Artificial Immune Algorithm Based Early-Warning System for Enterprise Financial Distress

To eliminate limitations of traditional early-warning of financial distress methods, an artificial immune algorithm based early-warning of financial distress is presented. To begin with, both antigens and memory antibodies with class information added to artificial immune network are trained to learn the feature of training samples. In this way, memory antibody cells pool can represent these samples better than those obtained without class information. Then the k-nearest neighbor method is used to classify the test samples. The testing results show that the method reaches higher training speed and lower error rate.