Integrated methodology of artificial intelligent and analytic hierarchy process for corporate credit evaluation

Abstract

Credit evaluation is a significant area of financial management which is of major interest to practitioners, financial and credit analysts. The credit/financial analysts have to investigate an enormous volume of financial and non-financial data of firms, estimate the corresponding credit evaluation, and finally make crucial decisions regarding the financing of firms. Considerable attention has been devoted in this field from the theoretical and academic points of view during the last three decades. Financial and operational researchers have tried to relate the characteristics of a firm (financial ratios and strategic variables) to its credit evaluation. According to this relationship the components of credit evaluation are identified, and decision models are developed to assess credit evaluation and the corresponding creditworthiness of firms as accurately as possible. Although many studies demonstrate that one technique outperforms the others for a given data set, there is often no way to tell a priori which of these techniques will be most effective to solve a specific classification problem. Alternatively, it has been suggested that a better approach to classification problem might be to integrate various learning methodology. Intelligent combing of several good learning algorithms and their synergistic use may lead to improving predictive ability. The aim of this study is to propose intelligent hybrid, multiple strategy methodology. The credit analysis is a complex process involving multiple strategy approach. This study employs four strategies in the credit evaluation; feature weighting, data discretisation, development of hybrid methodology, and selection of variables using financial and non-financial criteria. The proposed methodologies are as followed: The first, this thesis adopts the AHP of Saaty to incorporate judgmental and quantitative assessments of credit evaluation factors that are considered important in the classification and measurement of cr...