An ontogenic neural network for bankruptcy classification

Neural networks are now accepted as a viable alternative to more traditional and conventional solution approaches in the area of pattern classification (e.g. classification, signal recognition, discriminant analysis). Such networks possess the significant advantage of being nonparametric – as well as being easy to use and understand. Network development is typically accomplished by means of a two-phase approach. In the first, a network architecture is selected. In the second, a training exercise is conducted so as to establish the weights on the network branches. However, as with any tool for analysis, neural-network classifiers have certain drawbacks. Included among these is the quite ad hoc nature of the design and training process. Another problem is one common not only to neural networks, but also inherent in almost any other method of classification. This is the fact that such methods generally ‘do not know what they do not know’. As a consequence, even when faced with new cases that are very much unlike anything that they have been trained upon, they still do not hesitate to boldly (and often foolishly) produce a classification. In this paper, we present an approach that simultaneously designs and trains ontogenic neural network classifiers. Ontogenic neural networks, in turn, have two features of particular interest. First, they virtually design and train themselves. Second, they are hesitant to classify objects that appear to be ‘too dissimilar’ from those upon which they were trained. We demonstrate the performance of such an approach on a very specific problem: the classification of firms with regard to their future fiscal well-being.