Journal of Credit Risk

Risk.net

An effective credit rating method for corporate entities using machine learning

Hansheng Sun, Roy H. Kwon, Binbin Dai and Pubudu Premawardena

  • A new approach to design credit risk rating models for corporate entities is introduced. This approach allows a bank to make accurate and cost-effective rating decisions by maximizing risk adjusted return under model uncertainty.
  • We propose a meta-algorithm, which effectively utilizes ordinal information embedded in the expert assigned credit ratings to accurately rank the customers. Then, a cost-sensitive rating assignment method is used to reduce the impact of model uncertainty on the bank’s risk adjusted return.
  • We provide detailed discussions on specifying the cost matrix under the Basel Regulatory Framework. Empirical results on North American medium and large sized companies show strong performance of the proposed approach.

In this study we introduce a new approach to designing credit risk rating models for corporate entities. This approach allows a bank to make accurate and cost-effective rating decisions by maximizing risk-adjusted returns under model uncertainty. We propose a meta-algorithm, which exploits the ordinal information embedded in the expert-assigned credit ratings in order to accurately rank customers. Then, a costsensitive rating-assignment method is used to reduce the impact of model uncertainty on the bank’s risk-adjusted return. We provide detailed discussions on specifying the cost matrix under the Basel regulatory framework. Empirical results for North American large and medium-sized companies show strong performance from the proposed approach.

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 Risk.net? View our subscription options

If you already have an account, please sign in here.

You need to sign in to use this feature. If you don’t have a Risk.net 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: