Bennell, J.A., Crabbe, D., Thomas, S. and Gwilym, O.A. (2005) Modelling Sovereign Credit Ratings: Neural Networks versus Ordered Probit. Expert System with Applications, 30, 415-425.
https://doi.org/10.1016/j.eswa.2005.10.002

has been cited by the following article:

• TITLE: The Development of an Alternative Method for the Sovereign Credit Rating System Based on Adaptive Neuro-Fuzzy Inference System

  AUTHORS: Hakan Pabuçcu, Tuba Yakıcı Ayan

  KEYWORDS: Credit Rating, Logistic Regression (LR), Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), Comparative Studies

  JOURNAL NAME: American Journal of Operations Research, Vol.7 No.1, January 11, 2017

  ABSTRACT: The main purpose of this article is to determine the factors affecting credit rating and to develop the credit rating system based on statistical methods, fuzzy logic and artificial neural network. Variables used in this study were determined by the literature review and then the number of them was reduced by using stepwise regression analysis. Resulting variables were used as independent variables in the logistic model and as input variables for ANN and ANFIS model. After evaluating the models and comparing with each other, the ANFIS model was chosen as the best model to forecast credit rating. Rating determination was made for the countries that haven’t had a credit rating. Consequently, the ANFIS model made consistent, reliable and successful rating forecasts for the countries.