財務比率在先前的研究中已被廣泛使用，以建立其財務困境預測模型。奧特曼（Altman）所提出的Z分數模型已成為預測中最常使用的方法，特別是在學術研究中。在理想情況下，Altman的Z-Score模型旨在在兩年內衡量公司的財務狀況，並且被證實在各種情況和市場中預測破產是準確的。然而，以前的研究都沒有嘗試以不同的方式來識別和分析五個奧特曼變量，並根據它們的行為對其進行威脅。因此，本研究受到研究問題的推動：使用疊加泛化將五個Altman變量分為長期和短期行為，是否可以幫助預測明年台灣上市公司的財務困境？為了研究該問題，我們提出了將五個奧特曼變量並行處理為兩個不同特徵集的堆疊整合學習方法，並進行了綜合分析。這些研究發現不僅有助於混合所有財務比率資訊，還可以根據長期和短期條件仔細考慮，從而協助公共投資考慮貸款決策。

Financial Ratio had been used widely on the previous research to build their model of financial distress prediction. Altman’s Z-Score was become the most often used for predicting especially in academic studies. Ideally, Altman’s Z-Score purposes to measure a company’s financial health within two years and it proven accurate to forecast bankruptcy in a wide variety of contexts and markets. However, none of the previous research tried to identify and analyse the five Altman variables differently and threat them based on their behaviour. Therefore, this study is motivated by research question: Could the splitting of five Altman Variables into Long-Term and Short-term behaviour using stacking generalization help to predict the financial distress of Taiwan list companies in the next year? To examine this question, we proposed the stacking ensemble learning which threat five Altman Variables into two different feature set parallel and conducted a comprehensive analysis. These findings will help the public investment to consider a lending decision, not only by mixing all information of financial ratio, but carefully consider based on its long-term condition and short-term condition.

[1] J. Sun, H. Li, Q. H. Huang, and K. Y. He, “Predicting financial distress and corporate failure: A review from the state-of-the-art definitions, modeling, sampling, and featuring approaches,” Knowledge-Based Systems, vol. 57, pp. 41–56, 2014.
[2] S. Cho, J. Kim, and J. K. Bae, “An integrative model with subject weight based on neural network learning for bankruptcy prediction,” Expert Systems with Applications, vol. 36, no. 1, pp. 403–410, Jan. 2009.
[3] Y. S. Huang and C. Y. Suen, “Behavior-knowledge space method for combination of multiple classifiers,” in IEEE Computer Vision and Pattern Recognition, 1993.
[4] E. I. Altman, “FINANCIAL RATIOS, DISCRIMINANT ANALYSIS AND THE PREDICTION OF CORPORATE BANKRUPTCY,” The Journal of Finance, 1968.
[5] D. Liang, C. C. Lu, C. F. Tsai, and G. A. Shih, “Financial ratios and corporate governance indicators in bankruptcy prediction: A comprehensive study,” European Journal of Operational Research, 2016.
[6] P. du Jardin, D. Veganzones, and E. Séverin, “Forecasting Corporate Bankruptcy Using Accrual-Based Models,” Computational Economics, 2019.
[7] F. Lin, D. Liang, and W. S. Chu, “The role of non-financial features related to corporate governance in business crisis prediction,” Journal of Marine Science and Technology, 2010.
[8] E. I. Altman, M. Iwanicz-Drozdowska, E. K. Laitinen, and A. Suvas, “Distressed Firm and Bankruptcy Prediction in an International Context: A Review and Empirical Analysis of Altman’s Z-Score Model,” SSRN Electronic Journal, 2014.
[9] C. Brentani, “Financial statement analysis and financial ratios,” in Portfolio Management in Practice, Elsevier, 2004, pp. 149–163.
[10] P. A. Griffin, “Financial Statement Analysis,” in Finding Alphas: A Quantitative Approach to Building Trading Strategies, 2015.
[11] E. J. Allen, C. R. Larson, and R. G. Sloan, “Accrual reversals, earnings and stock returns,” Journal of Accounting and Economics, 2013.
[12] S. Tian and Y. Yu, “Financial ratios and bankruptcy predictions: An international evidence,” International Review of Economics and Finance, 2017.
[13] Jo, Blocher, and Lin, “Prediction of Corporate Financial Distress: An Application of the Composite Rule Induction System,” The International Journal of Digital Accounting Research, 2001.
[14] J. A. Ohlson, “Financial Ratios and the Probabilistic Prediction of Bankruptcy,” Journal of Accounting Research, 1980.
[15] H. FRYDMAN, E. I. ALTMAN, and D.-L. KAO, “Introducing Recursive Partitioning for Financial Classification: The Case of Financial Distress,” The Journal of Finance, vol. 40, no. 1, pp. 269–291, Mar. 1985.
[16] R. C. Lacher, P. K. Coats, S. C. Sharma, and L. F. Fant, “A neural network for classifying the financial health of a firm,” European Journal of Operational Research, vol. 85, no. 1, pp. 53–65, Aug. 1995.
[17] M. P. Sesmero, A. I. Ledezma, and A. Sanchis, “Generating ensembles of heterogeneous classifiers using Stacked Generalization,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2015.
[18] W. Jiang, Z. Chen, Y. Xiang, D. Shao, L. Ma, and J. Zhang, “SSEM: A Novel Self-Adaptive Stacking Ensemble Model for Classification,” IEEE Access, vol. 7, pp. 120337–120349, 2019.
[19] S. Džeroski and B. Ženko, “Is Combining Classifiers with Stacking Better than Selecting the Best One?,” Machine Learning, vol. 54, no. 3, pp. 255–273, Mar. 2004.
[20] E. Menahem, L. Rokach, and Y. Elovici, “Troika – An improved stacking schema for classification tasks,” Information Sciences, vol. 179, no. 24, pp. 4097–4122, Dec. 2009.
[21] M.-Y. Chen, “Predicting corporate financial distress based on integration of decision tree classification and logistic regression,” Expert Systems with Applications, vol. 38, no. 9, pp. 11261–11272, Sep. 2011.
[22] A. J. Scott, D. W. Hosmer, and S. Lemeshow, “Applied Logistic Regression.,” Biometrics, 1991.
[23] L. Zhou, “Performance of corporate bankruptcy prediction models on imbalanced dataset: The effect of sampling methods,” Knowledge-Based Systems, 2013.