The credit scoring system is one of the most significant credit risk control tools in the banking industry. Usually, the existing credit scoring models classify customers into "good credit" and "bad credit" groups. In this study, a novel model is proposed to classify corporate client accounts into four groups - good credit, past due, overdue and doubtful - according to the definitions of the Central Bank of the Islamic Republic of Iran. This model enables lenders to develop specific policies for credit granting by predicting the solvency and insolvency rates of their corporate clients. For validation, the proposed model, trained by the hybrid approach of a self-organizing map and radial basis function (RBF) neural network, is compared with a single-step, four-class classification model and a model trained by support vector machines. The results show that the proposed model trained by the hybrid approach of a self-organizing map and RBF neural network outperforms the existing methods in terms of its final accuracy with regard to the four classes at the test stage.