Maps for Analyzing Failures of Small and Medium-sized Enterprises

Abstract

There are several ways to approach the phenomenon of corporate failure. The classic approach is to look at failure as a terminal disease that manifests itself in the financial statements of a company two or three years before the actual failure. An alternative approach is to view the tendency of an enterprise to fail as a chronic disease that manifests itself only occasionally. The fundamental issue is the ability of an enterprise to adapt to changes in its environment. If management is not able to react quickly enough to external impulses, the enterprise will have a “failure disorder” that leads to an increased risk of failure. This failure disorder may be latent for several years, i.e. there is a period of several years during which the enterprise has a high probability of failure. Simple linear discriminant analysis which is commonly used to predict the failure of companies is not capable of finding the more delicate patterns in financial statements of companies. In this chapter Kimmo Kiviluoto and Pentti Bergius show how the Self-Organizing Map is an essential tool for analyzing the financial statements of companies in order to find much more subtle patterns that are indicators of failure disorder.