Fuzzy Adaptive Network in Financial Credit Rating

摘要

Credit management is a basic problem for any financial institution. However, the uncertainty and vagueness inherent in the dynamics of the system due to the involvement of human behavior make the usual approach by using the rigorous mathematical models inappropriate. This paper presents a neuro-fuzzy soft computing approach to deal with this vague and generally not well-defined credit rating problem. The approach integrates the concept of fuzzy aggregation and fuzzy adaptive network to form a combined estimation and neural learning model. A numerical example is used to illustrate the approach.