The Default Risk of Firms Examined with Smooth Support Vector Machines

In the era of Basel II a powerful tool for bankruptcy prognosis is vital for banks. The tool must be precise but also easily adaptable to the bank's objections regarding the relation of false acceptances (Type I error) and false rejections (Type II error). We explore the suitabil- ity of Smooth Support Vector Machines (SSVM), and investigate how important factors such as selection of appropriate accounting ratios (predictors), length of training period and structure of the training sample in°uence the precision of prediction. Furthermore we show that oversampling can be employed to gear the tradeo® between error types. Finally, we illustrate graphically how di®erent variants of SSVM can be used jointly to support the decision task of loan o±cers.