction through application of genetic algorithms. Thesample under investigation in this research includes 70 pairs of bankruptand non-bankrupt companies during 2001-2011. Having examined theobtained data from financial statements of the companies under study,5 financial independent variables were identified so as to be used in themodel. The results indicated that employment of genetic algorithm in predicting financial bankruptcy is highly effective, to the extent it managedto correctly predict the financial bankruptcy of companies twoyears before the base year, one year before the base year and the baseyear at accuracies of 96.44, 97.94 and 95.53, respectively.