An integrated data mining model for customer credit evaluation

Abstract

Based on the customer information relating to details of financing and payment histories from a financial institution, this study derived single data mining models using MLP, MDA, and DTM. The results obtained from these single models were subsequently compared with the results from an integrated model developed using GA. This study not only verifies existing single models and but also attempts to overcome the limitations of these approaches. While our comparative analysis of single models for the purpose of identifying the best-fit model relies upon existing techniques, this study presents a new methodology to build an integrated data mining model using GA. © Springer-Verlag Berlin Heidelberg 2005.