An Evolutionary-Programming-Based Knowledge Ensemble Model for Business Credit Risk Analysis
Business credit risk management is a scientific field which many academic and professional people have been working for, at least, the last three decades. Almost all financial organizations, such as banks, credit institutions, clients, etc., need this kin
- PDF / 537,288 Bytes
- 17 Pages / 595.276 x 841.89 pts (A4) Page_size
- 86 Downloads / 155 Views
10.1 Introduction Business credit risk management is a scientific field which many academic and professional people have been working for, at least, the last three decades. Almost all financial organizations, such as banks, credit institutions, clients, etc., need this kind of information for some firms in which they have an interest of any kind. However, business credit risk management is not an easy thing because business credit risk management is a very complex and challenging task from the viewpoint of system engineering. It contains many processes, such as risk identification and prediction, modeling and control. In this complex system analysis, risk identification is no doubt an important and crucial step (Lai et al., 2006a), which directly influences the later processes of business credit risk management. This chapter only focuses on the business credit risk identification and analysis. For credit risk identification and analysis, some approaches were presented during the past decades. Originally, the first approach to identify business credit risk started with the use of empirical methods (e.g., the “three A” method, the “five C” method, and the “credit-men” method) proposed by large banks in USA (Lai et al., 2006a). Then, the financial ratios methodology was developed for business credit risk identification and prediction. These ratios have been long considered as objective indicators of firm insolvency risk (Lai et al., 2006a; Beaver, 1966; Courtis, 1978; Altman, 1993). The approach of the financial ratios (also called univariate statistical approach), gave rise to the methods for business credit risk prediction based on the multivariate statistical analysis. In 1968 already, Altman (1968) proposed to use the discriminant analysis (a discriminant function with five financial ratios has been assessed) for predicting the business failure risk. Subsequently, the use of this method has continued to spread out to the point that today we can speak of discriminant models of
180
10 An EP-Based Knowledge Ensemble Model for Credit Risk Analysis
predicting business bankruptcy risk. At the same time, however, the generalization of the discriminant analysis resulted in some critical papers; interested readers can see Eisenbeis (1977), Ohlson (1980), and Dimitras et al (1996) for more details. Since the work of Altman (1968), several studies proposing other methods have been used to overcome some disadvantages of the discriminant analysis so as to provide higher prediction accuracy. Among these studies, we can cite the study of Ohlson (1980) and Zavgren (1985) using logit analysis and the study of Zmijewski (1984) using probit analysis. In addition, Frydman et al. (1985) first employed the recursive partitioning algorithm while Gupta et al. (1990) used mathematical programming methods for the business failure prediction problem. Other methods used were survival analysis by Luoma and Latitinen (1991), expert systems by Messier and Hansen (1988), neural networks by Altman et al. (1994), Lee et al. (2005), and Lai et
Data Loading...
