臺灣博碩士論文加值系統

以往有關財務危機之預警模式，大多採用傳統統計方法如區別分析建構模式，其財務資料是否符合假設條件實為一大問題，所以本研究試圖透過非線性的基因演算法、類神經網路來建構預警模式；另外，有鑒於預警模式本身無法萃取影響企業失敗關鍵性指標及參考數值，所以本研究首先使用決策樹的技術來萃取企業失敗的關鍵性指標及其參考數值，據此，本文建立的的研究目的如下：
一、透過基因演算法的強大搜尋能力篩選出影響企業失敗的染色體。
二、建構類神經網路與傳統區別分析之財務預警模式，並比較模式間在企業失敗發生前三年的預警能力。
三、透過決策樹萃取出影響企業失敗的關鍵解釋指標及其數值，以提供投資大眾及相關機構隨時專注於關鍵性財務指標的變化。
本研究所採用的基因演算法其最大的特色便是在於它的巨量平行的最佳化搜尋能力，經由實證結果顯示：
一、透過基因演算法篩選影響企業失敗的基因組合（染色體），當基因演算至第六百代時，演化出最佳染色體組合為營業利益率、每股營業額、稅前純益/實收資本、每股淨值(A)、每股淨值(B)、內部保留比率、現金流量允當變動率、利息保障倍數、固定資產週轉率、營業費用率。
二、由實證的結果得出，採用以基因演算法萃取出的解釋變數所建構之類神經網路預警模式及區別分析對於樣本企業有極佳的預測力(前三年平均：0.9500＞0.9055)。而危機前一年類神經網路的擊中率雖然等於區別分析法之擊中率(0.9667)，而危機前二年及前三年之擊中率卻高於區別分析法(0.9500>0.9166；0.9333>0.8333)，顯示類神經網路預警模式較區別分析更能早期偵測出失敗企業。
三、決策樹的結果並未能將成功及失敗企業的樣本群完全分開；使用內部保留比率進行分裂時，擊中的機率達88﹪，而同時使用企業內部保留比率及營業利益率進行分裂時，擊中的機率更高達97.33﹪。

In the past, the pre-warning models for Financial Crisis are usually established based on traditional statistical methods such as Discriminant Analysis. However, it is often questionable whether the financial data satisfies the assumptions of such models. Therefore, this study investigates the construction of pre-warning model through nonlinear methods such as Genetic Algorithm and Neural Network. In additional, since the reference value for the key indicator that influences business failure most cannot be extracted from the pre-warning model, this study starts with using Decision Tree technique to extract this reference value. Based upon this, the objectives of this thesis include the following:
1.Identify the chromosome that influences business failure most through Genetic Algorithm’s strong searching capability.
2.Construct financial pre-warning models from Neural Network and traditional Discriminant Analysis techniques, and evaluate their pre-warning performance by comparing the ability to predict business failure three years before its occurrence.
3.Extract the reference value and the key descriptive indicator that influences business failure most through Decision Tree technique, thus enabling the investing public and associated authority to constantly monitor the key financial factors.
The main characteristic of the Genetic Algorithm used in this study is its massive parallel optimizing ability. The analyses on the actual data show that:
1.Identify the Genetic component (chromosome) that influences business failure most through Genetic Algorithm: after 500 generations, the optimal chromosome combinations are Operating Income Ratio, Sales per Share, Earnings before Interest/Equity, Net Present Value per Stock (A), Net Present Value per Stock (B), Retained Profit Ratio, Cash Flow Adequacy Ratio, Times Interest Earned, Fixed Asset Turnover Ratio, and Operating Expense Ratio.
2.By employing the key indicators obtained from Genetic Algorithm, both Neural Network model and Discriminant Analysis model can accurately predict business failure (on average, for three-year ago prediction, hit ratio: 0.9500 compared with 0.9055). The hit ratios for both models are the same (0.9667) for one-year ago prediction. However, the hit ratios for two- and three-year ago predictions are higher for Neural Network model (0.9500 and 0.9333 compared with 0.9166 and 0.8333). This indicates that Neural Network pre-warning model has higher probability to successfully predict business failure earlier.
3.The Decision Tree cannot effectively distinguish the samples of successful and failure business. The following results are observed. When the Retained Profit Ratio of a business is larger than 0.9931, the business failure rate is about 88%. When the Retained Profit Ratio is larger than 0.9931 and Operating Income Ratio is lower than 0.0098, the business failure rate is as high as 97.33%.

謝辭 I
中文論文提要 II
英文論文提要 III
目錄 V
表次 VII
圖次 VIII
第壹章 緒論 1
第一節 研究動機 1
第二節 研究目的 3
第三節 研究架構 5
第貳章 相關理論基礎與文獻探討 7
第一節 相關理論對企業經營失敗之定義 7
第二節 實證文獻探討 10
第三節 探討文獻之意涵與對本研究之影響 17
第參章 研究方法 18
第一節 研究流程 18
第二節 研究範圍 19
第三節 變數的操作型定義 20
第四節 樣本的選取 32
第五節 基因演算法 34
第六節 區別分析 41
第七節 類神經網路 43
第八節 決策樹 47
第肆章 實證結果與分析 54
第一節 資料的初步分析 54
第二節 基因演算法萃取變數 55
第三節 類神經及傳統區別分析實證結果比較 56
第四節 決策樹分類結果 62
第五節 研究發現 63
第伍章 結論及建議 65
第一節 研究結論 65
第二節 研究貢獻 66
第三節 後續研究建議 67
第四節 研究限制 68
參考文獻 69
附錄一 自變數代號財務比率計算公式 74
附錄二 失敗樣本企業的敘述統計量 76
附錄三 成功樣本企業的敘述統計量 79
作者簡歷 82

一、中文部分
1. 王俊傑，「財務危機預警模式－以現金流量觀點」，國立台北大學企業管理研究所未出版碩士論文，2000。
2. 古永嘉、賴以建、許志鈞，「基因演算法、類神經網路及決策樹於財務危機預警模式之應用研究」，北商學術論壇研討會，第一屆，頁194-196，2002。
3. 古永嘉譯，企業研究方法，華泰書局，第五版，1996。
4. 何太山，「運用區別分析建立商業放款信用評分制度」，國立政治大學企業管理研究所碩士論文，1977。
5. 李洪慧，「動態化財務預警模式之研究-以證券經濟商為例」，東吳大學企管研究所未出版之碩士論文，1997。
6. 林伯峰，「上市公司於上市前、後之財務特性變化與財務困難之研究」，交通大學管理科學研究所未出版之碩士論文，1993。
7. 施並洲，「類神經網路、案例推理法、灰色關連分析於財務危機之應用」，國立中央大學工業管理研究所未出版碩士論文，1999。
8. 洪啟智，「集團企業財務危機之預警研究」，中央大學財務管理研究所未出版碩士論文，1998。
9. 張志光，「台灣上市公司企業危機探討與預警之研究」，南華大學亞洲太平洋研究所，2000。
10. 張智欽，「財務比率、區別分析與台灣股票上市公司升降類之研究」，成功大學企管研究所未出版之碩士論文，1994。
11. 程郁斌，「東亞國家金融危機預警系統之研究」，國立台灣大學國家發展研究所，2001。
12. 黃焜煌、卓統佑，「模糊評等趨勢對台灣上市電子公司財務危機的預測」，朝陽學報，第五期，頁241-259，1998。
13. 楊宗儒，「運用財務比率建立股票投資績效評估模式之研究」，淡江大學管理科學研究所未出版碩士論文，1987。
14. 趙偉勝，「以狀態空間模型整合基因演算法建立股市預測模型」，國立台北大學企業管理研究所未出版碩士論文，2000。
15. 潘玉葉，「台灣股票上市公司財務危機預警分析」，淡江大學管理科學研究所未出版博士論文，1990。
16. 謝國義，「決策樹形成過程中計算複雜度之研究改善」，成功大學工業管理研究所未出版碩士論文，1998。
二、英文部分
1. Altman, E. I., “Financial Ratios, Discriminate Analysis and the Predictions of Corporate Bankruptcy,” Journal of Finance, September, 1968, pp.589-609.
2. Argenti, John, “Corporate Collapse--the Causes and symptoms,” London: McGraw-Hill, 1976.
3. Beaver, William H., “Financial Ratio as Predictors of Failure,” Empirical Research in Accounting: Selected Study, Supplement to Journal of Accounting Research, 1966,71-111.
4. Berry & Linoff， “Data Mining Techniques: for marketing, sales, and customer support”，John Wiley & Sons, Inc,1997。
5. Blum, M.,“Failing Company Discriminant Analysis,” Journal of Accounting Research, Spring, 1974, pp.1-25.
6. Breiman, L.,Friedman,J.H.,Olshen,R.A.and Stone,C.J., “Classification and Regression Trees” 1984.
7. Breiman, L.,Friedman,J.H.,Olshen,R.A.and Stone,C.J., “Classification and Regression Trees”.
8. Coats, P.K. & Fant, L.F., “Recognizing financial distress using a Neural networktool”, Financial management , Auturm, ,1993, 142-155.
9. Cooper, D. R. and Emory, C. W., “Business Research Method”, Dryden: Orlando, 1995.
10. Deakin, E.B., 1972, “A Discriminant Analysis of Predictors of Business Failure”, Journal of Accounting Research, 10, 167-179.
11. Desai, V. S., Crook, J.N., and Overstreet. G. A., “A Comparison of Neural Networks and Linear Scoring Models in the Credit Environment,” European Journal of Operational Research, vol.95, pp. 24-37, 1996.
12. Fish, K.E., J.H. Barnes, and M.W. Aiken, “Artificial neural networks: a new methodology for industrial market segmentation,” Industrial Marketing Management, Vol.24, pp.431-438, 1995.
13. Freeman, J. A. and Skapura, D. M., “Neural Networks Algorithms, Applications, and Programming Techniques”, Addison-Wesley Publishing Company, New York, NY, 1992.
14. Goldberg, D. E.,” Genetic Algorithms in Search, Optimization and Machine Learning”, Reading, MA: Addison-Wesley, 1989.
15. Holland, J. H., Adaptation in Natural and Artificial Systems:”An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence”, Cambridge: MIT Press, 1992.
16. Holland, J. H., and J. H. Miller, “Artificial Adaptive Agents in economic Theory.” American Economic Review, 18, pp.365-370, 1991.
17. Kim, S.H. and Lee, D.H. and Ahn, B.S.,” A conjoint model for Internet shopping malls using customer’s purchasing data”, Expert System with Applications, Vol. 19, pp.59-66, 2000.
18. Laitinen, E.K. and T. Laitinen, “Cash Management Behavior And Failure Prediction”, Journal of Business Finance Accounting, Sept/Oct1998, pp.613-630.
19. Lee, G., Sung, T. K. and Chang, N., “Dynamics of modeling in data mining: interpretive approach to bankruptcy prediction,” Journal of Management Information Systems, Vol. 16, No. 1, pp. 63-85,1999.
20. Lee, H., Jo, H. and Han, I. “ Bankruptcy prediction using case-based reasoning, neural networks, and discriminant analysis,” Expert Systems With Applications, Vol. 13, No. 2 (), pp. 97-108,1997
21. Martin.D,“Early Warning of Bank Failure”,The Journal of Banking and Finance, ,pp.249-276,1977.
22. Odom, J.A., and R.Sharda, “A Neural Network Model for Bankruptcy Prediction”, Ieee Inns Ijcnn,12, 163-168 ,1990.
23. Ohlson.J.A.,“Financial Ratio And Probabilistic Prediction Of Bankruptcy”,Journal Of Accountuig Research,Spring,pp.109-131,1980.
24. Rumelhart, E., Hinton, G. E. and Williams, R. J., “Learning internal representationsby error propagation in parallel distributed processing”, MIT Press: Cambridge, pp. 318-362,1985.
25. Sinkey. J. F, “A Multivariate Statistical Analysis of the Character Problem Banks”, Journal of Finance, March, pp.21-3, 1975.
26. Sung, T.K., Chang, N., Lee, G. “Dynamics of modeling in data mining; interpretive approach to bankruptcy prediction,” Journal of Management Information Systems, Vol. 16, No. 1, pp. 63-85,1999.
27. Tam, K.Y. and Kiang, M.Y., ”Managerial Applications of NeutralNetworks: The Case of Bank Failure Predictions”, Management Science, Vol.38, No.7, pp.926-947, 1992.
28. Trevino, L. J., and Daniels, J. D., “FDI theory and foreign direct investment in theUnited States: a comparison of investors and non-investors”, International Business Review, Vol.4, No. 2, pp. 177-194,1995.
29. Varetto,“Genetic Algorithms Applications in the Analysis of Insolvency Risk”,The Journal of Banking and Finance, ,pp.1421-1439,1998.
30. Vellido, A., Lisboa, P. J. G. and Vaughan, J., “Neural networks in business: asurvey of applications (1992-1998)”, Expert Systems With Applications, Vol. 17, pp. 51-70,1999.
31. Zhang, G., Patuwo, B. E. and Hu, M. Y., “Forecasting with artificial neural networks: the state of the art,” International Journal of Forecasting, Vol. 14, No. 1, pp. 35-62,1998.