Identifying companies' bankruptcy using an enhanced neural network model: a case study evaluating the bankruptcy of Iranian stock exchange companies

The purpose of this research is to utilise an enhanced neural network model to anticipate the bankruptcy of stock exchange companies and test the predictive power of this model by considering the concept of misclassification. Misclassifications decrease the accuracy of prediction. Among every one of the structures of the two-layer neural network, the perceptron model with the structure of nine neurons in the input layer and a neuron in the output layer with the Levenberg learning algorithm demonstrated the most predictive power. The neuron structures three, five, and nine were considered to decide the proper characteristics of a two-layer perceptron for anticipating companies' bankruptcy. Among them, the two-layer perceptron with nine neurons in the input layer and one neuron in the output layer identified to has the best performance. The findings demonstrate that applying artificial neural network models amplify financial management for facing with fluctuations and bankruptcy.