A deep learning approach of financial distress recognition combining text

Jiawang Li; Chongren Wang; Jiawang Li; Chongren Wang

doi:10.3934/era.2023240

Electronic Research Archive

2023, Volume 31, Issue 8: 4683-4707. doi: 10.3934/era.2023240

Previous Article Next Article

Research article

A deep learning approach of financial distress recognition combining text

Jiawang Li ^,,
Chongren Wang ^,

School of Management Science and Engineering, Shandong University of Finance and Economics, Jinan 250014, Shandong, China

Received: 05 April 2023 Revised: 04 June 2023 Accepted: 15 June 2023 Published: 03 July 2023

The financial distress of listed companies not only harms the interests of internal managers and employees but also brings considerable risks to external investors and other stakeholders. Therefore, it is crucial to construct an efficient financial distress prediction model. However, most existing studies use financial indicators or text features without contextual information to predict financial distress and fail to extract critical details disclosed in Chinese long texts for research. This research introduces an attention mechanism into the deep learning text classification model to deal with the classification of Chinese long text sequences. We combine the financial data and management discussion and analysis Chinese text data in the annual reports of 1642 listed companies in China from 2017 to 2020 in the model and compare the effects of the data on different models. The empirical results show that the performance of deep learning models in financial distress prediction overcomes traditional machine learning models. The addition of the attention mechanism improved the effectiveness of the deep learning model in financial distress prediction. Among the models constructed in this study, the Bi-LSTM+Attention model achieves the best performance in financial distress prediction.
- financial distress prediction,
- deep learning,
- attention mechanism,
- text analytics,
- LSTM
Citation: Jiawang Li, Chongren Wang. A deep learning approach of financial distress recognition combining text[J]. Electronic Research Archive, 2023, 31(8): 4683-4707. doi: 10.3934/era.2023240

Related Papers:

Abstract

The financial distress of listed companies not only harms the interests of internal managers and employees but also brings considerable risks to external investors and other stakeholders. Therefore, it is crucial to construct an efficient financial distress prediction model. However, most existing studies use financial indicators or text features without contextual information to predict financial distress and fail to extract critical details disclosed in Chinese long texts for research. This research introduces an attention mechanism into the deep learning text classification model to deal with the classification of Chinese long text sequences. We combine the financial data and management discussion and analysis Chinese text data in the annual reports of 1642 listed companies in China from 2017 to 2020 in the model and compare the effects of the data on different models. The empirical results show that the performance of deep learning models in financial distress prediction overcomes traditional machine learning models. The addition of the attention mechanism improved the effectiveness of the deep learning model in financial distress prediction. Among the models constructed in this study, the Bi-LSTM+Attention model achieves the best performance in financial distress prediction.

References

[1]	G. Wang, G. Chen, Y. Chu, A new random subspace method incorporating sentiment and textual information for financial distress prediction, Electron. Commer. Res. Appl., 29 (2018), 30–49. https://doi.org/10.1016/j.elerap.2018.03.004 doi: 10.1016/j.elerap.2018.03.004
[2]	G. Wang, J. L. Ma, G. Chen, Y. Yang, Financial distress prediction: Regularized sparse-based random subspace with er aggregation rule incorporating textual disclosures, Appl. Soft Comput., 90 (2020), 106152. https://doi.org/10.1016/j.asoc.2020.106152 doi: 10.1016/j.asoc.2020.106152
[3]	Z. Halim, S. M. Shuhidan, Z. M. Sanusi, Corporation financial distress prediction with deep learning: analysis of public listed companies in malaysia, Bus. Process Manage. J., 27 (2021), 1163–1178. https://doi.org/10.1108/Bpmj-06-2020-0273. doi: 10.1108/Bpmj-06-2020-0273
[4]	P. du Jardin, A two-stage classification technique for bankruptcy prediction, Eur. J. Oper. Res., 254 (2016), 236–252. https://doi.org/10.1016/j.ejor.2016.03.008 doi: 10.1016/j.ejor.2016.03.008
[5]	D. Campa, M. D. Camacho-Minano, The impact of SME's pre-bankruptcy financial distress on earnings management tools, Int. Rev. Financ. Anal., 42 (2015), 222–234. https://doi.org/10.1016/j.irfa.2015.07.004 doi: 10.1016/j.irfa.2015.07.004
[6]	J. Bertomeu, E. Cheynel, E. Floyd, W. Pan, Using machine learning to detect misstatements, Rev. Accounting Stud., 26 (2021), 468–519. https://doi.org/10.1007/s11142-020-09563-8 doi: 10.1007/s11142-020-09563-8
[7]	J. Donovan, J. Jennings, K. Koharki, J. Lee, Measuring credit risk using qualitative disclosure, Rev. Accounting Stud., 26 (2021), 815–863. https://doi.org/10.1007/s11142-020-09575-4 doi: 10.1007/s11142-020-09575-4
[8]	W. Ben‐Amar, I. Belgacem, Do socially responsible firms provide more readable disclosures in annual reports, Corporate Social Responsib. Environ. Manage., 25 (2018), 1009–1018. https://doi.org/10.1002/csr.1517 doi: 10.1002/csr.1517
[9]	P. Hajek, R. Henriques, Mining corporate annual reports for intelligent detection of financial statement fraud–a comparative study of machine learning methods, Knowledge-Based Syst., 128 (2017), 139–152. https://doi.org/10.1016/j.knosys.2017.05.001 doi: 10.1016/j.knosys.2017.05.001
[10]	F. Mai, S. N. Tian, C. Lee, L. Ma, Deep learning models for bankruptcy prediction using textual disclosures, Eur. J. Oper. Res., 274 (2019), 743–758. https://doi.org/10.1016/j.ejor.2018.10.024 doi: 10.1016/j.ejor.2018.10.024
[11]	Y. B. Qian, A critical genre analysis of mda discourse in corporate annual reports, Discourse Commun., 14 (2020), 424–437. https://doi.org/10.1177/1750481320910525 doi: 10.1177/1750481320910525
[12]	W. H. Beaver, Financial ratios as predictors of failure, J. Accounting Res., 4 (1966), 71–111. https://doi.org/10.2307/2490171 doi: 10.2307/2490171
[13]	E. B. Deakin, A discriminant analysis of predictors of business failure, J. Accounting Res., 10 (1972), 167–179. https://doi.org/10.2307/2490225 doi: 10.2307/2490225
[14]	D. Carmichael, Auditor's Reporting Obligation: The Meaning and Implementation of the Fourth Standard of Reporting; Auditing Research Monographh, 1, American Institute of Certified Public Accountants, 1978.
[15]	M. E. Zmijewski, Methodological issues related to the estimation of financial distress prediction models, J. Accounting Res., 22 (1984), 59–82. https://doi.org/10.2307/2490859 doi: 10.2307/2490859
[16]	E. I. Altman, The Prediction of Corporate Bankruptcy: A Discriminant Analysis, University of California, Los Angeles, 1967.
[17]	A. I. Dimitras, S. H. Zanakis, C. Zopounidis, A survey of business failures with an emphasis on prediction methods and industrial applications, Eur. J. Oper. Res., 90 (1996), 487–513. https://doi.org/10.1016/0377-2217(95)00070-4 doi: 10.1016/0377-2217(95)00070-4
[18]	S. A. Ross, R. Westerfield, J. F. Jaffe, Corporate Finance, Irwin/McGraw-Hill, 1999.
[19]	Y. Ding, X. Song, Y. Zen, Forecasting financial condition of chinese listed companies based on support vector machine, Expert Syst. Appl., 34 (2008), 3081–3089. https://doi.org/10.1016/j.eswa.2007.06.037 doi: 10.1016/j.eswa.2007.06.037
[20]	R. B. Geng, I. Bose, X. Chen, Prediction of financial distress: An empirical study of listed chinese companies using data mining, Eur. J. Oper. Res., 241 (2015), 236–247. https://doi.org/10.1016/j.ejor.2014.08.016 doi: 10.1016/j.ejor.2014.08.016
[21]	S. Ruan, X. Sun, R. Yao, W. Li, Deep learning based on hierarchical self-attention for finance distress prediction incorporating text, Comput. Intell. Neurosci., 2021 (2021), 1165296. https://doi.org/10.1155/2021/1165296 doi: 10.1155/2021/1165296
[22]	F. Y. Lin, D. R. Liang, E. C. Chen, Financial ratio selection for business crisis prediction, Expert Syst. Appl., 38 (2011), 15094–15102. https://doi.org/10.1016/j.eswa.2011.05.035 doi: 10.1016/j.eswa.2011.05.035
[23]	E. I. Altman, Financial ratios, discriminant analysis and the prediction of corporate bankruptcy, J. Finance, 23 (1968), 589–609. https://doi.org/10.2307/2978933 doi: 10.2307/2978933
[24]	G. Wang, J. Ma, S. L. Yang, An improved boosting based on feature selection for corporate bankruptcy prediction, Expert Syst. Appl., 41 (2014), 2353–2361. https://doi.org/10.1016/j.eswa.2013.09.033 doi: 10.1016/j.eswa.2013.09.033
[25]	J. Huang, H. B. Wang, G. Kochenberger, Distressed chinese firm prediction with discretized data, Manage. Decis., 55 (2017), 786–807. https://doi.org/10.1108/Md-08-2016-0546 doi: 10.1108/Md-08-2016-0546
[26]	L. G. Zhou, K. P. Tam, H. Fujita, Predicting the listing status of chinese listed companies with multi-class classification models, Inf. Sci., 328 (2016), 222–236. https://doi.org/10.1016/j.ins.2015.08.036 doi: 10.1016/j.ins.2015.08.036
[27]	D. Alaminos, A. Del Castillo, M. A. Fernandez, A global model for bankruptcy prediction, PLoS One, 11 (2016), e0166693. https://doi.org/10.1371/journal.pone.0166693 doi: 10.1371/journal.pone.0166693
[28]	Y. P. Huang, M. F. Yen, A new perspective of performance comparison among machine learning algorithms for financial distress prediction, Appl. Soft Comput., 83 (2019), 105663. https://doi.org/10.1016/j.asoc.2019.105663 doi: 10.1016/j.asoc.2019.105663
[29]	K. Olorunnimbe, H. Viktor, Deep learning in the stock market-a systematic survey of practice, backtesting, and applications, Artif. Intell. Rev., 56 (2023), 2057–2109. https://doi.org/10.1007/s10462-022-10226-0 doi: 10.1007/s10462-022-10226-0
[30]	S. Ben Jabeur, V. Serret, Bankruptcy prediction using fuzzy convolutional neural networks, Res. Int. Bus. Finance, 64 (2023), 101844. https://doi.org/10.1016/j.ribaf.2022.101844 doi: 10.1016/j.ribaf.2022.101844
[31]	Y. D. Wang, Y. L. Jia, Y. H. Tian, J. Xiao, Deep reinforcement learning with the confusion-matrix-based dynamic reward function for customer credit scoring, Expert Syst. Appl., 200 (2022), 117013. https://doi.org/10.1016/j.eswa.2022.117013 doi: 10.1016/j.eswa.2022.117013
[32]	S. X. Li, W. X. Shi, J. C. Wang, H. S. Zhou, A deep learning-based approach to constructing a domain sentiment lexicon: A case study in financial distress prediction, Inf. Process. Manage., 58 (2021), 102673. https://doi.org/10.1016/j.ipm.2021.102673 doi: 10.1016/j.ipm.2021.102673
[33]	J. Jing, W. Yan, X. Deng, A hybrid model to estimate corporate default probabilities in china based on zero-price probability model and long short-term memory, Appl. Econ. Lett., 28 (2020), 413–420. https://doi.org/10.1080/13504851.2020.1757611 doi: 10.1080/13504851.2020.1757611
[34]	J. Sun, H. Li, H. Fujita, B. B. Fu, W. G. Ai, Class-imbalanced dynamic financial distress prediction based on adaboost-svm ensemble combined with smote and time weighting, Inf. Fusion, 54 (2020), 128–144. https://doi.org/10.1016/j.inffus.2019.07.006 doi: 10.1016/j.inffus.2019.07.006
[35]	X. D. Du, W. Li, S. M. Ruan, L. Li, Cus-heterogeneous ensemble-based financial distress prediction for imbalanced dataset with ensemble feature selection, Appl. Soft Comput., 97, (2020), 106758. https://doi.org/10.1016/j.asoc.2020.106758 doi: 10.1016/j.asoc.2020.106758
[36]	J. Sun, H. Fujita, Y. J. Zheng, W. G. Ai, Multi-class financial distress prediction based on support vector machines integrated with the decomposition and fusion methods, Inf. Sci., 559 (2021), 153–170. https://doi.org/10.1016/j.ins.2021.01.059 doi: 10.1016/j.ins.2021.01.059
[37]	H. Wang, X. Liu, Undersampling bankruptcy prediction: Taiwan bankruptcy data, PLoS One, 16 (2021), e0254030. https://doi.org/10.1371/journal.pone.0254030 doi: 10.1371/journal.pone.0254030
[38]	X. Wu, S. Du, An analysis on financial statement fraud detection for chinese listed companies using deep learning, IEEE Access, 10 (2022), 22516–22532. https://doi.org/10.1109/ACCESS.2022.3153478 doi: 10.1109/ACCESS.2022.3153478
[39]	J. Liu, J. Li, Risk analysis of textile industry foreign investment based on deep learning, Comput. Intell. Neurosci., 2022 (2022), 3769670. https://doi.org/10.1155/2022/3769670 doi: 10.1155/2022/3769670
[40]	P. Craja, A. Kim, S. Lessmann, Deep learning for detecting financial statement fraud, Decis. Support Syst., 139 (2020), 113421. https://doi.org/10.1016/j.dss.2020.113421 doi: 10.1016/j.dss.2020.113421
[41]	T. Mikolov, K. Chen, G. Corrado, J. Dean, Efficient estimation of word representations in vector space, arXiv preprint, (2013), arXiv: 1301.3781. https://doi.org/10.48550/arXiv.1301.3781
[42]	S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural Comput., 9 (1997), 1735–80. https://doi.org/10.1162/neco.1997.9.8.1735 doi: 10.1162/neco.1997.9.8.1735
[43]	S. J. Yu, D. L. Liu, W. F. Zhu, Y. Zhang, S. M. Zhao, Attention-based lstm, gru and cnn for short text classification, J. Intell. Fuzzy Syst., 39 (2020), 333–340. https://doi.org/10.3233/Jifs-191171 doi: 10.3233/Jifs-191171
[44]	A. Galassi, M. Lippi, P. Torroni, Attention in natural language processing, IEEE Trans. Neural Networks Learn. Syst., 32 (2021), 4291–4308. https://doi.org/10.1109/TNNLS.2020.3019893 doi: 10.1109/TNNLS.2020.3019893
[45]	V. Mnih, N. Heess, A. Graves, Recurrent models of visual attention, arXiv preprint, (2014), arXiv: 1406.6247. https://doi.org/10.48550/arXiv.1406.6247
[46]	D. Bahdanau, K. Cho, Y. Bengio, Neural machine translation by jointly learning to align and translate, arXiv preprint, (2014), arXiv: 1409.0473. https://doi.org/10.48550/arXiv.1409.0473
[47]	Z. Yang, D. Yang, C. Dyer, X. He, A. Smola, E. Hovy, Hierarchical attention networks for document classification, in Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, ACL, San Diego, USA, (2016), 1480–1489.
[48]	J. Sun, H. Fujita, P. Chen, H. Li, Dynamic financial distress prediction with concept drift based on time weighting combined with adaboost support vector machine ensemble, Knowledge-Based Syst., 120 (2017), 4–14. https://doi.org/10.1016/j.knosys.2016.12.019 doi: 10.1016/j.knosys.2016.12.019
[49]	S. Zhao, K. Xu, Z. Wang, C. Liang, W. Lu, B. Chen, Financial distress prediction by combining sentiment tone features, Econ. Modell., 106 (2022), 105709. https://doi.org/10.1016/j.econmod.2021.105709 doi: 10.1016/j.econmod.2021.105709
[50]	J. B. Jing, W. W. Yan, X. M. Deng, A hybrid model to estimate corporate default probabilities in China based on zero-price probability model and long short-term memory, Appl. Econ. Lett., 28 (2021), 413–420. https://doi.org/10.1080/13504851.2020.1757611 doi: 10.1080/13504851.2020.1757611
[51]	Y. Chen, Convolutional Neural Network for Sentence Classification, Master's thesis, University of Waterloo, 2015.
[52]	A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, et al., Attention is all you need, arXiv preprint, (2017), arXiv: 1706.03762. https://doi.org/10.48550/arXiv.1706.03762

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)