Early Detection of Defaulting Firms : Artificial Neural Network Application; Australian Context

There is no doubt that after BASL III framework is effective in Banking system in January 2013, many Australian Depository Institutions to which the framework will be applicable, require much more sophisticated risk management tools and systems to meet the APRA requirements in terms of having sound lending practices and to some extent less risky approach to grant loans, especially for corporate borrowers. The predominant presence of uncertainty in this context same as the other areas of contemporary finance, has always been an issue and great challenge for managers. To response to this vital need, many researchers and practitioners have sought methodologies and models to help managers come up with more accurate decisions in credit risk measurement. Conventionally, there are three broad categories of models used to estimate PD - one of the critical credit risk components : (1) expert systems, including artificial neural networks; (2) rating systems; and (3) credit scoring models.In this paper, we have focused on the first classification. Historically, Lenders have applied Models such as 5 C's expert systems to assess credit quality. They are character (reputation), capital (leverage), capacity (earnings volatility), collateral, and cycle (macroeconomic) conditions. Evaluation of the 5 C's is performed by human experts, who may be inconsistent and subjective in their assessments. Moreover, traditional expert systems specify no weighting scheme that would order the 5C's in terms of their relative importance in forecasting PD, or detecting defaulting firms