Development of credit risk model in banking industry based on GRA

A grey relational analysis (GRA) approach is proposed for analyzing the credit risks of banking industry. To construct a financial distress warning system for banking industry, a GRA approach is developed and applied to the real data set with 34 banking samples for the period 2004-2006. The results of the current model are compared to those of traditional ones. The empirical results show that in the prediction of financially distress as well as financially sound banks, the proposed GRA model demonstrates a good prediction model. The results also imply that the three-year average leads to the best accuracy. It is a significant implication for the establishment of early warning models of financial crisis. The current results show that the proposed GRA provides a new and robust approach in managing financial distress warning tasks.