ArticlesNo Access

ARTIFICIAL METAPLASTICITY NEURAL NETWORK APPLIED TO CREDIT SCORING

Group for Automation in Signals and Communications, Technical University of Madrid, ETSI Telecomunciación, Ciudad Universitaria, Madrid 28040, Spain

Search for more papers by this author

A. MARIN-DE-LA-BARCENA

Group for Automation in Signals and Communications, Technical University of Madrid, ETSI Telecomunciación, Ciudad Universitaria, Madrid 28040, Spain

Search for more papers by this author

J. JIMENEZ-TRILLO

Group for Automation in Signals and Communications, Technical University of Madrid, ETSI Telecomunciación, Ciudad Universitaria, Madrid 28040, Spain

Search for more papers by this author

J. A. PIÑUELA

Group for Automation in Signals and Communications, Technical University of Madrid, ETSI Telecomunciación, Ciudad Universitaria, Madrid 28040, Spain

Search for more papers by this author

, and

D. ANDINA

Group for Automation in Signals and Communications, Technical University of Madrid, ETSI Telecomunciación, Ciudad Universitaria, Madrid 28040, Spain

Search for more papers by this author

https://doi.org/10.1142/S0129065711002857Cited by:39 (Source: Crossref)

Abstract

The assessment of the risk of default on credit is important for financial institutions. Different Artificial Neural Networks (ANN) have been suggested to tackle the credit scoring problem, however, the obtained error rates are often high. In the search for the best ANN algorithm for credit scoring, this paper contributes with the application of an ANN Training Algorithm inspired by the neurons' biological property of metaplasticity. This algorithm is especially efficient when few patterns of a class are available, or when information inherent to low probability events is crucial for a successful application, as weight updating is overemphasized in the less frequent activations than in the more frequent ones. Two well-known and readily available such as: Australia and German data sets has been used to test the algorithm. The results obtained by AMMLP shown have been superior to state-of-the-art classification algorithms in credit scoring.

Keywords:

References

L. C. Thomas, International Journal of Forecasting 16, 149 (2000), DOI: 10.1016/S0169-2070(00)00034-0. Web of Science, Google Scholar
C. M. Wang and Y. F. Huang, Expert Syst. Appl. 36, 5900 (2009), DOI: 10.1016/j.eswa.2008.07.026. Web of Science, Google Scholar
S. T. Li, W. Shiue and M. H. Huang, Expert Syst. Appl. 30, 772 (2006). Web of Science, Google Scholar
A. Laha, Adv. Eng. Inform. 21, 281 (2007). Web of Science, Google Scholar
A. Vellido, P. J. Lisboa and J. Vaughan, Expert Syst. Appl. 17, 51 (1999), DOI: 10.1016/S0957-4174(99)00016-0. Web of Science, Google Scholar
A. Khashman, Int. J. Neural Syst. 19, 285 (2009). Link, Web of Science, Google Scholar
T. S. Leeet al., Expert Syst. Appl. 23, 245 (2002), DOI: 10.1016/S0957-4174(02)00044-1. Web of Science, Google Scholar
D. West, Comput. Oper. Res. 27, 1131 (2000). Web of Science, Google Scholar
D. Wuet al., Int. J. Neural Syst. 20(2), 109 (2010). Link, Web of Science, Google Scholar
C. S. Ong, J. J. Huang and G. H. Tzeng, Expert Syst. Appl. 29, 41 (2005). Web of Science, Google Scholar
J. J. Huang, G. H. Tzeng and C. S. Ong, Appl. Math. Comput. 174, 1039 (2006). Web of Science, Google Scholar
D. Martenset al., Eur. J. Oper. Res. 183, 1466 (2007). Web of Science, Google Scholar
F. Hoffmannet al., Eur. J. Oper. Res. 177, 540 (2007). Web of Science, Google Scholar
C. L. Huang, M. C. Chen and C. J. Wang, Expert Syst. Appl. 33, 847 (2007), DOI: 10.1016/j.eswa.2006.07.007. Web of Science, Google Scholar
Y. Penget al., Decis. Support Syst. 44, 1016 (2008), DOI: 10.1016/j.dss.2007.12.001. Web of Science, Google Scholar
C. F. Tsai and J. W. Wu, Expert Syst. Appl. 34, 2639 (2008). Web of Science, Google Scholar
L. Nanni and A. Lumini, Expert Syst. Appl. 36, 3028 (2009), DOI: 10.1016/j.eswa.2008.01.018. Web of Science, Google Scholar
X. Xu, C. Zhou and Z. Wang, Expert Syst. Appl. 36, 2625 (2009), DOI: 10.1016/j.eswa.2008.01.024. Web of Science, Google Scholar
S. T. Luo, B. W. Cheng and C. H. Hsieh, Expert Syst. Appl. 36, 7562 (2009), DOI: 10.1016/j.eswa.2008.09.028. Web of Science, Google Scholar
C. F. Tsai, Knowledge-Based Syst. 32, 120 (2009). Google Scholar
Y. Ping, Hybrid classifier using neighborhood rough set and SVM for credit scoring, Proc. 2nd Int. Conf. on Business Intelligence and Financial Engineering (2009) pp. 138–142. Google Scholar
F. L. Chen and F. C. Li, Expert Syst. Appl. 37, 4902 (2010), DOI: 10.1016/j.eswa.2009.12.025. Web of Science, Google Scholar
A. Marcano-Cedeño, J. Quintanilla-Dominguez and D. Andina, Neurocomputing 74(8), 1243 (2011), DOI: 10.1016/j.neucom.2010.07.019. Web of Science, Google Scholar
UCI Machine Learning Repository. http://archive.ics.uci.edu/ml/datasets.html . Google Scholar
D. Andina and J. Ropero-Pelaez, On the biological plausibility of artificial metaplasticity, in LNCS, Springer, 6686 (2011) 119–128 . Google Scholar
J. Menke and T. Martinez, Int. J. Neural Syst. 19(1), 1 (2009). Link, Web of Science, Google Scholar
F. Rasheed, M. Alshalalfa and R. Alhajj, Int. J. Neural Syst. 19(1), 11 (2009). Link, Web of Science, Google Scholar
R. Savitha, S. Suresh and N. Sundararajan, Int. J. Neural Syst. 19(4), 253 (2009). Link, Web of Science, Google Scholar
S. Schliebs, N. Kasabv and M. Defoin-Platel, Int. J. Neural Syst. 20(6), 481 (2010). Link, Web of Science, Google Scholar
F. J. Ropero-Pelaez and D. Andina, Probabilistic versus incremental presynaptic learning in biologically plausible synapses, in LNCS, Springer 6686 (2011) 80–89 . Google Scholar
H. Adeli and A. Panakkat, Neural Networks 22, 1018 (2009), DOI: 10.1016/j.neunet.2009.05.003. Medline, Web of Science, Google Scholar
E. Lopez-Rubio and J. M. Ortiz-de-Lazcano-Lobato, Int. J. Neural Syst. 19(2), 91 (2009). Link, Web of Science, Google Scholar
E. Lopez-Rubio, Int. J. Neural Syst. 19(5), 345 (2009). Link, Web of Science, Google Scholar
M. Ahmadlou and H. Adeli, Integrated Computer-Aided Engineering 17(3), (2010). Google Scholar
D. Andinaet al., Intell. Autom. Soft Co. 15(4), 683 (2009). Web of Science, Google Scholar
D. Andina, J. Martinez-Antorrena and I. Melgar, Importance sampling in neural detector training phase, Proc. of the World Automation Congress (2004) pp. 43–48. Google Scholar
A. Marcano-Cedeño, A. Álvarez-Vellisco and D. Andina, Artificial metaplasticity MLP applied to image classification, Proc. 7th Int. Conf. on Industrial Informatics (2009) pp. 650–653, DOI: 10.1109/INDIN.2009.5195879. Google Scholar
A. Marcano-Cedeño, J. Quintanilla-Domínguez and D. Andina, Wood defects classification using artificial metaplasticity neural network, Proc. 35th Annual Conf. on of the IEEE Industrial Electronics Society pp. 3422–3427, DOI: 10.1109/IECON.2009.5415189. Google Scholar