Rating Prediction Using Neural Networks

Abstract

The aim of this thesis is to design a model for the rating prediction using the frontal and forward neural networks. This thesis is divided into three main chapters. The rating is described in the first chapter. The concept of rating, the financial risk connected with the rating and information about the types of rating is described there. The second chapter is about the neural networks. The basic concept of neural networks is explained. The possibility of using neural networks for the prediction and general definitions of the frontal and feed-forward neural networks are also presented in this section. The model for the rating prediction is designed in the third and last chapter. There are also described the obtained data. The results of training and testing process of neural networks are described. The best model for rating prediction is introduced at the end.