Research On Enterprise Credit Evaluation Model Based On Factor Analysis And Wavelet Network

At present, enterprise credit issue has encountered huge challenges, and it has already become the important barrier blocking social and economic development. The enterprise credit evaluation has thus been paid more and more attention.As one kind of nonlinear complex problem, the traditional analysis methods cannot solve it perfectly. In recent years, the wavelet network technology, an effective tool especially researching on complex question, has demonstrated its extraordinary superiority in pattern recognition and classification, prediction, automatic control aspect and etc. The factorial analysis is a method which analyzes many variables' intrinsic relationship in the statistic multivariate analysis area. In view of the shortcomings and the deficiencies existing in enterprise credit evaluation methods at present, this paper combines the unique characteristics of credit evaluation and establishes an enterprise credit evaluation model based on factor analysis and wavelet network.First, the paper studies the related literature of enterprise credit evaluation and the selecting ratings of credit evaluation method. Second, it uses statistical methods to carry on preliminary screening towards the collected data; then it carries on factor analysis, and inputs factor score into the wavelet network evaluation model. Finally, after determining the wavelet network structure, it establishes the wavelet network evaluation model using the MATLAB7.1 software and carries on a simulation testing towards the enterprise credit evaluation model. The study indicates that the credit evaluation model based on factor analysis and wavelet network is a model without linear mapping, high in correlation among indexes, changing non-line and that a relatively satisfying outcome can be gotten. So it's a relatively optimum method used for forecasting, with wide applying area and high value of popularizing.