Discriminating on Credit Risk Distortion of Enterprise based on HP Filter-neural Network Method
Guixian Wang · 2013
False information release usually leads to the credit risk distortion of an enterprise.How to restore the real credit default level and find a distortion calibration method are the research focus in the world.Integrating the multidimensional feature and time series characteristics of the false information,the paper designs a dimension reduction method for the information data based on Hodrick-Prescott(HP) filter.Furthermore,by introducing the double factors of enterprise itself and similar industry,for discriminating the credit risk distortion,the paper derives the neural network model of time series of multi-sample and multidimensional indexes.Finally,the paper gives an empirical experiment,in which the results show the validity of the model.