قدرت شبکه عصبی پیچشی در پیش‌بینی درماندگی مالی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دانشگاه ارشاد دماوند-واحد تهران

2 استادیار گروه حسابداری، دانشکده علوم اجتماعی و اقتصادی، دانشگاه الزهرا

چکیده

در این پژوهش ضمن نگاه بر سیر تکامل ادبیات پیش‌بینی درماندگی مالی، به ارائه یک مدل یادگیری عمیق پرداخته شده است. در این روش به شکلی مراحلی که روش‌های پیشین برای پیش‌بینی درماندگی طی ‌کرده‌اند،  کوتاه‌تر و خودکارتر شده است. در نهایت، به مقایسه دقت پیش‌بینی مدل توسعه داده شده با مدل‌های پیشین در این حوزه پرداخته شده است. در این پژوهش یک شبکه عصبی پیچشی به‌عنوان یک مدل یادگیری عمیق که داده‌های 14 متغیر مرتبط با پیش‌بینی درماندگی مالی را در طول 3 سال متوالی واکاوی می‌کند، برای پیش‌بینی درماندگی مالی مورداستفاده قرار گرفته است.بدر این راستا، به‌منظور جلوگیری از خطاهای احتمالی تعمیم‌پذیری، از روش K-fold برای نمونه‌گیری فرعی استفاده شده است که داده‌های 300 نمونه را مورد بررسی قرار می‌دهد. در نهایت، با استفاده از آزمون ناپارامتریک Wilcoxon به بررسی معنی‌دار بودن اختلاف دقت پیش‌بینی ارائه شده میان مدل توسعه داده شده و مدل‌های پیشین پرداخته شده است. نتایج این پژوهش نشان می‌دهد مدل شبکه عصبی پیچشی به شکل معنی‌داری در سطح اطمینان 95 درصد مدل‌های پیش‌بینی درماندگی سابق از جمله رگرسیون لجستیک و ماشین بردار پشتیبان را در دقت پیش‌بینی شکست می‌دهد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

The Strength of Convolutional Neural Network in Financial Distress Prediction

نویسندگان [English]

  • Amin Aminimehr 1
  • Hanieh Hekmat 2
1 student of Ershad Damavand institute of higher education
2 Assistant professor of accounting, Alzahra University Tehran, Iran
چکیده [English]

Aim of study: In this study, by reviewing at the literature of financial distress prediction, a deep learning method has been developed that automates and shortens the earlier procedures of financial distress prediction. At last, the developed method is validated by comparing it to the earlier methods of this area.
Methodology: The developed Convolutional Neural Network is used to extract knowledge within 14 related features to financial distress, through 3 consecutive years. In order to avoid the probable generalization error, the advantage of K-fold method to slice the entire 300 sample into sub-samples, was taken. Finally, the advantage of non-parametric Wilcoxon test was taken to verify the differences between the accuracy of the proposed method with the earlier ones.
Result: Results of this study implies that the Convolutional Neural Network beats the other well-known methods in this area such as logistic regression and support vector machine with 95 percent confidence interval, in terms of prediction accuracy.

کلیدواژه‌ها [English]

  • Financial distress
  • Prediction
  • Convolutional Neural Network
  • Deep Learning
Aliakbarlou, A., Mansourfar, G., & Ghayour, F. (2020). Comparing the Identifying Criteria for Financially Distressed Companies using Logistic Regression and Artificial Intelligence Methods. Financial Management Perspective, 10(29), 147-166. https://doi.org/10.52547/jfmp.10.29.147 (In Persian)
Altman, Edward I. "Financial Ratios, Discriminant Analysis and the Prediction of Corporate Bankruptcy." The Journal of Finance 23, no. 4 (1968): 589-609. https://doi.org/10.2307/2978933. http://www.jstor.org/stable/2978933.
Beaver, William H. "Financial Ratios as Predictors of Failure." Journal of Accounting Research 4 (1966): 71-111. https://doi.org/10.2307/2490171. http://www.jstor.org/stable/2490171.
Blum, Marc. "Failing Company Discriminant Analysis." Journal of Accounting Research 12, no. 1 (1974): 1-25. https://doi.org/10.2307/2490525. http://www.jstor.org/stable/2490525.
Chou, Chih-Hsun, Su-Chen Hsieh, and Chui-Jie Qiu. "Hybrid Genetic Algorithm and Fuzzy Clustering for Bankruptcy Prediction." Applied Soft Computing 56 (2017/07/01/ 2017): 298-316. https://doi.org/https://doi.org/10.1016/j.asoc.2017.03.014. https://www.sciencedirect.com/science/article/pii/S1568494617301370.
Deakin, Edward B. "A Discriminant Analysis of Predictors of Business Failure." Journal of Accounting Research 10, no. 1 (1972): 167-79. https://doi.org/10.2307/2490225. http://www.jstor.org/stable/2490225.
Erdogan, Birsen Eygi. "Prediction of Bankruptcy Using Support Vector Machines: An Application to Bank Bankruptcy." Journal of Statistical Computation and Simulation 83, no. 8 (2013/08/01 2013): 1543-55. https://doi.org/10.1080/00949655.2012.666550.
Fallahpour, S., Norouzian Lakvan, E., & Hendijani Zadeh, M. (2017). Use of Combined Approach of Support Vector Machine and Feature Selection for Financial Distress Prediction of Listed Companies in Tehran Stock Exchange Market. Financial Research Journal, 19(1), 139-156. https://doi.org/10.22059/jfr.2015.52758 (In Persian)
Foster, Gladys Parker. "The Endogeneity of Money and Keynes’s General Theory." Journal of Economic Issues 20, no. 4 (1986/12/01 1986): 953-68. https://doi.org/10.1080/00213624.1986.11504570.
Gordon, M. J. "Towards a Theory of Financial Distress." The Journal of Finance 26, no. 2 (1971): 347-56. https://doi.org/10.2307/2326050. http://www.jstor.org/stable/2326050.
He, K., X. Zhang, S. Ren, and J. Sun. "Deep Residual Learning for Image Recognition." Paper presented at the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27-30 June 2016 2016.
Huang, Yu-Pei, and Meng-Feng Yen. "A New Perspective of Performance Comparison among Machine Learning Algorithms for Financial Distress Prediction." Applied Soft Computing 83 (2019/10/01/ 2019): 105663. https://doi.org/https://doi.org/10.1016/j.asoc.2019.105663. https://www.sciencedirect.com/science/article/pii/S1568494619304430.
Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet Classification with Deep Convolutional Neural Networks." Commun. ACM 60, no. 6 (2017): 84–90. https://doi.org/10.1145/3065386.
LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. "Deep Learning." Nature 521, no. 7553 (2015/05/01 2015): 436-44. https://doi.org/10.1038/nature14539.
Malakauskas, Aidas, and Aušrinė Lakštutienė. "Financial Distress Prediction for Small and Medium Enterprises Using Machine Learning Techniques." Engineering Economics 32, no. 1 (2021/02/26 2021): 4-14. https://doi.org/10.5755/j01.ee.32.1.27382. http://dx.doi.org/10.5755/j01.ee.32.1.27382.
Mansourfar, g., ghayour, f., & lotfi, b. (2015). The Ability of Support Vector Machine (SVM) in Financial Distress Prediction. Empirical Research in Accounting, 5(3), 177-195. https://doi.org/10.22051/jera.2015.646 (In Persian)
Martin, Daniel. "Early Warning of Bank Failure: A Logit Regression Approach." Journal of Banking & Finance 1, no. 3 (1977/11/01/ 1977): 249-76. https://doi.org/https://doi.org/10.1016/0378-4266(77)90022-X. https://www.sciencedirect.com/science/article/pii/037842667790022X.
Namazi, M., & Ebrahimi, S. (2021). Financial Distress Prediction of the Listed Companies on Tehran Stock Exchange (TSE) and Iran Fara Burse (IFB) Using Support Vector Machine. Financial Management Strategy, 9(1), 115-132. https://doi.org/10.22051/jfm.2020.25973.2077 (In Persian)
Odom, M. D., and R. Sharda. "A Neural Network Model for Bankruptcy Prediction." Paper presented at the 1990 IJCNN International Joint Conference on Neural Networks, 17-21 June 1990 1990.
Raei. R, Fallahpour, S. Support Vector Machines Application in Financial Distress Prediction of Companies Using Financial Ratios. (2009). Accounting and Auditing Review, 15(4). https://acctgrev.ut.ac.ir/article_27750.html (In Persian)
Ravi Kumar, P., and V. Ravi. "Bankruptcy Prediction in Banks and Firms Via Statistical and Intelligent Techniques - a Review." European Journal of Operational Research 180, no. 1 (2007): 1-28. https://EconPapers.repec.org/RePEc:eee:ejores:v:180:y:2007:i:1:p:1-28.
Rey, Denise, and Markus Neuhäuser. "Wilcoxon-Signed-Rank Test." In International Encyclopedia of Statistical Science, edited by Miodrag Lovric, 1658-59. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011.
Saeedi, A., & Aghaie, A. (2009). Predicting Financial Distress of firms Listed in Tehran Stock Exchange Using Bayesian networks. Accounting and Auditing Review, 16(2). https://acctgrev.ut.ac.ir/article_20001.html (In Persian)
Srivastava, Nitish, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. "Dropout: A Simple Way to Prevent Neural Networks from Overfitting." Journal of Machine Learning Research 15 (06/01 2014): 1929-58.
Sun, Jie, Hamido Fujita, Yujiao Zheng, and Wenguo Ai. "Multi-Class Financial Distress Prediction Based on Support Vector Machines Integrated with the Decomposition and Fusion Methods." Information Sciences 559 (2021/06/01/ 2021): 153-70. https://doi.org/https://doi.org/10.1016/j.ins.2021.01.059. https://www.sciencedirect.com/science/article/pii/S0020025521000979.
Sun, Jie, and Hui Li. "Financial Distress Prediction Using Support Vector Machines: Ensemble Vs. Individual." Applied Soft Computing 12, no. 8 (2012/08/01/ 2012): 2254-65. https://doi.org/https://doi.org/10.1016/j.asoc.2012.03.028. https://www.sciencedirect.com/science/article/pii/S1568494612001263.
Taj mazinani, M., Fallahpour, S., & Bajalan, S. (2015). The Use of Feature Selection Method (HARC) in Predicting Financial Distress in Tehran Stock Exchange. Financial Management Strategy, 3(2), 77-106. https://doi.org/10.22051/jfm.2015.2169 (In Persian)
Tsai, C.-F., Sue, K.-L., Hu, Y.-H., & Chiu, A. (2021). Combining feature selection, instance selection, and ensemble classification techniques for improved financial distress prediction. Journal of Business Research, 130, 200-209. https://doi.org/https://doi.org/10.1016/j.jbusres.2021.03.018
Ward, Terry J., and Benjamin P. Foster. "A Note on Selecting a Response Measure for Financial Distress." Journal of Business Finance & Accounting 24 (1997): 869-79.
Whitaker, Richard B. "The Early Stages of Financial Distress." Journal of Economics and Finance 23, no. 2 (1999/06/01 1999): 123-32. https://doi.org/10.1007/BF02745946.
Yu, Lean, Rongtian Zhou, Ling Tang, and Rongda Chen. "A Dbn-Based Resampling Svm Ensemble Learning Paradigm for Credit Classification with Imbalanced Data." Applied Soft Computing 69 (2018/08/01/ 2018): 192-202. https://doi.org/https://doi.org/10.1016/j.asoc.2018.04.049. https://www.sciencedirect.com/science/article/pii/S1568494618302400.
Zmijewski, Mark E. "Methodological Issues Related to the Estimation of Financial Distress Prediction Models." Journal of Accounting Research 22 (1984): 59-82. https://doi.org/10.2307/2490859. http://www.jstor.org/stable/2490859.