Abstract
Many recent papers have dealt with the application of feedforward neural networks in financial data processing. This powerful neural model can implement very complex nonlinear mappings, but when outputs are not available or clustering of patterns is required, the use of unsupervised models such as self-organizing maps is more suitable. The present work shows the capabilities of self-organizing feature maps for the analysis and representation of financial data and for aid in financial decision-making. For this purpose, we analyse the Spanish banking crisis of 1977–1985 and the Spanish economic situation in 1990 and 1991, making use of this unsupervised model. Emphasis is placed on the analysis of the synaptic weights, fundamental for delimiting regions on the map, such as bankrupt or solvent regions, where similar companies are clustered. The time evolution of the companies and other important conclusions can be drawn from the resulting maps.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Abbreviations
- nx :
-
x dimension of the neuron grid, in number of neurons
- ny :
-
y dimension of the neuron grid, in number of neurons
- n :
-
dimension of the input vector, number of input variables
- (i, j):
-
indices of a neuron on the map
- k :
-
index of the input variables
- w ijk :
-
synaptic weight that connects thek input with the (i, j) neuron on the map
- W ij :
-
weight vector of the (i, j) neuron
- x k :
-
input vector
- X :
-
input vector
- ∈(t):
-
learning rate
- ∈o :
-
starting learning rate
- ∈f :
-
final learning rate
- R(t):
-
neighbourhood radius
- R0 :
-
starting neighbourhood radius
- R f :
-
final neighbourhood radius
- t :
-
iteration counter
- t rf :
-
number of iterations until reachingR f
- t ∈f :
-
number of iterations until reaching ∈f
- h(·):
-
lateral interaction function
- σ:
-
standard deviation
- ∀:
-
for every
- d (x, y):
-
distance between the vectors x and y
References
Lippman RP. An introduction to computing with Neural Nets. IEEE ASSP Magazine 1987; April: 4–22
Hecht-Nielsen R. Neurocomputing: Picking the human brain. IEEE Spectrum 1988; March: 36–41
Eberhart RC, Dobbins RW. Neural Networks PC Tools. San Diego: Academic Press, 1990
Hoptroff RG. The principles and practice of times series forecasting and business modelling using Neural Networks. Neural Comput & Applic 1993; 1: 59–66
Martín-del-Brío B, Serrano-Cinca C. A comparison of artificial neural systems and traditional financial data analysis methods. The Solvency Map. (Submitted)
Blinks DL, Allinson NM. Financial data recognition and prediction using Neural Networks. In: Proceedings Int. Conf. on Artificial Neural Networks (ICANN '91), Espoo, Finland, 1991, 1709–1712
Dutta S, Shekhar S. Bond Rating: a non conservative application of Neural Networks. In: Proceedings IEEE Int. Conf. on Neural Networks, vol 2, San Diego, 1988; 443–458
Refenes AN, Azema-Barac M, Treleaven PC. Financial Modelling using Neural Networks. In: Liddell H (ed.), Commercial Applications of Parallel Computing. London: UNICOM, 1993
Serrano-Cinca C, Martín-del-Brío B. Predicción de la quiebra bancaria mediante el empleo de Redes Neuronales Artificiales. Rev Española Financ y Contab 1993; 74: 153–176
Trigueiro D, Berry RH. Neural Networks and the automatic selection of financial ratios. Tech Rep, INESC, Portugal, 1991
Utans J, Moody J, Selecting neural networks architectures for prediction risk: application to corporate bond rating prediction. In: Proceedings Int. Conf. on Artif. Intelligence Applic. in Wall Street, IEEE Comp Press, Los Alamillos, CA, 1991
Varfis A, Versino C. Univariant economic time series forecasting by Connectionist Methods. In: Proceedings Int. Neural Networks Conf., Paris, France, 1990: 342–345.
White H. Economic prediction using Neural Networks: The case of IBM daily stock returns. In: Proceedings IEEE Int. Conf. on Neural Networks, vol 2, San Diego, 1988; 451–459.
Rumelhart DE, Hinton GE, Willians RJ. Learning representations by backpropagating errors. Nature 1986; 323: 533–536
Kohonen T. Self-Organization and Associative Memory, 3rd edn. Berlin: Springer-Verlag, 1989
Kohonen T. The Self-Organizing Map. Proc of the IEEE 1990; 78(9): 1464–1480
Ritter H, Obermayer K, Schulten K et al. Self-Organizing Maps and Adaptive Filters. In: Domany E, van Hemmen JL, Schulten K (eds), Models of Neural Networks. Berlin: Springer-Verlag, 1991; 281–306
Spiegel MR. Statistics. New York: McGraw Hill, 1988
Ritter H, Martinetz T, Schulten K. Neural Computation and Self-Organizing Maps: An Introduction. Reading, MA: Addison-Wesley, 1992
Beaver W. Financial ratios as predictors of failure. J. Account Research, Suppl Empirical Research in Accounting: Selected studies, 1966; V: 71–111
Laffarga J, Martin JL; Vazquez MJ: El análisis de la solvencia en las instituciones bancarias: propuesta de una metodología y aplicaciones de la banca española. Esic-Market 1985; 48, April–June
Laffarga J, Martin JL, Vazquez MJ: El pronóstico a corto plazo del fracaso en las instituciones bancarias: metodología y aplicaciones al caso español. Esic-Market 1986; 53, July–September
Pina V. Estudio empírico de la crisis bancaria. Rev Española Financ y Contab 1989; XVIII (58)
Hartvigsen G. Limitations of Knowledge-Based systems for Financial Analysis in Banking. Expert Systems Applications 1992; 4: 19–32
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Martín-del-Brío, B., Serrano-Cinca, C. Self-organizing neural networks for the analysis and representation of data: Some financial cases. Neural Comput & Applic 1, 193–206 (1993). https://doi.org/10.1007/BF01414948
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01414948