Neural networks and the evolution of firms and industries:

Introduction The basic objectives of this paper are twofold: (1) to show how neural networks might be applied to and used to analyse firms; and (2) to investigate the effect of different 'firm types' on evolutionary processes at the industry level. Applying neural networks to economic, managerial and financial issues is not, in itself, original. In business and finance, neural network analysis is not uncommon (see, for example,firm applications of neural network analysis within economics are becoming increasingly important, for example: Binner et al (2005) on inflation; Papadas and Hutchinson (2002) on input-output technology; Johnes (2000) on macroeconomic modelling; Franses and Homelen (1998) and Plasmans et al (1998) on exchange rate modelling. But previous published work that has applied a neural network framework to the firm (for example, Delgado et al, 2004) has not developed the analysis using actual data as is done in this paper. The rest of the discussion is organised as follows. In the next section there is a brief introduction to neural networks and how they might be relevant for the analysis of the