Martín, B. and Serrano Cinca, C. (1994): "Self Organizing Neural Netwoks: The Financial State of Spanish Companies", in Neural Networks in the Capital Markets, Nov 1994, Ed. N.A. Refenes, John Wiley & Sons

Abstract In this chapter we focus on the application of neural network architectures with unsupervised learning to financial analysis, although the methodology used can also be applied to data processing in other fields. The financial analysis tries to transform the data contained in company accounting statements into useful information for economic decision-making. This is an interdisciplinary exercise that uses methodologies from other fields, such as those of statistics, operations research and computing. Economic and financial data, particularly that contained in company financial statements, consists of a great amount of correlated data, sometimes incomplete and adulterated. This kind of data is well suited for processing by means of artificial neural networks that present some advantages in relation to more conventional tools, such as nonlinear modeling capability, generalisation from examples, robustness to noise and ease of use Keywords Neural Networks, unsupervised learning, Self-Organizing Feature Maps, data processing, financial data analysis, weight analysis. Book (Amazon)