應用基於改良式調和搜尋之支援向量分類法於企業危機預測

Applying Improved Harmony Search-based Support Vector Classification to Business Failure Prediction

10.6459/JCM.201103_8(1).0007

陳明華(M. H. Chen)

支援向量機 ； 改良調和搜尋法 ； 主成份分析 ； 企業危機預測 ； Support Vector Machine ； Improved Harmony Search ； Principle Component Analysis ； Business Failure Prediction

危機管理學刊

8卷1期（2011 / 03 / 01）

63 - 74

繁體中文

本研究使用支援向量機(Support Vector Machine, SVM)模型，來識別並預測企業危機(Business Failure Prediction, BFP)問題。因進行支援向量分類模型訓練時，存在會影響SVM分類正確率的待訂參數，傳統上大都使用格點搜尋或基因演算法，本研究使用一新的最佳化搜尋法，稱改良式調和搜尋(Improved Harmony Search, IHS)演算法，來決定支援向量分類模型的參數，使支援向量機有較佳的分類正確率。並使用主成份分析(Principle Component Analysis, PCA)對自變數作因次縮減，混合模型稱PCA-SVMIHS，並與傳統前饋多層感知器網路(FMPN)模型做比較。本研究樣本是以1996至2005年間於中國上海與深圳掛牌上市公司，共884家，其中268家危機公司與616家正常公司。所得結果顯示，PCA-SVMIHS模型預測正確率優於FMPN模型，故本研究主要貢獻在提供一較佳之PCA-SVMIHS模型，可作爲企業危機預測之另一可行模型。

In this paper, the support vector machine is combined with improved harmony search (IHS) and principle component analysis (PCA), by which the dimensionalities of independent variables are condensed, to construct a classification model for business failure prediction (BFP), so called PCA-SVMIHS model. The sample in this study includes 884 Chinese companies listed in Shanghai Stock Exchange or in Shenzhen Stock Exchange during 1996 to 2005, which contains 268 failure companies and 616 health companies. In comparison with the conventional feedforward multilayer perceptron network (FMPN) model, the proposed PCA-SVMIHS model performs better not only results in a higher correct rate for predicting the failure of company, but also produce a higher AUC value. This empirical result shows that the PCA-SVMIHS model is superior to the FMPN model as an alternative to predict business failure.

1. Shlens, J. (2009). A Tutorial on Principle Component Analysis, Unpublished,version 3.01.
2. Altman, E. I.(1968).Financial ratios discriminant analysis and the prediction of corporate bankruptcy.Journal of Finance,23(4),589-609.
3. Bishop, C. M.(1995).Neural Networks for Pattern Recognition.Oxford:Oxford University Press.
4. Boser, B. E.,Guyon, I. M.,Vapnik,V. N.(1992).A training algorithm for Optimal margin classifiers.Proceedings of the Fifth Annual Workshop on Computational Learning Theory
5. Bryant, S. M.(1997).A case-based reasoning approach to bankruptcy prediction modeling, Intelligent Systems in Accounting.Finance and Management,6,195-214.
6. Burges, C. J. C.(1998).A tutorial on support vector machines for pattern recognition.Data Mining and Knowledge Discovery,2(2),955-974.
7. Fawcett, T.(2006).An introduction to ROC analysis.Pattern Recognition Letters,27,861-874.
8. Fletcher, R.(1987).Practical methods of optimization.John Wiley and Sons, Inc..
9. Geem, Z. W.,Kim, J. H.,Loganathan,G. V.(2001).A new heuristic optimization algorithm: harmony search.Simulation,76(2),60-68.
10. Gunn, S. R.(1998).Technical ReportTechnical Report,University of Southampton.
11. Lee, K. C.,Han, I.,Kwon, Y.(1996).Hybrid neural network models for bankruptcy predictions.Decision Support Systems,18,63-72.
12. Leshno, M.,Spector, Y.(1996).Neural network prediction analysis: the bankruptcy case.Neurocomputing,10,125-147.
13. Li, H.,Sun, J.(2009).Gaussian Case-based reasoning for business failure prediction with empirical data in China.Information Sciences,179,89-108.
14. Lin, F. Y.,McClean, S.(2001).A data mining approach to the prediction of corporate failure.Knowledge-Based Systems,14,189-195.
15. Lin, H. T.,Lin, C. J.(2003).Technical reportTechnical report,Department of Computer Science & Information Engineering, National Taiwan University.
16. Lincoln, M.(1984).An empirical study of the usefulness of accounting ratios to describe levels of insolvency risk.Journal of Banking and Finance,8,321-340.
17. Mahdavi, M.,Fesanghary, M.,Damangir, E.(2007).An Improved Harmony Search Algorithm for Solving Optimization Problems.Applied Mathematics and Computation,188(2),1567-1579.
18. Moller, M. F.(1993).A scaled conjugate gradient algorithm for fast supervised learning.Neural Networks,6,525-533.
19. Odom, M.,Sharda, R.(1990).A neural networks model for bankruptcy prediction.Proceedings of International Joint Conference on Neural Networks,SanDiego, CA:
20. Rafiq, M. Y.,Bugmann, G.,Easterbrook, D. J.(2001).Neural network design for engineering applications.J. Comput. Struct,79,1541-1552.
21. Salchenberger, L.,Mine, C.,Lash, N.(1992).Neural networks: a tool for predicting thrift failures.Decision Sciences,23,899-916.
22. Schlköpf, B.,Burges, C. J. C.,Smola, A. J.(1999).Advances in kernel methods-support vector learning.Cambridge, MA:
23. Svozil, D.,Kvasnicka, V.,Pospichal, J.(1997).Introduction to multilayer feed-forward neural networks.J. Chemometrics Intell. Lab. Syst,39,43-62.
24. Tam, K. Y.(1991).Neural network models and the prediction of bank bankruptcy.Omega,19(5),429-445.
25. Tam, K. Y.,Kiang, M.(1992).Managerial applications of neural networks: the case of bank failure predictions.Management Science,38(7),926-947.
26. Tsai, C. F.,Wu, J. W.(2008).Using neural network ensembles for bankruptcy prediction and credit scoring.Expert Systems with Applications,34(4),2639-2649.
27. Wilson, R. L.,Sharda, R.(1994).Bankruptcy prediction using neural networks.Decision Support Systems,11,545-557.
28. 陳俊佑(2007)。中國大陸上市公司財務危機事件之探討。貨幣觀測與信用評等，64，51-64。