Research of Enterprise Credit Rating Based on K-Means GMDH Model

Abstract

Since the outbreak of credit risk, researching on corporate credit rating has been brought into investors, the government and scholars focus. This paper constructs an optimal K-means clustering Group Method of Data Handling model can effectively improve the accuracy of rating results, reduce the computational complexity, and this paper proves the model under the least squares estimation can get the optimal results. This article uses Chinese corporate credit rating and financial indexes to study, comparing its results with the concequences of Hidden Markov GMDH model and other traditional neural network models. The empirical outcomes show that the K-means clustering GMDH model is better than Hidden Markov GMDH model and the remaining four neural network models, indicating that the method can effectively improve the accuracy of corporate credit rating assessment and reduce the cost of rating.