Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지

GA-based Normalization Approach in Back-propagation Neural Network for Bankruptcy Prediction Modeling

유전자알고리즘을 기반으로 하는 정규화 기법에 관한 연구 : 역전파 알고리즘을 이용한 부도예측 모형을 중심으로

  • Tai, Qiu-Yue (College of Business Administration, Ewha Womans University) ;
  • Shin, Kyung-Shik (College of Business Administration, Ewha Womans University)
  • 태추월 (이화여자대학교 경영학과) ;
  • 신경식 (이화여자대학교 경영학과)
  • Received : 2010.09.02
  • Accepted : 2010.09.19
  • Published : 2010.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

The back-propagation neural network (BPN) has long been successfully applied in bankruptcy prediction problems. Despite its wide application, some major issues must be considered before its use, such as the network topology, learning parameters and normalization methods for the input and output vectors. Previous studies on bankruptcy prediction with BPN have shown that many researchers are interested in how to optimize the network topology and learning parameters to improve the prediction performance. In many cases, however, the benefits of data normalization are often overlooked. In this study, a genetic algorithm (GA)-based normalization transform, which is defined as a linearly weighted combination of several different normalization transforms, will be proposed. GA is used to extract the optimal weight for the generalization. From the results of an experiment, the proposed method was evaluated and compared with other methods to demonstrate the advantage of the proposed method.

역전파 알고리즘은 오랫동안 부도예측모형 관련한 연구에 많이 적용되어왔다. 역전파 알고리즘을 사용하기전에 필히 고려해야 할 중요한 요소들로는 네트워크 구조, 학습요소, 정규화 방법 등이다. 하지만 신경망 성과를 향상시키기 위한 네트워크 구조 및 학습요소 최적화 관련한 연구는 기존의 연구들에서 많이 이루어 졌지만 데이터 정규화와 관련한 연구는 아직 많이 이루어지지 않았다. 따라서 본 연구에서는 유전자 알고리즘을 기반으로 하는 정규화 기법을 제시하였다. 최적의 입력데이터 정규화를 위하여 본 연구에서는 우선 각각의 서로 다른 정규화 기법들을 동일 가중치를 두어 일반화 시켰으며 유전자 알고리즘을 이용하여 최적의 가중치를 찾음으로써 최적화된 입력변수 정규화가 이루어지도록 하였다. 제안한 방법론을 검증하기 위하여 부도예측 데이터를 이용하여 실험을 하였으며 제안하는 방법과 기존 다른 방법들간의 비교를 통하여 그 타당성을 검증하였다.

Keywords

References

  1. A1 Shalabi, L., and Shaaban, Z., "Normalization as a preprocessing engine for data mining and the approach of preference matrix", IEEE Computer Society, Proceedings of the Internatinal Conference on Dependability of Computer Systems, 0-7695-256, (2006).
  2. Akdemir, B. and Yu, L., "Elliot waves predicting for stock marketing using Euclidean based normalization method merged with artificial neural network", Fourth International Conference on Computer Science and Convergence Information Technology, (2009), 562-567.
  3. Barniv, R., Anuragh, A., and Leach R., "Predicting the outcome following bankruptcy filing : a three state classification using NN", International Journal of Intelligence System in Accounting, Finance and Management, Vol.6(1997), 177-194. https://doi.org/10.1002/(SICI)1099-1174(199709)6:3<177::AID-ISAF134>3.0.CO;2-D
  4. Berry, M. and Linoff, G., "Data mining techniques for marketing, sales and customer support", Wiley Computer Publishing, 1997.
  5. Chen, W. and Du, Y., "Using neural networks and data mining techniques for the financial distress prediction model", Expert Systems with Applications, Vol.36(2009), 4075-4086. https://doi.org/10.1016/j.eswa.2008.03.020
  6. Chia, W., Holliday, J., and Willett, P., "Effect of data standardization on chemical clustering and similarity searching", Journal of Chemical Information and Modeling, Vol.49 No.2(2009), 155-161.
  7. Cror, K., and Ross, A., "Score normalization in multimodal biometric systems", Pattern Recognition, Vol.38(2005), 2270-2285. https://doi.org/10.1016/j.patcog.2005.01.012
  8. Javanmard, H. and Saleh, F., "The comparison artificial neural networks and multi decimal analysis models for forecasting bankruptcy and financial distress", Proceedings of the Worlds Congress on Engineering, July, 2009.
  9. Jiang, Y., Wang, Y., and Xu, L., "Using genetic algorithms to predict financial performance", IEEE Xplore, 1-4244-099, (2007), 3255-3229.
  10. Jolai, F. and Ghanbari, A., "Integrating data transformation techniques with Hopfield neural networks for solving travelling salesman problem", Expert Systems with Applications, Vol.37, No.7(2010), 5331-5335. https://doi.org/10.1016/j.eswa.2010.01.002
  11. Khashman, A., "Neural networks for credit risk evaluation : Investigation of different neural models and learning schemes", Vol.37, No.9 (2010). 6233-6239 https://doi.org/10.1016/j.eswa.2010.02.101
  12. Kim, D. "Normalization methods for input and output vectors in back-propagation neural networks", International Journal of Computer Mathematics, Vol.71(1999), 161-171. https://doi.org/10.1080/00207169908804800
  13. Kim, K. W., Kim, D., and Jung, H. "Normalization methods on back-propagation for the estimation of drivers' route choice", KSCE Journal of Civil Engineering, Vol.9 No.5(2005), 403-406. https://doi.org/10.1007/BF02830631
  14. Kim, K. and Han, I., "Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index", Expert Systems with Applications, Vol.19(2000), 125-132. https://doi.org/10.1016/S0957-4174(00)00027-0
  15. Kim, M. and Han, I., "The discovery of experts' decision rules from qualitative bankruptcy data using genetic algorithms", Expert Systems with Applications, Vol.25(2003), 637-646. https://doi.org/10.1016/S0957-4174(03)00102-7
  16. Kotsiantis, S., Kanellopoulos, D., and Pintelas, P., "Data preprocessing for supervised learning", Internatinal Journal of Computer Science, Vol.1, No.2(2006), 1306-4428.
  17. Leshno, M., "Neural network prediction analysis: The bankruptcy case", Neural computing, Vol.10, No.2(1996), 125-147.
  18. Liu, C. and Marukawa, K., "Normalization ensemble for handwritten character recognition", IEEE Computer Society, International Conference on Computational Intelligence for Modeling Control and Automation, 0-7695-218, (2004).
  19. Mazzatorta,P. and Benfenati, E., "The importance of scaling in data mining for toxicity prediction", Journal of Chemical Information and Computer Sciences, Vol.42(2002), 1250-1255. https://doi.org/10.1021/ci025520n
  20. Min, S., Lee, J., and Han, I., "Hybrid genetic algorithms and support vector machines for bankruptcy prediction", Expert Systems with Applications, Vol.31(2006), 652-660. https://doi.org/10.1016/j.eswa.2005.09.070
  21. Mitchel, M., "An introduction to genetic algorithms", Cambridge, MA : The MIT Press, 1996.
  22. Moody, J. and Utans, J., "Architecture selection strategies for neural networks : Application to bond rating prediction", Neural Networks in the Capital Markets, (1995).
  23. O'leary, D., "Using neural networks to predict corporate failure", International Journal of Intelligent Systems in Accounting, Finance and Management, Vol.7(1998), 187-197. https://doi.org/10.1002/(SICI)1099-1174(199809)7:3<187::AID-ISAF144>3.0.CO;2-7
  24. Olden, J. and Jackson, D., "Illuminating the "black box" : a randomization approach for understanding variable contribution in artificial networks", Ecological Modeling, Vol.154, No.1-2(2002), 135-150. https://doi.org/10.1016/S0304-3800(02)00064-9
  25. Rahimian, E., Singh, S., and Thammachote, T., "Bankruptcy prediction by neural network", Neural Networks in Finance and Investing : Using Artificial Intelligence to Improve Real-World Performance, Probus, Chicage, IL., (1993), 159-176.
  26. Salchenberger, L., Cinear, E., and Lash, N., "Neural Networks : A new tools for Thrift failure", Decision Science, Vol.23(1992), 899-916. https://doi.org/10.1111/j.1540-5915.1992.tb00425.x
  27. Schaffer, C. and Green, P., "An empirical comparison of variable standardization methods in cluster analysis", Multivariate Behavioral Research, Vol.31, No.2(1996), 149-167. https://doi.org/10.1207/s15327906mbr3102_1
  28. Sen, T., Ghandforoush, P., and Stivason, C., "Improving Prediction Of Neural Networks : A Study Of Two Financial Prediction tasks", Journal of Applied Mathematics and Decision Science, Vol.8, No.4(2004), 219-233.
  29. Shanker, M., Hu, M., and Hung, M., "Effect of data standardization on neural network training", Omega, International Journal of Science, Vol.24 No.4(1996), 385-397.
  30. Sharda, R. and Wilson, R., "Performance comparison issues in neural network experiments for classification problems", Proceedings of the 26th Hawaii International Conference on System Sciences, IEEE Press, 1993.
  31. Shin, K. and Han, I., "Case-based reasoning supported by genetic algorithms for corporate bond rating", Expert Systems with Applications, Vol.23, No.3(2002), 321-328. https://doi.org/10.1016/S0957-4174(02)00051-9
  32. Shin, K. and Lee, T., "A genetic algorithm application in bankruptcy prediction modeling", Expert Systems with Applications, Vol.23, No.3(2002), 321-328 https://doi.org/10.1016/S0957-4174(02)00051-9
  33. Surkan, A. and Singleton, J., "Neural networks for bond rating improved by multiple hidden layers", International Joint Conference on Neural Networks, (1990), 157-162.
  34. Swicegood, P., and Clark, J., "Off-site monitoring for predicting bank under performance : a comparison of neural networks, discriminant analysis and professional human judgement", International Journal in Accounting, Finance and Management, Vol.10(2001), 169-186.
  35. Tam K., "Neural networks models and the prediction of bankruptcy", Omega, Vol.19, No.5(1991), 429-445. https://doi.org/10.1016/0305-0483(91)90060-7
  36. Tsai, C. and Wu, J., "Using neural network ensembles for bankruptcy prediction and credit scoring", Expert Systems with Applications, Vol.34(2008), 2639-2649. https://doi.org/10.1016/j.eswa.2007.05.019
  37. Tsukuda, J. and Baba, S., "Predicting Japanese corporate bankruptcy in terms of finance data using neural network", Computer and Industrial Engineering, Vol.1, No.4(1994), 445-448.
  38. Utans, J. and Moody, J., "Selecting neural network architecture via the prediction risk : Application to corporate bond rating prediction", IEEE Xplore, (1994), 35-41.
  39. Visalakshi, N. and Thagavel, K., "Impact of normalization in distributed k-means clustering", International Journal of Soft Computing, Vol.4, No.4(2009), 168-172.
  40. Wang, H. and Zhang, J., "Analysis of different data standardization form for fuzzy clustering evaluation results' influence", IEEE Xplore, 978-1-4244, (2009), 1-4.
  41. Wilson, R. and Shandra, R., "Bankruptcy prediction using neural networks", Decision Support Systems, Vol.11, No.5(1994), 545-557. https://doi.org/10.1016/0167-9236(94)90024-8
  42. Wu, C., Tzeng, G., Goo, Y., and Fang, W., "A real-valued genetic algorithm to optimize the parameters of support vector machine for predicting bankruptcy", Expert Systems with Applications, Vol.32, No.2(2007), 397-408. https://doi.org/10.1016/j.eswa.2005.12.008
  43. Yim, J. and Mitchell, H., "A comparison of corporate failure models in Australia : Hybrid neural networks, logit models and discriminant analysis", RMIT Working Paper, Vol.10(2002).