Research on Financial Distress Prediction with Adaptive Genetic Fuzzy Neural Networks on Listed Corporations of China

Zhibin XIONG

School of Mathematical Sciences, South China Normal University, Guangzhou, China.

DOI: 10.4236/ijcns.2009.25043                

Abstract

To design a multi-population adaptive genetic BP algorithm, crossover probability and mutation probability are self-adjusted according to the standard deviation of population fitness in this paper. Then a hybrid model combining Fuzzy Neural Network and multi-population adaptive genetic BP algorithm—Adaptive Genetic Fuzzy Neural Network (AGFNN) is proposed to overcome Neural Network’s drawbacks. Furthermore, the new model has been applied to financial distress prediction and the effectiveness of the proposed model is performed on the data collected from a set of Chinese listed corporations using cross validation approach. A comparative result indicates that the performance of AGFNN model is much better than the ones of other neural network models.

Keywords

Multi-Population Adaptive Genetic BP Algorithm, Fuzzy Neural Network, Cross Validation, Financial Distress

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	P. Jackson and W. Perraudin, “Regulatory implications of credit risk modeling,” Journal of Banking and Finance, Elsevier Science Inc., Vol. 24, pp. 1-14, 2000.
[2]	T. G. Calderon and J. J. Cheh, “A roadmap for future neural networks research in auditing and risk assessment,” International Journal of Accounting Information Systems, Elsevier Science Inc. Vol. 3, pp. 203-235, 2002.
[3]	A. F. Shapiro, “The merging of neural networks, fuzzy logic, and genetic algorithms,” Insurance, Mathematics and Economics, Elsevier Science Inc., Vol. 31, pp. 115-131, 2002.
[4]	R. Malhotra and D. K. Mahotra, “Differentiating between good credits and bad credits using neuro-fuzzy systems,” European Journal of Operational Research, Elsevier Science Inc., Vol. 136, pp. 190–211, 2002.
[5]	S. Piramuthn, “Financial credit risk evaluation with neural and neuro-fuzzy systems,” European Journal of Operational Research, Elsevier Science Inc., Vol. 112, pp. 310–321, 1999.
[6]	C. J. Lin and Y. J. Xu, “A self-adaptive neural fuzzy network with group-based symbiotic evolution and prediction applications,” Fuzzy Sets and Systems, Elsevier Science Inc., Vol. 157, pp. 1036-1056, 2006.
[7]	R. Sikora and S. Piramuthu, “Framework for efficient feature selection in genetic algorithm based data mining,” European Journal of Operational Research, Elsevier Science Inc., Vol. 180, pp. 723-737, 2007.
[8]	M. Srinivas and L. M. Patnaik, “Adaptive probabilities of crossover and mutation in genetic algorithms,” Systems, Man and Cybernetics, IEEE Transactions on, Vol. 24, No. 4, pp. 656-667, 1994.
[9]	X. T. Guo and Y. Zhu, “Evolutionary neural networks based on genetic algorithms,” Journal of Qinghua University (National Science Edition), Vol. 40, No. 10, pp. 116-119, October 2000.
[10]	B. A. Jain and B. N. Nag, “Performance evaluation of neural network decision models,” Journal of Manage Information Systems, Elsevier Science Inc., Vol. 14, pp. 201-216, 1997.
[11]	R. A. Johnson and D. W. Wichern, “Applied multivariate statistical analysis,” 5th Edition, Prentice-Hall, Upper Saddle River, N. J., 2002.
[12]	J. S. R. Jang, C. T. Sun, and E. Mizutani, “Neuro-fuzzy and soft computing, matlab curriculum series,” Prentice-Hall, Englewood Cliffs, N. J., 1997.
[13]	Z. B. Xiong and R. –J. Li, “Credit risk evaluation with fuzzy neural networks on listed corporations of China,” Proceedings of IWVDVT, China, pp. 397-402, May, 2005.