The corporate credit rating represents an assessment of the relative level of risk associated with the timely payments required by the debt obligation. It plays a more and more important role as with the rapid progress of capital market encouraged by the liberalization of interest rate and globalization. Therefore it becomes essential that the scientific credit rating model should be developed in order to improve the accuracy and objectiveness of credit rating. From the previous research, various statistical methods, such as Multivariate Discriminant Analysis(MDA), Regression Analysis, Logit, and Probit, have been applied in traditional ways. Since late 1980's, the artificial intelligent methods such as inductive learning algorithm and Neural Networks(NN) have gained popularity on corporate credit rating.
In this study, the corporate credit rating model employed AI methods including NN and Case-Based Reasoning(CBR). At first, we suggested three classification models, as partitioned neural networks, all of which convert multi-group classification problems into two group classification ones: Ordinal Pairwise Partitioning(OPP) model used in the previous study, and binary classification model and simple classification model newly suggested in this study. The experimental results showed that the partitioned NN outperformed the conventional NN.
In addition, we put to use CBR that is widely used recently as a problem-solving and learning tool both in academic and business areas. With an advantage of the easiness in model design compared to a NN model, the CBR model proved itself to have good classification capability through the highest hit ratio in the corporate credit rating.