Credit Risk Analysis with Computational Intelligence: A Review

Credit risk analysis has attracted much attention from financial institutions due to the recent financial crises and regulatory concerns of Basel II (Yu et al., 2008). Furthermore, business competition for obtaining more market share and profit become more and more aggressive in recent years, some institutions take more risks to achieve competitive advantage in the market. Consequently, many financial institutions suffered a great loss from a steady increase of defaults and bad loans from their counterparties. In USA, the general credit cards issuers charged off 27.19 billion in debt as a loss in 1997 and this figure had reached $31.91 billion in 2006 (HSN Consultants Inc., 2007). However, more and more adult population use credit products, such as mortgages, car loan, and credit card, etc., from banks or other financial institutions. For the financial institutions, they can not refuse such a large credit market to averse the credit risk. Therefore, an effective credit risk analysis model has been a crucial factor because an effective credit risk analysis technique would be transformed into significant future savings.

The remainder of this chapter is organized as follows. In next section, we explain how literatures were selected. Section 1.3 examines and analyzes 32 articles in detail and investigates their quantitative methods and classification accuracy. In addition, the performance of 12 articles using support vector machines will be reported in detail. The main factors that affect the performance of the SVM will be explored in this section. Subsequently, some implications and future research directions are pointed out in Section 1.4. Finally, Section 1.5 concludes the chapter.