Trained Radial Neural Networks Based on Variables of Statistical Models and Their Comparison in Bankruptcy Prediction

Nowadays artificial neural networks have found a special position among these methods. this study seeks to find a better method of building and training artificial neural networks which leads to more accurate predictions of bankruptcy. Meanwhile, three neural networks of radial basis function type were built and trained separately by Altman model (1983), Zmijewski model (1984) and combinatory models’ variables. After evaluating the ability of these three models of bankruptcy prediction, their accuracy has been compared. Generally, this study is based on these hypotheses: First, artificial neural network models can predict bankruptcy using Altman, Zmijewski, and combinatory variables. Second, Type I and Type II error rates are equal in the aforementioned artificial neural network models. Time span of 2004 to 2012 (eight years) has been used to select samples from the listed companies in Tehran Stock Exchange. Results show that all three models have the ability of predicting bankruptcy and the model trained with Altman Model’s variables is more accurate than the other two models in this regard.