Journal of Credit Risk

Modeling corporate customers’ credit risk considering the ensemble approaches in multiclass classification: evidence from Iranian corporate credits

Parastoo Rafiee Vahid and Abbas Ahmadi

  • Recommends a flexible model to provide banks with a tool to grant credit to a broader range of applicants.
  • Decrease credit risk by predicting solvency and insolvency rates of the bank corporate customers.
  • Propose a novel ensemble approach for a multiclass classification problem.
  • Classify bank corporate customers into four groups.


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.

Sorry, our subscription options are not loading right now

Please try again later. Get in touch with our customer services team if this issue persists.

New to View our subscription options

You need to sign in to use this feature. If you don’t have a account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here