A comparison of artificial neural network model and logistics regression in prediction of companies’ bankruptcy (A case study of Tehran stock exchange)

This paper aims to focus on the comparison of the artificial neural network model and logistic regression model in the prediction of companies’ bankruptcy in Tehran stock exchange (TSE) in 3,2 and 1 year in advance. This study exercises an analytic-mathematical approach which has been utilized three-layer artificial neural network tools, which includes one hidden layer and one output neuron and logistic regression (LR) with seven independent variable and one dependent variable for testing research’s hypotheses. Although the given results illustrates the high potential capacities of both models in the prediction of bankruptcies in an interval of three years, two years and one year before bankruptcy, capacity of neural network model showed the relative higher capability than LR model. This study takes into consideration the comparison of two popular tools of artificial neural networks (ANNs) and LR in bankruptcy prediction that are of importance in their own type.