Evaluation of the hybrid method of genetic algorithm and adaptive neural-fuzzy network (ANFIS) model in predicting the bankruptcy of companies listed on the Tehran stock exchange

Abstract

One of the most important issues in financial, economic, and accounting matters is the phenomenon of bankruptcy and its prediction. There is presented a hybrid method of genetic algorithm and adaptive neural-fuzzy network model (ANFIS) to evaluate predicting the bankruptcy of companies listed on the Tehran Stock Exchange. The statistical population of this research is the successful and bankrupt manufacturing companies in Tehran Stock Exchange and in this research, there is a different way as opposed to previous and purposeful research and all companies can prevent their possible bankruptcy with accurate forecasting. In this way, the statistical population includes 136 companies consisting of bankrupt and non-bankrupt companies. In order to construct prediction models, four variables were first selected: 1. Independent sample t-test, 2. Correlation matrix (CM), 3. Step-by-step diagnostic analysis (SDA) and 4. Principal component analysis (PCA). The final financial ratios were selected from 19 financial ratios that using selected financial ratios and a hybrid model of ANFIS and genetic algorithm and the results of the proposed model and its comparison with the hybrid model of genetic algorithm and group method of data handling shows the high capability of the proposed GA-ANFIS model in bankruptcy prediction modeling and its superiority over GA-GMDH method. The results also show that the CM-GA-ANFIS model is known as the best model for predicting bankruptcy of companies listed on the Tehran Stock Exchange. The main reason for choosing the model (GA-ANFIS) is that in addition to the fact that for the first time a combination of two methods ANFIS and genetic algorithm is used to predict the bankruptcy of companies, and also in none of the studies conducted in both areas which further highlights the need for the present study.