企業繼續經營假設是企業財務報表編制重大假設之一。現今企業所面臨的挑戰越來越多元，尤其在2008年的金融海嘯、2020年新型冠狀病毒COVID-19席捲全球的重大衝擊下，企業更加容易面臨爆發財務危機甚至會因此瀕臨倒閉的風險。然而普遍市場投資人及其利害關係人並不直接涉及企業主要營運與管理，若能提前預測企業財務危機，對於其投資決策則有重大的幫助。
早期財務危機預警分析較多以傳統統計方法做為分析工具，近年開始有學者從類神經網路工具來進行分析研究，然而隨著硬體設備的提升及多元的演算法，因此企業預警分析研究可以更加多元。本研究以台灣經濟新報資料庫為其樣本資料來源並以財務比率作為其自變數及搭配機器學習演算法來建立其財務預警預測模型，如決策樹、隨機森林、自身適應增強分類演算法、人工神經網路、支援向量機、K-近鄰演算法、羅吉斯迴歸、單純貝氏分類器等機器學習工具。本研究結果隨機森林明顯優於其他分類器，其AUC各別為0.850，是屬於Hosmer and Lemeshow (2000) 提到excellent discrimination.

關鍵詞：機器學習、財務危機預警、永續

Going concern basis is one of the assumptions when a company prepares financial reports. They have multiple challenges at a time, often across different categories today. Under the impacts of financial crisis in 2008 and the Coronavirus (COVID-19) in 2020, there were more operation risks on corporate failure or bankruptcies. If it can be predicted on finical crisis in advance, it is helpful on making investment decision for the investor and interested parties, because they are not involved in corporate operation.
People used the statical analysis on financial crisis precaution over the past year and they also used artificial neural network on their research. The advancement in Science and Technology Research provides us various way on financial crisis precaution research. The sample of this study uses the Taiwan Economic Journal Database. We also use the finical rates and non-financial rates with machine learning algorithms on building financial crisis precaution models, including Decision Tree, Random Forest, Adaptive Boosting, AdaBoost, Artificial Neural Network, SVM, K Nearest Neighbor, Logistic Regression, Navie Bayes. Random Forest is considered excellent discrimination of algorithm model on financial crisis precaution. The AUC results is 0.850 and this is between 0.8 and 0.9 is considered excellent discrimination by Hosmer and Lemeshow (2000).

Keywords: Machine Learning, Financial Crisis Precaution, and Sustainability.

陳明賢. (1986). 財務危機預測之計量分析研究 [國立臺灣大學]. 收入 商學研究所: 卷 碩士. https://hdl.handle.net/11296/q8e8m9
陳肇榮. (1983). 運用財務比率預測企業財務危機之實證研究 [國立政治大學]. 收入 企業管理研究所: 卷 博士. https://hdl.handle.net/11296/muxs4m
高惠松, 李建然, 陳樹衡, Kao, H.-S., Lee, J.-Z., & Chen, S.-H. (2012). 不同公司治理情境之股權評價：類神經模糊專家系統之應用. 管理與系統, 19(3), 373–408.
郭啟賢(Chii-Shyan Kuo), 張鳳真(Feng-Chen Chang), 張芸瑄(Zoey Chang), & 余士迪(Shih-Ti Yu). (2021). 我國銀行業盈餘與資本適足比率之調配. 應用經濟論叢, 109, 169–213. https://doi.org/10.3966/054696002021060109005
簡文樂. (2019). 香港上市公司財務危機預警模型之建立與應用 [國立政治大學]. 收入 政治大學會計學系學位論文 (期 2019年, 頁 57). https://doi.org/10.6814/NCCU201900787
簡禎富, 彭金堂, 許嘉裕, Chien, C.-F., Peng, J.-T., & Hsu, C.-Y. (2013). 產學合作模式之研究－以科學工業園區固本精進產學合作計畫為例. 管理與系統, 20(1), 27–54.
賴擁連(Yung-Lien Lai), 吳慧菁(Hui-Ching Wu), & 蔡田木(Tien-Muh Tsai). (2021). 女性毒品收容人釋放後生活關注議題以及尋求協助需求之初探. 藥物濫用防治, 6(2), 37–60. https://doi.org/10.6645/JSAR.202106_6(2).3
李建然(Jan-Zan Lee), 廖秀梅(Hsiu-Mei Liao), & 馬心屏(Hsin-Ping Ma). (2022). 影響上市櫃公司於公開資訊觀測站自願申報自結損益的決定因素. 臺大管理論叢, 32(1), 127–152. https://doi.org/10.6226/NTUMR.202204_32(1).0004
李沃牆. (2020). 全球疫情不止　經濟復甦疑慮多. 會計研究月刊, 417, 16–20. https://doi.org/10.6650/ARM.202008_(417).0003
林冠廷. (2018). 財務危機預警模型實證研究─考慮表外風險因素 [國立臺灣大學]. 收入 臺灣大學國際企業學研究所學位論文 (期 2018年, 頁 51). https://doi.org/10.6342/NTU201802803
林左裕(Calvin Tso-Yu Lin), 鄭瑞昌(Jui-Chang Cheng), 柯俊禎(James J. C. Ko), & 陳毓芬(Yu-Fen Chen). (2013). 公司治理與財務危機關聯性之研究. 評價學報, 6, 1–26.
潘玉葉. (1990). 臺灣股票上市公司財務危機預警分析 [淡江大學]. 收入 管理科學研究所: 卷 博士. https://hdl.handle.net/11296/2g724a
邱皓政(Haw-Jeng Chiou). (2017). 多元迴歸的自變數比較與多元共線性之影響：效果量、優勢性與相對權數指標的估計與應用. 臺大管理論叢, 27(3), 65–108. https://doi.org/10.6226/NTUMR.2017.JAN.A103-022
巫沛倉(Pei-Tsang Wu), 廖紫柔(Tzu-Jou Liao), & 邱詩彥(Shi-Yan Qiu). (2021). 運用灰關聯分析與倒傳遞類神經網路建構財務危機預警模型. 管理資訊計算, 10(1), 121–132. https://doi.org/10.6285/MIC.202103_10(1).0012
許溪南(Hsinan Hsu), 歐陽豪(Ou-Yang Hou), & 陳慶芳(Ching-Fang Chen). (2007). 公司治理、盈餘管理與財務預警模型之建構. 會計與公司治理, 4(1), 85–121. https://doi.org/10.30139/JACG.200706.0004
余惠芳(Hui-Fun Yu), 蘇明達(Ming-Da Su), & 李巧妤(Qiao-Yu Li). (2020). 融資決策、股利政策與營運績效之研究：中國上市公司之實證. 全球管理與經濟, 16(2), 65–80. https://doi.org/10.6565/JGME.202012_16(2).0005
張書瑋. (2020). 疫情下的企業財務危機求生術. 會計研究月刊, 416, 60–64. https://doi.org/10.6650/ARM.202007_(416).0009
鄭碧月. (1997). 上市公司營運危機預測模式之研究 [朝陽技術學院]. 收入 財務金融系所研究所: 卷 碩士. https://hdl.handle.net/11296/e32gpk
卓一誠. (2008). 運用倒傳遞類神經網路建構電子業財務危機預警模型 [國立交通大學]. 收入 管理學院碩士在職專班資訊管理組: 卷 碩士. https://hdl.handle.net/11296/qk2e3u
Altman, E. I. (1968). Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy. The Journal of Finance, 23(4), 589–609. https://doi.org/10.2307/2978933
Altman, E. I. (2013). Predicting financial distress of companies: Revisiting the Z-Score and ZETA® models. Handbook of Research Methods and Applications in Empirical Finance, 428–456.
Altman, E. I., Haldeman, R. G., & Narayanan, P. (1977). ZETATM analysis A new model to identify bankruptcy risk of corporations. Journal of Banking & Finance, 1(1), 29–54. https://doi.org/10.1016/0378-4266(77)90017-6
Altman, E. I., Iwanicz-Drozdowska, M., Laitinen, E. K., & Suvas, A. (2015). Financial and Non-Financial Variables as Long-Horizon Predictors of Bankruptcy (SSRN Scholarly Paper 期 2669668). Social Science Research Network. https://doi.org/10.2139/ssrn.2669668
Ansari, A., Ahmad, I. S., Bakar, A. A., & Yaakub, M. R. (2020). A Hybrid Metaheuristic Method in Training Artificial Neural Network for Bankruptcy Prediction. IEEE Access, 8, 176640–176650. https://doi.org/10.1109/ACCESS.2020.3026529
Atiya, A. F. (2001). Bankruptcy prediction for credit risk using neural networks: A survey and new results. IEEE Transactions on Neural Networks, 12(4), 929–935. https://doi.org/10.1109/72.935101
Beaver, W. H. (1966). Financial Ratios As Predictors of Failure. Journal of Accounting Research, 4, 71–111. https://doi.org/10.2307/2490171
Berkson, J. (1944). Application of the Logistic Function to Bio-Assay. Journal of the American Statistical Association, 39(227), 357–365. https://doi.org/10.1080/01621459.1944.10500699
Blum, M. (1974). Failing Company Discriminant Analysis. Journal of Accounting Research, 12(1), 1–25. https://doi.org/10.2307/2490525
Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Brown, L. W., De Leon, J. A., & Rasheed, A. A. (2019). Corporate Political Activity and Free Riding under Market Uncertainty: An Investigation of TARP Funding. Business and Society Review, 124(1), 115–143. https://doi.org/10.1111/basr.12165
Burges, C. J. C. (1998). A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery, 2(2), 121–167. https://doi.org/10.1023/A:1009715923555
Chen, J., Chollete, L., & Ray, R. (2010). Financial distress and idiosyncratic volatility: An empirical investigation. Journal of Financial Markets, 13(2), 249–267. https://doi.org/10.1016/j.finmar.2009.10.003
Chen, M.-Y. (2011). Bankruptcy prediction in firms with statistical and intelligent techniques and a comparison of evolutionary computation approaches. Computers & Mathematics with Applications, 62(12), 4514–4524. https://doi.org/10.1016/j.camwa.2011.10.030
Coats, P. K., & Fant, L. F. (1991). A Neural Network Approach to Forecasting Financial Distress. The Journal of Business Forecasting Methods & Systems, 10(4), 9. ABI/INFORM Collection; Accounting, Tax & Banking Collection; Healthcare Administration Database.
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. https://doi.org/10.1007/BF00994018
Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1), 21–27. https://doi.org/10.1109/TIT.1967.1053964
David W. Hosmer, Stanley Lemeshow. (2000). Applied Logistic Regression. 收入 Applied Logistic Regression (頁 i–xii). John Wiley & Sons, Ltd. https://doi.org/10.1002/0471722146.fmatter
Deakin, E. B. (1972). A Discriminant Analysis of Predictors of Business Failure. Journal of Accounting Research, 10(1), 167–179. https://doi.org/10.2307/2490225
Delen, D., Sharda, R., & Bessonov, M. (2006). Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks. Accident Analysis & Prevention, 38(3), 434–444. https://doi.org/10.1016/j.aap.2005.06.024
Demyanyk, Y., & Van Hemert, O. (2008). Understanding the Subprime Mortgage Crisis (SSRN Scholarly Paper 期 1020396). Social Science Research Network. https://doi.org/10.2139/ssrn.1020396
Fernández, A., García, S., del Jesus, M. J., & Herrera, F. (2008). A study of the behaviour of linguistic fuzzy rule based classification systems in the framework of imbalanced data-sets. Fuzzy Sets and Systems, 159(18), 2378–2398. https://doi.org/10.1016/j.fss.2007.12.023
Freund, Y., & Schapire, R. E. (1999). A Short Introduction to Boosting. 14.
Hanley, J.A., McNeil, B.J. (1982). The meaning and use of the area under a receiver operating characteristic (ROC) curve. | Radiology. https://pubs.rsna.org/doi/abs/10.1148/radiology.143.1.7063747
Hopwood, W., McKEOWN, J. C., & Mutchler, J. F. (1994). A Reexamination of Auditor versus Model Accuracy within the Context of the Going-Concern Opinion Decision*. Contemporary Accounting Research, 10(2), 409–431. https://doi.org/10.1111/j.1911-3846.1994.tb00400.x
Lin, W.-Y., Hu, Y.-H., & Tsai, C.-F. (2012). Machine Learning in Financial Crisis Prediction: A Survey. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42(4), 421–436. https://doi.org/10.1109/TSMCC.2011.2170420
Odom, M. D., & Sharda, R. (1990). A neural network model for bankruptcy prediction. 1990 IJCNN International Joint Conference on Neural Networks, 163–168 卷2. https://doi.org/10.1109/IJCNN.1990.137710
Ohlson, J. A. (1980). Financial Ratios and the Probabilistic Prediction of Bankruptcy. Journal of Accounting Research, 18(1), 109–131. https://doi.org/10.2307/2490395
Perboli, G., & Arabnezhad, E. (2021). A Machine Learning-based DSS for mid and long-term company crisis prediction. Expert Systems with Applications, 174, 114758. https://doi.org/10.1016/j.eswa.2021.114758
Pinches, G. E. (1980). Factors influencing classification results from multiple discriminant analysis. Journal of Business Research, 8(4), 429–456. https://doi.org/10.1016/0148-2963(80)90017-X
Sun, X., & Lei, Y. (2021). Research on financial early warning of mining listed companies based on BP neural network model. Resources Policy, 73, 102223. https://doi.org/10.1016/j.resourpol.2021.102223
Tkáč, M., & Verner, R. (2016). Artificial neural networks in business: Two decades of research. Applied Soft Computing, 38, 788–804. https://doi.org/10.1016/j.asoc.2015.09.040
Zeitun, R., Tian, G., & Keen, S. (2007). Macroeconomic determinants of corporate performance and failure: Evidence from an emerging market the case of Jordan. Faculty of Commerce - Papers (Archive), 179–194.
Zmijewski, M. E. (1984). Methodological Issues Related to the Estimation of Financial Distress Prediction Models. Journal of Accounting Research, 22, 59–82. https://doi.org/10.2307/2490859