1. NCCU Academic Hub
  2. 學術產出
  3. 資訊學院
  4. 學位論文
  5. Item

學術產出-學位論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 以財務比率、共同比分析和公司治理指標預測 上市公司財務危機之基因演算法與支持向量機的計算模型
Applying Genetic Algorithms and Support Vector Machines for Predicting Financial Distresses with Financial Ratios and Features for Common-Size Analysis and Corporate Governance
作者 黃珮雯
Huang, Pei-Wen
貢獻者 劉昭麟
Liu, Chao-Lin
黃珮雯
Huang, Pei-Wen
關鍵詞 財務危機預測
共同比分析
公司治理
基因演算法
支持向量機
Financial Distress Prediction
Common-Size Analysis
Corporate Governance
Genetic Algorithms
Support Vector Machines
日期 2005
上傳時間 17-九月-2009 13:57:07 (UTC+8)
摘要 過去已有許多技術應用來建立預測財務危機的模型，如統計學的多變量分析或是類神經網路等分類技術。這些早期預測財務危機的模型大多以財務比率作為變數。然而歷經安隆（Enron）、世界通訊（WorldCom）等世紀騙局，顯示財務數字計算而成的財務比率有其天生的限制，無法在公司管理階層蓄意虛增盈餘時，及時給予警訊。因此，本論文初步探勘共同比分析、公司治理及傳統的Altman財務比率等研究方法，試圖突破財務比率在財務危機預測問題的限制，選出可能提高財務危機預測的特徵群。接著，我們進一步應用基因演算法篩選質性與非質性的特徵，期望藉由基因演算法裡子代獲得親代間最優基因的交配過程，可以讓子代的適應值最大化，找出最佳組合的特徵群，然後以此特徵群訓練支持向量機預測模型，以提高財務預測效果並降低公眾的損失。實驗結果顯示，共同比分析與公司治理等相關特徵確實能提升預測財務危機模型的預測效果，我們應當用基因演算法嘗試更多質性與非質性的特徵組合，及早預警財務危機公司以降低社會成本。
參考文獻 1 T. Abdelwahed and E. M. Amir. New evolutionary bankruptcy forecasting model based on genetic algorithms and neural networks. Proceedings of the 17th IEEE International Conference on Tools with Artificial Intelligence, pp. 241-245, 2005.
2 E. I. Altman. Financial ratios, discriminant analysis, and the prediction of corporate bankruptcy. Journal of Finance, Vol. 23, pp. 589-609, 1968.
3 E. I. Altman , R. Haldeman and P. Narayanan. Zeta analysis: a new model to identify bankruptcy risk of corporations, Journal of Banking and Finance, Vol. 1, pp. 29-54, 1977.
4 C. C. Chang and C. J. Lin. LIBSVM: A library for support vector machines, 2001. http://www.csie.ntu.edu.tw/~cjlin/libsvm
5 J. R. Coakley and C. E. Brown. Artificial neural networks in accounting and finance: modeling issues. International Journal of Intelligent Systems in Accounting, Finance & Management, Vol. 9, pp. 119-144, 2000.
6 A. Fan and M. Palaniswami. Selecting bankruptcy predictors using a support vector machine approach. Proceedings of the International Joint Conference on Neural Networks, Vol. 6, pp. 354-359, 2000.
7 K. Fanning, K. Cogger, and R. Srivastava. Detection of management fraud: A neural network approach. International Journal of Intelligent Systems in Accounting, Finance & Management, Vol. 4, pp. 113-26, 1995.
8 J. H. Holland. Adaptation in Natural and Artificial Systems. MIT Press, Cambridge, MA, USA, 1992.
9 P.-W. Huang and C.-L. Liu. Exploiting corporate governance and common-size analysis for financial distress detecting models. Proceedings of the 5th International Conference on Computational Intelligence in Economics and Finance, to appear, 2006.
10 S. Johnson, P. Boone, A. Breach, and E. Friedman. Corporate governance in the Asian financial crisis. Journal of Financial Economics, Vol. 58, pp. 141-186, 2000.
11 R. La Porta, F. Lopez-de-Silanes, A. Shleifer, and R. Vishny. Agency problems and dividend policies around the world. Journal of Finance, Vol. 55, pp. 1-33, 2000.
12 T. S. Lee and Y. H. Yeh. Corporate governance and financial distress: evidence from Taiwan. Corporate Governance, Vol. 12, pp. 378-388, 2004.
13 M. L. Nasir, R. I. John, S. C. Bennett, D. M. Russell, and A. Patel. Predicting corporate bankruptcy using artificial neural networks. Journal of Applied Accounting Research, Vol. 5, pp. 30-52, 2000.
14 M. D. Odom and R. Sharda. A neural network model for bankruptcy prediction. International Joint Conference on Neural Networks. Vol. 2, pp. 163-168, 1990.
15 D. E. O’Leary. Using neural networks to predict corporate failure. International Journal of Intelligent Systems in Accounting, Finance & Management, Vol. 7, pp. 187-197, 1998.
16 Z. Pawlak. Rough sets. International Journal of Parallel Programming, Vol. 11, pp. 341-356, 1982.
17 J. R. Quinlan. Introduction of decision trees. Machine Learning, Vol. 1, No. 1, pp. 81-106, 1986.
18 J. R. Quinlan. C4.5: programs for machine learning. Morgan Kaufmann, 1993.
19 Van Rijsbergen. Information Retrieval, 2nd Edition, Butterworth-Heinemann Newton, 1979.
20 S. Salcedo-Sanz, M. Deprado-Cumplido, and M. J. Segovia-Vargas. Feature selection methods involving support vector machines for prediction of insolvency in non-life insurance companies. International Journal of Intelligent Systems in Accounting, Finance & Management, Vol. 12, pp. 261-281, 2004.
21 H. Schilit. Financial shenanigans: how to detect accounting gimmicks & fraud in financial reports. New York: McGraw-Hill, 2002.
22 K. S. Shin, T. S. Lee, and H. J. Kim. An application of support vector machines in bankruptcy prediction model. Expert Systems with Applications, Vol. 28, pp. 127-135, 2005.
23 K. S. Shin and Y. J. Lee. A genetic algorithm application in bankruptcy prediction modeling. Expert Systems with Applications, Vol. 23, pp. 321-328, 2002.
24 I. H. Witten and E. Frank. Data mining: practical machine learning tools and techniques, 2nd Edition, Morgan Kaufmann, San Francisco, 2005.
25 Y. H. Yeh, T. S. Lee and T. Woidtke. Family control and corporate governance: evidence for Taiwan. International Review of Finance, Vol. 2, pp. 21-48, 2001.
26 MATLAB: http://www.mathwork.com
27 TEJ: http://www.tej.com.tw
28 葉銀華、李存修與柯承恩，「公司治理與評等系統」，初刷，商智文化，台灣，民國91年10月
29 湯玲郎與施並洲，「灰關聯分析、類神經網路、案例推理法於財務危機預警模式之應用研究」，中華管理評論，第四卷，第二號，頁25-37，民國90年3月
描述 碩士
國立政治大學
資訊科學學系
93753013
94
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0093753013
資料類型 thesis
dc.contributor.advisor 劉昭麟zh_TW
dc.contributor.advisor Liu, Chao-Linen_US
dc.contributor.author (作者) 黃珮雯zh_TW
dc.contributor.author (作者) Huang, Pei-Wenen_US
dc.creator (作者) 黃珮雯zh_TW
dc.creator (作者) Huang, Pei-Wenen_US
dc.date (日期) 2005en_US
dc.date.accessioned 17-九月-2009 13:57:07 (UTC+8)-
dc.date.available 17-九月-2009 13:57:07 (UTC+8)-
dc.date.issued (上傳時間) 17-九月-2009 13:57:07 (UTC+8)-
dc.identifier (其他 識別碼) G0093753013en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/32653-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學學系zh_TW
dc.description (描述) 93753013zh_TW
dc.description (描述) 94zh_TW
dc.description.abstract (摘要) 過去已有許多技術應用來建立預測財務危機的模型，如統計學的多變量分析或是類神經網路等分類技術。這些早期預測財務危機的模型大多以財務比率作為變數。然而歷經安隆（Enron）、世界通訊（WorldCom）等世紀騙局，顯示財務數字計算而成的財務比率有其天生的限制，無法在公司管理階層蓄意虛增盈餘時，及時給予警訊。因此，本論文初步探勘共同比分析、公司治理及傳統的Altman財務比率等研究方法，試圖突破財務比率在財務危機預測問題的限制，選出可能提高財務危機預測的特徵群。接著，我們進一步應用基因演算法篩選質性與非質性的特徵，期望藉由基因演算法裡子代獲得親代間最優基因的交配過程，可以讓子代的適應值最大化，找出最佳組合的特徵群，然後以此特徵群訓練支持向量機預測模型，以提高財務預測效果並降低公眾的損失。實驗結果顯示，共同比分析與公司治理等相關特徵確實能提升預測財務危機模型的預測效果，我們應當用基因演算法嘗試更多質性與非質性的特徵組合，及早預警財務危機公司以降低社會成本。zh_TW
dc.description.tableofcontents 第一章 概論 1
1.1 研究背景與動機 1
1.2 研究方法 1
1.3 研究成果 2
1.4 論文架構 3
第二章 文獻回顧 4
2.1 會計相關文獻 4
2.1.1 財務比率分析（Financial Ratio Analysis） 4
2.1.2 共同比分析（Common-Size Analysis） 6
2.1.3 公司治理（Corporate Governance） 8
2.2 資訊科學相關文獻 10
2.2.1 倒傳遞網路（Backpropagation Networks） 10
2.2.2 決策樹（Decision Trees） 10
2.2.3 基因演算法（Genetic Algorithms） 11
2.2.4 支持向量機（Support Vector Machines） 12
第三章 研究方法 15
第四章 財務比率、共同比分析和公司治理的特徵群 17
4.1 特徵群 17
4.2 分類器與衡量標準 20
4.2.1 分類器 20
4.2.2 衡量標準 20
4.3 以單季財報為資料單位之實驗 21
4.3.1 資料來源與應用 21
4.3.2 實驗結果與討論 25
4.4 以雙季財報為資料單位之實驗 29
4.4.1 資料來源與應用 29
4.4.2 實驗結果與討論 31
4.5 小結 34
第五章 基因演算法與支持向量機的計算模型 35
5.1 混合指標特徵群 35
5.2 實驗設計 35
5.2.1 資料來源與應用 36
5.2.2 特徵挑選與預測 38
5.2.3 衡量標準 42
5.3 實驗結果與討論 42
5.3.1 三組基因演算法及增益比值法的實驗結果 43
5.3.2 綜合比較三組基因演算法的實驗結果 46
5.4 分析基因演算法實驗的共同特徵 48
5.5 小結 55
第六章 比較其他方法與本論文的計算模型 56
6.1 比較C4.5決策樹與本論文的計算模型 56
6.1.1 實驗設計 57
6.1.2 實驗結果與討論 57
6.2 過去相關研究的準確率 60
6.3 小結 61
第七章 結論 62
參考文獻 65		zh_TW
dc.format.extent 48123 bytes-
dc.format.extent 68422 bytes-
dc.format.extent 84960 bytes-
dc.format.extent 70468 bytes-
dc.format.extent 101413 bytes-
dc.format.extent 185287 bytes-
dc.format.extent 86845 bytes-
dc.format.extent 264167 bytes-
dc.format.extent 295739 bytes-
dc.format.extent 134908 bytes-
dc.format.extent 100703 bytes-
dc.format.extent 58903 bytes-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0093753013en_US
dc.subject (關鍵詞) 財務危機預測zh_TW
dc.subject (關鍵詞) 共同比分析zh_TW
dc.subject (關鍵詞) 公司治理zh_TW
dc.subject (關鍵詞) 基因演算法zh_TW
dc.subject (關鍵詞) 支持向量機zh_TW
dc.subject (關鍵詞) Financial Distress Predictionen_US
dc.subject (關鍵詞) Common-Size Analysisen_US
dc.subject (關鍵詞) Corporate Governanceen_US
dc.subject (關鍵詞) Genetic Algorithmsen_US
dc.subject (關鍵詞) Support Vector Machinesen_US
dc.title (題名) 以財務比率、共同比分析和公司治理指標預測 上市公司財務危機之基因演算法與支持向量機的計算模型zh_TW
dc.title (題名) Applying Genetic Algorithms and Support Vector Machines for Predicting Financial Distresses with Financial Ratios and Features for Common-Size Analysis and Corporate Governanceen_US
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) 1 T. Abdelwahed and E. M. Amir. New evolutionary bankruptcy forecasting model based on genetic algorithms and neural networks. Proceedings of the 17th IEEE International Conference on Tools with Artificial Intelligence, pp. 241-245, 2005.zh_TW
dc.relation.reference (參考文獻) 2 E. I. Altman. Financial ratios, discriminant analysis, and the prediction of corporate bankruptcy. Journal of Finance, Vol. 23, pp. 589-609, 1968.zh_TW
dc.relation.reference (參考文獻) 3 E. I. Altman , R. Haldeman and P. Narayanan. Zeta analysis: a new model to identify bankruptcy risk of corporations, Journal of Banking and Finance, Vol. 1, pp. 29-54, 1977.zh_TW
dc.relation.reference (參考文獻) 4 C. C. Chang and C. J. Lin. LIBSVM: A library for support vector machines, 2001. http://www.csie.ntu.edu.tw/~cjlin/libsvmzh_TW
dc.relation.reference (參考文獻) 5 J. R. Coakley and C. E. Brown. Artificial neural networks in accounting and finance: modeling issues. International Journal of Intelligent Systems in Accounting, Finance & Management, Vol. 9, pp. 119-144, 2000.zh_TW
dc.relation.reference (參考文獻) 6 A. Fan and M. Palaniswami. Selecting bankruptcy predictors using a support vector machine approach. Proceedings of the International Joint Conference on Neural Networks, Vol. 6, pp. 354-359, 2000.zh_TW
dc.relation.reference (參考文獻) 7 K. Fanning, K. Cogger, and R. Srivastava. Detection of management fraud: A neural network approach. International Journal of Intelligent Systems in Accounting, Finance & Management, Vol. 4, pp. 113-26, 1995.zh_TW
dc.relation.reference (參考文獻) 8 J. H. Holland. Adaptation in Natural and Artificial Systems. MIT Press, Cambridge, MA, USA, 1992.zh_TW
dc.relation.reference (參考文獻) 9 P.-W. Huang and C.-L. Liu. Exploiting corporate governance and common-size analysis for financial distress detecting models. Proceedings of the 5th International Conference on Computational Intelligence in Economics and Finance, to appear, 2006.zh_TW
dc.relation.reference (參考文獻) 10 S. Johnson, P. Boone, A. Breach, and E. Friedman. Corporate governance in the Asian financial crisis. Journal of Financial Economics, Vol. 58, pp. 141-186, 2000.zh_TW
dc.relation.reference (參考文獻) 11 R. La Porta, F. Lopez-de-Silanes, A. Shleifer, and R. Vishny. Agency problems and dividend policies around the world. Journal of Finance, Vol. 55, pp. 1-33, 2000.zh_TW
dc.relation.reference (參考文獻) 12 T. S. Lee and Y. H. Yeh. Corporate governance and financial distress: evidence from Taiwan. Corporate Governance, Vol. 12, pp. 378-388, 2004.zh_TW
dc.relation.reference (參考文獻) 13 M. L. Nasir, R. I. John, S. C. Bennett, D. M. Russell, and A. Patel. Predicting corporate bankruptcy using artificial neural networks. Journal of Applied Accounting Research, Vol. 5, pp. 30-52, 2000.zh_TW
dc.relation.reference (參考文獻) 14 M. D. Odom and R. Sharda. A neural network model for bankruptcy prediction. International Joint Conference on Neural Networks. Vol. 2, pp. 163-168, 1990.zh_TW
dc.relation.reference (參考文獻) 15 D. E. O’Leary. Using neural networks to predict corporate failure. International Journal of Intelligent Systems in Accounting, Finance & Management, Vol. 7, pp. 187-197, 1998.zh_TW
dc.relation.reference (參考文獻) 16 Z. Pawlak. Rough sets. International Journal of Parallel Programming, Vol. 11, pp. 341-356, 1982.zh_TW
dc.relation.reference (參考文獻) 17 J. R. Quinlan. Introduction of decision trees. Machine Learning, Vol. 1, No. 1, pp. 81-106, 1986.zh_TW
dc.relation.reference (參考文獻) 18 J. R. Quinlan. C4.5: programs for machine learning. Morgan Kaufmann, 1993.zh_TW
dc.relation.reference (參考文獻) 19 Van Rijsbergen. Information Retrieval, 2nd Edition, Butterworth-Heinemann Newton, 1979.zh_TW
dc.relation.reference (參考文獻) 20 S. Salcedo-Sanz, M. Deprado-Cumplido, and M. J. Segovia-Vargas. Feature selection methods involving support vector machines for prediction of insolvency in non-life insurance companies. International Journal of Intelligent Systems in Accounting, Finance & Management, Vol. 12, pp. 261-281, 2004.zh_TW
dc.relation.reference (參考文獻) 21 H. Schilit. Financial shenanigans: how to detect accounting gimmicks & fraud in financial reports. New York: McGraw-Hill, 2002.zh_TW
dc.relation.reference (參考文獻) 22 K. S. Shin, T. S. Lee, and H. J. Kim. An application of support vector machines in bankruptcy prediction model. Expert Systems with Applications, Vol. 28, pp. 127-135, 2005.zh_TW
dc.relation.reference (參考文獻) 23 K. S. Shin and Y. J. Lee. A genetic algorithm application in bankruptcy prediction modeling. Expert Systems with Applications, Vol. 23, pp. 321-328, 2002.zh_TW
dc.relation.reference (參考文獻) 24 I. H. Witten and E. Frank. Data mining: practical machine learning tools and techniques, 2nd Edition, Morgan Kaufmann, San Francisco, 2005.zh_TW
dc.relation.reference (參考文獻) 25 Y. H. Yeh, T. S. Lee and T. Woidtke. Family control and corporate governance: evidence for Taiwan. International Review of Finance, Vol. 2, pp. 21-48, 2001.zh_TW
dc.relation.reference (參考文獻) 26 MATLAB: http://www.mathwork.comzh_TW
dc.relation.reference (參考文獻) 27 TEJ: http://www.tej.com.twzh_TW
dc.relation.reference (參考文獻) 28 葉銀華、李存修與柯承恩，「公司治理與評等系統」，初刷，商智文化，台灣，民國91年10月zh_TW
dc.relation.reference (參考文獻) 29 湯玲郎與施並洲，「灰關聯分析、類神經網路、案例推理法於財務危機預警模式之應用研究」，中華管理評論，第四卷，第二號，頁25-37，民國90年3月zh_TW