Multiple classifier architectures and their application to credit risk assessment

Multiple classifier systems combine several individual classifiers to deliver a final classification decision. An increasingly controversial question is whether such systems can outperform the single best classifier and if so, what form of multiple classifier system yields the greatest benefit. In this paper the performance of several multiple classifier systems are evaluated in terms of their ability to correctly classify consumers as good or bad credit risks. Empirical results suggest that many, but not all, multiple classifier systems deliver significantly better performance than the single best classifier. Overall, bagging and boosting outperform other multi-classifier systems, and a new boosting algorithm, Error Trimmed Boosting, outperforms bagging and AdaBoost by a significant margin.