Bankruptcy Prediction using Fuzzy Neural Networks

퍼지신경망을 이용한 기업부도예측

  • 김경재 (한국과학기술원 테크노경영연구소) ;
  • 한인구 (한국과학기술원 테크노경영대학원)
  • Published : 2001.06.01

Abstract

This study proposes bankruptcy prediction model using fuzzy neural networks. Neural networks offer preeminent learning ability but they are often confronted with the inconsistent and unpredictable performance for noisy financial data. The existence of continuous data and large amounts of records may pose a challenging task to explicit concepts extraction from the raw data due to the huge data space determined by continuous input variables. The attempt to solve this problem is to transform each input variable in a way which may make it easier fur neural network to develop a predictive relationship. One of the methods selected for this is to map each continuous input variable to a series of overlapping fuzzy sets. Appropriately transforming each of the inputs into overlapping fuzzy membership sets provides an isomorphic mapping of the data to properly constructed membership values, and as such, no information is lost. In addition, it is easier far neural network to identify and model high-order interactions when the data is transformed in this way. Experimental results show that fuzzy neural network outperforms conventional neural network for the prediction of corporate bankruptcy.

본 연구에서는 퍼지신경망을 이용한 기업부실예측모형을 제안한다. 신경망은 탁월한 학습능력을 가진 것으로 알려져 있으나, 잡음이 심한 재무자료에 대해서는 종종 일관되지 못하고 기대에 미치지 못하는 예측성과를 보인다. 이는 연속형의 형태를 지닌 독립변수와 과다한 양의 원자료로부터 예측에 필요한 일정한 패턴을 찾기가 어렵기 때문이다. 이러한 문제점은 예측모형에서의 독립변수와 종속변수간의 인과관계를 신경망이 용이하게 찾아낼 수 있도록 독립변수의 형태를 변환함으로써 해결한 수 있다. 이러한 해결방법의 하나는 기존 신경망에 퍼지집합의 개념을 적용하여 신경망 학습에 사용될 자료를 퍼지화하고 이를 신경망에 학습시키는 것이다 입력자료를 퍼지화 함으로써 정보의 손실 없이도 신경망이 자료 내의 복잡한 관계를 용이하게 학습하는 것이 가능하다. 본 연구에서 제안된 퍼지신경망을 기업부도예측에 적용한 결과, 퍼지신경망이 기존의 신경망보다 우월한 예측성과를 나타내었다.

Keywords

References

  1. The Journal of Finance v.23 no.4 Financial ratios, discriminant analysis and the prediction of corporate bankruptcy Altman, E.
  2. Corporate Financial Distress - A Complete Guide to Predicting, Avoiding and Dealing with Bankruptcy Altman, E.
  3. Proceedings of the International Joint Conference on Artificial Intelligence Hybrid learning using genetic algorithms and decision trees for pattern classification Bala, J.;J. Huang;H. Vafaie;K. De Jong;H. Wechsler
  4. Pattern Recognition Letters v.19 no.11 Unsupervised feature selection using a neuro-fuzzy approach Basak, J.;R. K. De;S. K. Pal
  5. Applied Financial Economics v.8 no.3 Extreme events from the return-volume process: a discretization approach for complexity reduction Buhlmann, P.
  6. Annals of Operations Research v.75 A stock selection DSS combining AI and technical analysis Chou, S. T.;H. Hsu;C. Yang;F. Lai
  7. International Journal of Intelligent Systems in Accounting, Finance and Management v.9 no.2 Artificial neural networks in accounting and finance: Modeling issues Coakley, J. R.;C. E. Brown
  8. Mathematics of Control, Signals, and Systems v.2 Approximation by superpositions of a sigmoid function Cybenko, G.
  9. Intelligent Data Analysis: An International Journal v.1 no.3 Feature selection methods for classifications Dash, M.;H. Liu
  10. IEEE Transactions on Neural Networks v.4 no.1 Backpropagation neural nets with one and two hidden layers de Villiers, J.;E. Garnard
  11. Proceedings of the Twelfth International Conference on Machine Learning Supervised and unsupervised discretization of continuous features Dougherty, J.;R. Kohavi;M. Sahami;Prieditis, A.(ed.);S. Russell(ed.)
  12. Proceedings of the 13th International Joint Conference on Artificial Intelligence Multi-interval discretization of continuous-valued attributes for classification learning Fayyad, U. M.;K. B. Irani
  13. International Journal of Intelligent Systems in Accounting, Finance and Management v.7 no.2 Comparative performance of backpropagation networks designed by genetic algorithms and heuristics Hansen, J. V.
  14. Computational Intelligence v.15 no.3 Time series prediction with genetic-algorithm designed neural networks: An empirical comparison with modern statistical models Hansen, J. V.;J. B. McDonald;R. D. Nelson
  15. Statistical Methods for Business Economics Harnett, D. L.;A. K. Soni
  16. Expert Systems with Applications v.11 no.4 Integration of case-based forecasting, neural network, and discriminant analysis for bankruptcy prediction Jo, H.;I. Han
  17. Expert Systems with Applications v.13 no.2 Bankruptcy prediction using vase-based reasoning, neural networks, and discriminant analysis Jo, H.;I. Han;H. Lee
  18. Neorocomputing v.21 Predicting bankruptcies with the self-organizing map Kiviluoto, K.
  19. Expert Systems with Applications v.19 no.2 Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index Kim, K.;I. Han
  20. Advanced Technology for Developers Hybrid fuzzy encodings for improved backpropagation performance Klimasauskas, C. C.
  21. Intelligent Hybrid Systems Using fuzzy pre-processing with neural networks for chemical process diagnostic problems Klimasauskas, C. C.;Goonatilake, S.(ed.);S. Khebbal(ed.)
  22. Proceedings of the European Symposium on Intelligent Techniques A Bayesian approach to discretization Kontkanen, P.;P. Myllymaki;T. Silander;H. Tirri
  23. Technical Report UMIACS-TR-96-27 and CS-TR-3625 Noisy time series prediction using symbolic representation and recurrent neural network grammatical inference Lawrence, S.;A. C. Tsoi;C. L. Giles
  24. Knowledge-Based Systems v.9 no.1 Dimensionality reduction via discretization Liu, H.;R. Setiono
  25. IEEE Transactions on Neural Networks v.5 no.1 Genetic evolution of the topology and weight distribution of neural networks Maniezzo, V.
  26. Expert Systems with Applications v.15 no.3;4 An initial comparison of a fuzzy neural classifier and a decision tree based classifier Martens, J.;G. Wets;J. Vanthienen;C. Mues
  27. Practical Neural Network Recipes in C++ Masters, T.
  28. Intelligent Automation and Soft Computing v.5 no.3 Optimization of neural network topologies using genetic algorithm Nissinen, A. S.;H. N. Koivo;H. Koivisto
  29. Proceedings of the IEEE International Conference on Neural Networks A neural network model for bankruptcy prediction Odom, M. D.;R. Sharda
  30. Journal of Accounting Research v.18 no.1 Financial ratios and probabilistic prediction of bankruptcy Ohlson, J.
  31. Proceedings of the IEEE/IAFE A neural network that explains as well as predicts financial market behavior Ornes, C.;J. Sklanski
  32. Management Science v.44 no.3 Using feature construction to improve the performance of neural networks Piramuthu, S.;H. Ragavan;M. J. Shaw
  33. Advances in Intelligent Data Analysis Forming categories in exploratory data analysis and data mining Scott, P. D.;K. M. Williams;K. M. Ho
  34. Decision Support Systems v.17 Self organizing neural networks for financial diagnosis Serrano-Cinca, C.
  35. Management Science v.38 Managerial applications of neural networks: The case of bank failure predictions Tam, K. Y.;M. Y. Kiang
  36. Artificial Intelligence Review v.11 no.1-5 Discretization in lazy learning algorithms Ting, K. A.
  37. Decision Support Systems v.23 no.2 Forecasting S&P 500 stock index futures with a hybrid AI system Tsaih, R.;Y. Hsu;C. C. Lai
  38. IEEE Intelligent Systems and Their Applications v.13 no.2 Feature space transformation using genetic algorithms Vafaie, H.;K. De Jong
  39. Expert Systems with Applications v.17 no.1 Neural networks in business: a survey of applications Vellido, A.;P. J. G. Lisboa;J. Vaughan
  40. Proceedings of the 28th Symposium on the Interface A genetic algorithm for best subset selection in linear regression Wallet, B. C.;D. J. Marchette;J. L. Solka;E. J. Wegman
  41. Journal of Microcomputer Applications v.18 Refining a neural network credit application vetting system with a genetic algorithm Williamson, A. G.
  42. Decision Support Systems v.11 Bankruptcy prediction using neural networks Wilson, R. L.;R. Sharda
  43. IEEE Intelligent Systems and Their Applications v.13 no.2 Feature subset selection using a genetic algorithm Yang, J.;V. Honavar
  44. Journal of Business Research v.44 Probabilistic neural networks in bankruptcy prediction Yang, Z. R.;M. B. Platt;H. D. Platt