Discovering causes of financial distress by combining evolutionary algorithms and artificial neural networks

ABSTRACT

In this work we compare two soft-computing methods for producing models that are able to predict whether a company is going to have book losses: artificial neural networks (ANNs) and genetic programming (GP). In order to build prediction models that can be applied to an extensive number of practical cases, we need simple models which require a small amount of data. Kohonen's self-organizing map (SOM) is a non-supervised neural network that is usually used as a clustering tool. In our case a SOM has been used to reduce the dimensions of the prediction problem. Traditionally, ANNs have been considered able to produce better classifier structures than GP. In this work we merge the capability of GP for generating classification trees and the feature extraction abilities of SOM, obtaining a classification tool that beats the results yielded using an evolutionary ANN method.

REFERENCES

• 1: E. Alfaro-Cid, A. Cuesta-Cañada, K. Sharman, and A. I. Esparcia-Alcázar. Natural Computing in Computational Economics and Finance, chapter Strong Typing, Variable Reduction and Bloat Control for Solving the Bankruptcy Prediction Problem Using Genetic Programming. Springer, 2008.
• 2: E. Alfaro-Cid, A. Mora, J. Merelo, K. Sharman, and A. Esparcia-Alcázar. A SOM and GP tool for reducing the dimensionality of a financial distress prediction problem. LNCS, 2008. Accepted for publication.
• 3: E. Alfaro-Cid, K. Sharman, and A. Esparcia-Alcázar. A genetic programming approach for bankruptcy prediction using a highly unbalanced database. LNCS, 4448:169--178, 2007.
• 4: E. Altman. The success of business failure prediction models. An international survey. J. of Banking, Acc. and Finance, 8:171--198, 1984.
• 5: W. Beaver. Financial ratios as predictors of failures. Empirical research in accounting: Selected studies. J. of Acc. Research, 5:71--111, 1966.
• 6: Christopher M. Bishop, Neural networks for pattern recognition, Oxford University Press, Oxford, 1996
• 7: Anthony Brabazon , Michael O'Neill, Biologically Inspired Algorithms for Financial Modelling (Natural Computing Series), Springer-Verlag New York, Inc., Secaucus, NJ, 2006
• 8: A. Cangelosi, D. Parisi, and S. Nolfi. Cell Division and Migration in a Genotype for Neural Networks. Network: Computation in Neural Systems, 5:497--515, 1994.
• 9: P. Castillo, M. Arenas, J. Merelo, V. Rivas, and G. Romero. Multiobjective optimization of ensembles of multilayer perceptrons for pattern classification. In Proceedings PPSN IX, pages 453--462, 2006.
• 10: P. Castillo, J. Merelo, G. Romero, A. Prieto, and I. Rojas. Statistical Analysis of the Parameters of a Neuro-Genetic Algorithm. IEEE Trans. on Neural Networks, 13(6):1374--1394, 2002.
• 11: P. A. Castillo, J. M. D. la Torre, J. J. Merelo, and I. Román. Forecasting business failure. A comparison of neural networks and logistic regression for spanish companies. In Proc. of the 24th Eur. Acc. Assoc., Athens, Greece, 2001.
• 12: P. A. Castillo, J. J. Merelo, V. Rivas, G. Romero, and A. Prieto. G-Prop: Global Optimization of Multilayer Perceptrons using GAs. Neurocomputing, 35(1-4):149--163, 2000.
• 13: Ivan De Falco , A. Iazzetta , P. Natale , Ernesto Tarantino, Evolutionary Neural Networks for Nonlinear Dynamics Modeling, Proceedings of the 5th International Conference on Parallel Problem Solving from Nature, p.593-602, September 27-30, 1998
• 14: P. Durr, C. Mattiussi, and D. Floreano. Neuroevolution with Analog Genetic Encoding. LNCS, 4193:671--680, 2006.
• 15: F. Fernández de Vega, M. Rubio del Solar, and A. Fernández Martínez. Implementación de algoritmos evolutivos para un entorno de distribución epidémica. In Actas del MAEB'05, pages 57--62, Granada, Spain, 2005.
• 16: Nathalie Japkowicz , Shaju Stephen, The class imbalance problem: A systematic study, Intelligent Data Analysis, v.6 n.5, p.429-449, October 2002
• 17: S. Kaski, J. Sinkkonen, and J. Peltonen. Bankruptcy analysis with self-organizing maps in learning metrics. IEEE Trans. Neural Networks, 12(4):936ss, 2001.
• 18: K. Kiviluoto. Predicting bankruptcies with the self-organizing map. Neurocomputing, 21(1-3):191--201, 1998.
• 19: T. Kohonen , M. R. Schroeder , T. S. Huang, Self-Organizing Maps, Springer-Verlag New York, Inc., Secaucus, NJ, 2001
• 20: T. Lensberg, A. Eilifsen, and T. E. McKee. Bankruptcy theory development and classification via genetic programming. Eur. J. of Op. Research, 169:677--697, 2006.
• 21: F. Leung, H. Lam, S. Ling, and P. Tam. Tuning of the structure and parameters of a neural network using an improved genetic algorithm. IEEE Trans. on Neural Networks, 14(1):79--88, 2003.
• 22: R. Lippmann. An introduction to computing with neural nets. IEEE ASSP Magazine, 3(4):4--22, 1987.
• 23: H. Mayer, R. Schwaiget, and R. Huber. Evolving topologies of artificial neural networks adapted to image processing tasks. In Proc. of 26th Int. Symp. on Remote Sensing of Environment, pages 71--74, Vancouver, BC, Canada, 1996.
• 24: J. J. Merelo, M. G. Arenas, J. Carpio, P. A. Castillo, V. M. Rivas, G. Romero, and M. Schoenauer. Evolving objects. In Proc. of FEA'2000 & JCIS'2000, pages 1083--1086, Atlantic City, NJ, 2000.
• 25: Juan J. Merelo Guervós , M. Patón , Antonio Cañas , Alberto Prieto , Federico Morán, Optimization of a Competitive Learning Neural Network by Genetic Algorithms, Proceedings of the International Workshop on Artificial Neural Networks: New Trends in Neural Computation, p.185-192, June 09-11, 1993
• 26: David J. Montana, Strongly typed genetic programming, Evolutionary Computation, v.3 n.2, p.199-230, Summer 1995 [doi>10.1162/evco.1995.3.2.199]
• 27: A. M. Mora, J. L. J. Laredo, P. A. Castillo, and J. J. Merelo. Predicting financial distress: A case study using self-organizing maps. In F.Sandoval and et al., editors, Proc. of the 9th International Work Conference on Artificial Neural Networks (IWANN 2007), volume 4507 of LNCS, pages 765--772, San Sebastian, Spain, June 2007.
• 28: D. Moriarty and R. Miikkulainen. Hierarchical evolution of neural networks. In Proc. of the ICEC'98, pages 428--433, Anchorage, AK, 1998.
• 29: I. Román, M. E. Gómez, J. M. D. la Torre, J. J. Merelo, and A. M. Mora. Predicting financial distress: Relationship between continued losses and legal bankrupcy. In Proc. of the 27th Annual Congress Eur. Acc. Assoc., Dublin, Ireland, 2006.
• 30: Sancho Salcedo-Sanz , José-Luis Fernández-Villacañas , María Jesús Segovia-Vargas , Carlos Bousoño-Calzón, Genetic programming for the prediction of insolvency in non-life insurance companies, Computers and Operations Research, v.32 n.4, p.749-765, April 2005 [doi>10.1016/j.cor.2003.08.015]
• 31: D. Thierens, J. Suykens, J. Vandewalle, and B. D. Moor. Genetic weight optimization of a feedforward neural network controller. In Proc. of the Conf. on Artificial Neural Nets and Genetic Algorithms, pages 658--663, 1993.
• 32: S. Ultsch. Kohonen's self-organizing maps for exploratory data analysis. In Proc. of the INNC'90, pages 305--308, 2000.
• 33: Darrell Whitley, The GENITOR algorithm and selection pressure: why rank-based allocation of reproductive trials is best, Proceedings of the third international conference on Genetic algorithms, p.116-121, December 1989, George Mason University, United States
• 34: X. Yao. Evolving artificial neural networks. Proc. of the IEEE, 87(9):1423--1447, 1999.

INDEX TERMS

Primary Classification:
  J. Computer Applications
  J.4 SOCIAL AND BEHAVIORAL SCIENCES

Additional Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.2 Design Methodology

General Terms:
Economics

Keywords:
artificial neural networks, financial distress prediction, genetic programming, self-organizing maps