面對瞬息萬變及高度競爭的經濟環境，企業經營績效之良莠受到外在景氣循
環及自身營運策略的影響甚鉅，若沒有做好財務風險的控管，或經理階層錯誤的
決策、不當的使用資金等，都可能導致企業發生經營不善、週轉不靈，甚至財務
危機的發生。而公司的經營不善，影響的不只公司的員工和股東的權益，還會造
成債權人和一般投資大眾的損失，上下游的企業也可能受到衝擊。如果能在企業
發生財務危機前偵測出危機的發生，或許能使公司及早做出應對措施，避免狀況
持續惡化。
本研究採用 2001 年至 2018 年間臺灣上市、上櫃曾發生過財務危機的公司和
未發生財務危機的公司，產生 1：1 及 1：2 兩組樣本集合，並選取事件發生前一
年及前兩年之財務比率年資料作為建構危機預警模型的觀察值。接著利用羅吉斯
迴歸、倒傳遞類神經網路、支撐向量機、決策樹和隨機森林等五種方法建立預測
模型。研究結果發現，在兩組樣本中，無論是 5-fold cross validation 之平均準確率或 AUROC 之百分比，隨機森林之表現皆優於其他模型。

In such fast-changing and highly competitive economic environment, company’s business performance is greatly affected by the external business cycle and its own operating strategies. Without proper risk management or making wrong decisions, companies may suffer poor turnover or even financial crisis. Not only does it affect the
rights and interests of employees and shareholders, but also cause the losses to creditors, upstream and downstream companies. If we can detect the occurrence of the crisis beforehand, it may enable the company to take early actions to avoid continued deterioration of the situation.
In this study, we adopt data of listed companies and OTC companies in Taiwan from 2001 to 2018, and generate 1:1 and 1:2 sample sets of distressed to non-distressed companies. Our observations are collected from the yearly financial report one year and two years ahead of the crisis occurrence date. Then, we apply logistic regression, back
propagation neural network, support vector machine, decision tree and random forest to build prediction models. The results show that whether compared by average accuracy of 5-fold cross validation or the percentage of AUROC, random forest outperforms all the other models in both sample sets.

1.Beaver, W. H., 1966, “Financial ratio as predictors of failure. Empirical research in accounting: selected study”, Supplement to Journal of Accounting Research, 4, 71-111.
2.Altman, E. I., 1968, “Financial ratios, discriminant analysis and the prediction of corporate bankruptcy”, The Journal of Finance, 23(4), 589-609.
3.Ohlson, J. A., 1980, “Financial Ratios and the Probabilistic Prediction of Bankruptcy”, Journal of Accounting Research, 18(1), 109-131.
4.Platt, H. D. and Platt, M. B., 1990, “Development of a Class of Stable Predictive Variable the Case of Bankruptcy Prediction”, Journal of Business Finance & Accounting, 17(1), 31-51.
5.Ligang Zhou, 2013, “Performance of corporate bankruptcy prediction models on imbalanced dataset: The effect of sampling methods”, Knowledge-Based Systems, 4, 16-25.
6.Berg, D., 2007, “Bankruptcy prediction by generalized additive models”, Applied Stochastic Models in Business and Industry, 23(2), 129-143.
7.E. Alfaro, N. García, M. Gámez, and D. Elizondo, 2008, “Bankruptcy forecasting: an empirical comparison of Adaboost and neural networks”, Decision Support Systems, 45, 110-122.
8.Zmijewski, M. E., 1984, “Methodological Issues Related to the Estimation of Financial Distress Prediction Models”, Journal of Accounting Research, 22, 59-82.
9.Odom, M. D., & Sharda, R., 1990, “A neural network model for bankruptcy prediction”, Proceedings of the IEEE International Joint Conference on Neural Network, 2, 163-168.
10.Deakin, E. B., 1972, "A discriminant analysis of predictors of business failure”, Journal of Accounting Research, 10(1), 167-179.
11.Blum, M., 1974, “Failure company discriminant analysis”, Journal of Accounting Research, 1-25.
12.Forster, G., 1977, “Quarterly Accounting Date: Time-Series Properties and Predictive Ability Results”, The Accounting Review, 52(1), 1-21.
13.Andrade, G. and Kaplan, S., 1998, “How Costly is Financial (Not Economic) Distress? Evidence from Highly Leveraged Transactions that Became Distressed”, The Journal of Finance, 53(5), 1443-1493.
14.Ross, B., 2000, “Financial Ratios and Different Failure Processes”, Journal of Business Finance, 3, 18-24.
15.Laitinen, E., 1991, “Financial Ratios and Different Failure Process”, Journal of Business Finance & Accounting, 18(5), 649-673.
16.Gordon, M. J., 1971, “Towards a Theory of Financial Distress”, The Journal of Finance, 26(2), 347-356.
17.Gilbert, L., Menon, K., and Schwartz, K., 1990, “Predicting Bankruptcy for Firms in Financial Distress”, Journal of Business Finance & Accounting, 17, 161-171.
18.Gestel, T., Baesens, B., Suykens, J., Van den Poel, D., Baestaens, D., and Willekens, M., 2006, “Bayesian Kernel Based Classification for Financial Distress Detection”, European Journal of Operational Research, 172(3), 979-1003.
19.Hendel, I., 1996, “Competition under Financial Distress”, The Journal of Industrial Economics, 54(3), 309-324.
20.Lau, H. L., 1987, “A Five-State Financial Distress Prediction Model”, Journal of Accounting Research, 25, 127-138.
21.Turetsky, H. and McEven, R., 2001, “An Empirical investigation of Firm Longevity: A Molde of the Ex Ante Predictors of Financial Distress”, Review of Quantitative Finance and Accounting, 16, 323-343.
22.Denis, D. and Denis, D., 1995, “Causes of Financial Distress Following Leveraged Recapitalizations”, Journal of Financial Economics, 37, 129-157.
23.Asquith, P., Gertner, R., and Sharfstein, D., 1994, “Anatomy of Financial Distress: An Explanation of Junk Bond Issuers”, The Quarterly Journal of Economics, 109, 625-658.
24.Opler, T. and Titman, S., 1994, “Financial Distress and Corporate Performance”, The Journal of Finance, 49(3), 1015-1040.
25.Tsai, B. H., 2012, “Comparison of Binary Logit Model and Multinomial Logit Model in Predicting Corporate Failure”, Review of Economics and Finance, 2(4), 99-111.
26.Coats, P. K. and Fant, L. F., 1993, “Recognizing Financial Distress Patterns Using a Neural Network Tool”, Financial Management, 22(3), 307-327.
27.Altman, E. I., Marco, G., and Varetto, F., 1994, “Corporate Distress Diagnosis: Comparisons Using Linear Discriminant Analysis and Neural Networks (The Italian Experience)”, Journal of Banking & Finance, 18(3), 505-529.
28.Wilson, R. L. and Sharda, R., 1994, “Bankruptcy Prediction Using Neural Networks”, Decision Support System, 11(5), 545-557.
29.Fernandez, E. and Olmeda, I., 1995, “Bankruptcy Prediction with Artificial Neural Networks”, Lecture Notes in Computer Science, 930, 1142-1146.
30.Efrim, B. J. and Kennedy, D. B., 1995, “Effectiveness of Neural Network Types for Prediction of Business Failure”, Expert Systems with Applications, 9(4), 503-512.
31.Kerling, M. (1996), “Corporate Distress Diagnosis-An International Comparison In A. P. N. Refenes, Y. AbuMostafa, J. Moody, & A. Weigend (Eds.)”, Neural Networks in Financial Engineering, World Scientific Singapore, 407-422.
32.Jo, H., Han, I., and Lee, H., 1997, “Bankruptcy Prediction Using Case-Based Reasoning, Neural Networks, and Discriminant Analysis”, Expert Systems with Applications, 13(2), 97-108.
33.Davalos, S., Gritta, R. D., and Chow, G., 1999, “The Application of a Neural Network Approach to Predicting Bankruptcy Risks Facing the Major US Air Carriers: 1979-1996”, Journal of Air Transport Management, 5(2), 81-86.
34.Koh, H. C. and Tan, S. S., 1999, “A Neural Network Approach to the Prediction of Going Concern Status”, Accounting and Business Research, 29(3), 211-216.
35.Wanous, M., Boussabaine, H. A., and Lewis, J., 2003, “A Neural Network Bid/No Bid Model: The Case for Contractors in Syria”, Construction Management and Economics, 21(7), 737-744.
36.Boser, B. E., I. Guyon, and V. N. Vapnik, 1992, “A training algorithm for optimal margin classifiers”, Proceedings of the Fifth Annual Workshop on Computational Learning Theory, 144-152.
37.Shin, K. S., Lee, T. S., and Kim, H. J., 2005, “An Application of Support Vector Machines in Bankruptcy Prediction Model”, Expert Systems with Applications, 28, 127-135.
38.Tzelepis, K. S., D. E. Koumanakos, and V. Tampakas, 2005, “Efficiency of Machine Learning Techniques in Bankruptcy Prediction”, 2nd International Conference on Enterprise Systems and Accounting (ICESAcc’05), 11-12.
39.Härdle, W., A. Rouslan, Moro, and Dorothea Schäfer, 2005, “Predicting Bankruptcy with Support Vector Machines”, SFB 649 Discussion Paper, 2005-009.
40.Liang, D., Lu, C.C., Tsai, C. F., and Shih, G. A., 2016, “Financial Ratios and Corporate Governance Indicators in Bankruptcy Prediction: A Comprehensive study”, European Journal of Operational Research, 252(2), 561-572.
41.Chen, M.Y., 2014, Using a Hybrid Evolution Approach to Forecast Financial Failures for Taiwan-Listed Companies”, Quantitative Finance, 14(6), 1047-1058.
42.Wo-Chiang Lee, 2006, “Genetic Programming Decision Tree for Bankruptcy Prediction”, Proceedings of the 2006 Joint Conference on Information Sciences (JCIS-06).
43.Barboza, F., Herbert, K., and Edward, A., 2017, “Machine Learning Models and Bankruptcy Prediction”, Expert Systems with Applications, 83(2017), 405-417.
44.Meese, E. N. and Viken, T., 2019, “Machine Learning in Bankruptcy Prediction”, Master thesis, Norwegian School of Economics.
45.Trabelsi, S., Elouedi, Z., Mellouli, K., 2007, “Pruning Belief Decision Tree Methods in Averaging and Conjunctive Approaches”, International Journal of Approximate Reasoning, 46(2007), 568-595.
46.陳肇榮，1983，「運用財務比率預測企業財務危機之實證研究」，政治大學企業管理研究所，博士論文。
47.潘玉葉，1990，「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，博士論文。
48.黃文隆，1993，「財務危機預警模式建立預驗證」，東吳大學管理科學研究所，碩士論文。
49.卓怡如，1995，「財務危機預警模型之建立以上市及未上市公司為例」，台灣大學財務金融研究，碩士論文。
50.黃振豊、呂紹強，2000，「企業財務危機預警模式之研究¬－以財務及非財務因素構建」，當代會計，1(1)，19-40。
51.王景煌，2006，「以資料探勘技術建構企業危機預警模式－結合財務與非財務及智慧資本指標」，中原大學資訊管理學系，碩士論文。
52.葉銀華、李存修、柯承思，2002，「公司治理與評等系統」，商智文化事業股份有限公司。
53.陳建宏、陳麗芬、戴錦周，2007，「樣本偏誤對財務危機預警模型影響之研究」，東吳經濟商學學報，57，29-47。
54.林長瑞，2010，「預測財務危機公司樣本配置之研究」，管理與資訊學報，15，1-30。
55.洪琳美，2005，「運用支撐向量機與類神經網路於銀行授信之研究」，國立臺灣科技大學資訊管理系碩士班，碩士論文。
56.張克群、楊淑閔、陳麗貞、范興宜，2010，「適應性類神經模糊推論系統於財務危機預測之應用」，臺灣銀行季刊，61(3)，61-75。
57.黃俊雄，1993，「企業財務危機預警模型在銀行授信決策之運用」，國立政治大學企業管理研究所，碩士論文。
58.蔡麗君，1994，「審計報告之資訊內涵－運用於財務危機之預測」，國立政治大學會計研究所，碩士論文。
59.高惠松，2012，「年度財務報表資訊揭露對預測財務危機之有用性：預視財務危機預測模型」，中華管理評論國際學報，15(4)，1-25。
60.林左裕、鄭瑞昌、柯俊禎、陳毓芬，2013，「公司治理與財務危機關連性之研究」，評價學報，6，1-26。
61.周百隆、盧俊安，2007，「以Cascaded Logistic Model建構我國企業財務危機預警模型之研究」，中華管理評論國際學報，10(2)，1-16。
62.張麗娟、許佳豪、張耀元，2012，「建構臺灣電子業財務預警－以資料探勘技術分析」，臺灣銀行季刊，63(1)，182-217。
63.余惠芳、潘麗卿，2014，「以勝算比觀點分析企業營運策略、公司治理與財務預測－台灣上市櫃股之實證研究」，全球管理與經濟，10(2)，57-77。
64.陳建宏、謝佩綺，2016，「企業資訊揭露、公司治理與財務危機預警之實證研究－以台灣上市上櫃電子業為例」，財金論文叢刊，25，93-104。
65.黃小玉，1988，「銀行放款信用評估模式之研究－最佳模式之選擇」，淡江大學管理科學研究所，碩士論文。
66.黃美月，1997，「上市公司營運危機預測模型建立之研究」，管理會計雜誌，41，53-82。
67.黃振豊、呂紹強，2000，「企業財務危機預警模式之研究－以財務及非財務因素構建」，當代會計，1(1)，19-40。
68.呂美慧，2000，「金融機構房貸客戶授信評量模式分析－Logistic回歸之應用」台灣金融財務季刊，1(1)，1-20。
69.周百隆，2002，「金融機構經營危機時程之研究－農會信用部實證分析」，行政院國家科學委員會專題研究計劃。
70.宋秋儀、謝孟潔、盧俊安，2005，「運用不同變數萃取模式預警我國企業危機之研究」，2005企業經營管理學術研討會。
71.李致寬、郭祥兆，1995，「類神經網路分析在財務危機預測之應用－銀行授信、個人投資、企業管理之分析決策工具」，臺灣經濟金融月刊，31(8)，20-28。
72.陳錦村、許通安、林蔓蓁，1996，「銀行授信客戶違約風險之預測」，管理科學學報，13(2)，173-195。
73.何文榮、彭俊豪，2001，「以不同類神經網路建構上市公司財務預警模型」，臺灣土地金融季刊，38(3)，1-22。
74.沈大白、張大成、劉宛鑫，2002，「運用類神經網路建構財務危機預警模型」，貨幣觀測與信用評等，38，95-102。
75.曾淑峰、江俊豪，2008，「GA-SVM組合式信用風險財務危機模型之研究」，台灣金融財務季刊，9(1)，1-25。
76.張斐章、張麗秋、黃浩倫，2003，「類神經網路理論與實務」，東華書局出版社。
77.葉怡成，2000，「類神經網路模式應用與實作」，儒林出版社。
78.劉立民、吳建華(譯)，2016，「Python機器學習」(原作者：Sebastian Raschka)，博碩文化股份有限公司。