A Multi-Stage Machine Learning Approach to Financial Distress Prediction: The Role of Corporate Social Responsibility and Corporate Governance with Emphasis on the Audit Committee

Alidoosti, Parisa; Dastgir, Mohsen; Soroushyar, Afsaneh

[Home ] [Archive]

[ فارسی ]

Main Menu

Home

Journal Information

Articles archive

For Authors

For Reviewers

Registration

Contact us

Site Facilities

Search in website

Receive site information

year 17, Issue 68 (2026)

fa 2026, 17(68): 68-82

Back to browse issues page

A Multi-Stage Machine Learning Approach to Financial Distress Prediction: The Role of Corporate Social Responsibility and Corporate Governance with Emphasis on the Audit Committee

Parisa Alidoosti¹

, Mohsen Dastgir ^*¹

, Afsaneh Soroushyar¹

1- Department of Accounting, Isf.C., Islamic Azad University, Isfahan, Iran.

Abstract: (13 Views)

Timely prediction of financial distress plays a critical role in reducing uncertainty, enhancing strategic decision-making, and improving investor confidence. The present study was designed to use a multi-stage machine learning approach to predict financial distress while examining the predictive roles of corporate social responsibility and corporate governance indicators, with particular emphasis on the audit committee. The study is applied in terms of objective and adopts a descriptive-correlational research design. The research sample consists of 112 firms listed on the Tehran Stock Exchange during 2016–2024, selected through a systematic elimination procedure. The results of the Random Forest algorithm reveal that ownership structure represents the most influential corporate governance dimension, whereas audit committee composition has the lowest predictive importance. Furthermore, among the Ridge, Lasso, Adaptive Lasso, and Elastic Net algorithms, Adaptive Lasso demonstrates the highest predictive accuracy. The findings indicated that all three indicators—corporate social responsibility, corporate governance, and audit committee—had a negative predictive association with financial distress. Furthermore, corporate governance demonstrated a greater negative predictive contribution to the selected model compared with corporate social responsibility and the audit committee.These results emphasize the importance of integrating managerial and monitoring indicators with advanced machine learning approaches to enhance financial distress prediction.

Article number: 4

Keywords: Financial Distress, Corporate Social Responsibility, Corporate Governance Mechanisms, Audit Committee, Machine Learning.

Full-Text [PDF 864 kb] (33 Downloads)

Type of Study: Applicable | Subject: Special

References

1. Adjapong Afrifa, G. (2016). Net working capital, cash flow and performance of UK SMEs. Review of Accounting and Finance 15(1): 21-44.

2. Aldubhani, M.A.Q., J. Wang, T. Gong & R.A. Maudhah. (2022). Impact of working capital management on profitability: evidence from listed companies in Qatar. Journal of Money and Business 2(1): 70-81.

3. Altman, E.I., M. Iwanicz-Drozdowska, E.K. Laitinen & A. Suvas. (2017). Financial distress prediction in an international context: A review and empirical analysis of Altman’s Z-Score model. Journal of International Financial Management and Accounting 28: 131-171.

4. Appuhami, R., & S. Tashakor. (2017). The impact of audit committee characteristics on CSR disclosure: An analysis of Australian firms. Australian Accounting Review 27: 400-420.

5. Arouri, M., M. Gomes & K. Pukthuanthong. (2019). Corporate social responsibility and M&A uncertainty. Journal of Corporate Finance 56: 176-198.

6. Carbo-Valverde, S., F. Rodriguez-Fernandez & G.F. Udell. (2016). Trade credit, the financial crisis, and SME access to finance. Journal of Money, Credit and Banking 48: 113-143.

7. Coelho, R., S. Jayantilal & J.J. Ferreira. (2023). The impact of social responsibility on corporate financial performance: A systematic literature review. Corporate Social Responsibility and Environmental Management 30(4): 1535-1560.

9. El Naqa, I. & M.J. Murphy. (2015). What is machine learning? In Machine Learning in Radiation Oncology: Theory and Applications: 3-11. Cham: Springer International Publishing.

10. Fariha, R., M.M. Hossain & R. Ghosh. (2022). Board characteristics, audit committee attributes and firm performance: empirical evidence from emerging economy. Asian Journal of Accounting Research 7(1): 84-96.

11. Farooq, M., A.A. Humayon, M. Imran Khan & S. Ali. (2022). Ownership structure and financial constraints: Evidence from an emerging market. Managerial Finance 48(7): 1007-1028.

12. Gabrielli, G., A. Melioli & F. Bertini. (2026). Corporate financial distress prediction: a machine learning approach in the era of big data. Journal of Accounting & Organizational Change 22(7): 31-65.

13. Habib, A., M.D. Costa, H.J. Huang, M.B.U. Bhuiyan & L. Sun. (2020). Determinants and consequences of financial distress: review of the empirical literature. Accounting & Finance 60: 1023-1075.

14. Kabir, R., & H. Minh Thai. (2017). Does corporate governance shape the relationship between corporate social responsibility and financial performance? Pacific Accounting Review 29(2): 227-258.

15. Li, X., J.B. Kim, H. Wu & Y. Yu. (2021). Corporate social responsibility and financial fraud: The moderating effects of governance and religiosity. Journal of Business Ethics 170(3): 557-576.

16. Lu, Q., Y. Deng, B. Liu & J. Chen. (2023). Promoting supply chain financing performance of SMEs based on the extended resource-based perspective. Journal of Business & Industrial Marketing 38(9): 1865-1879.

17. Meng, Q., X. Zheng & S. Wang. (2024). Corporate governance and financial distress in China: a multi-dimensional nonlinear study based on machine learning. Pacific-Basin Finance Journal 88: 102549.

18. Nguyen, V.C., & T.N.T. Huynh. (2023). Characteristics of the board of directors and corporate financial performance: Empirical evidence. Economies 11(2): 53.

19. Powell, R.J., D.V. Dinh, N.T. Vu & D.H. Vo. (2024). Accounting-based variables as an early warning indicator of financial distress in crisis and non-crisis periods. International Journal of Finance & Economics 29(4): 4105-4124.

20. Sakulpolphaisan, E., & S. Hensawang. (2022). Impact of audit committee and financial performance on financial distress prediction: An empirical study of the listed companies in the Market for Alternative Investment (MAI). Cuadernos de Economía 45(127): 128-139.

21. Song, Y., M. Jiang, S. Li & S. Zhao. (2024). Class-imbalanced financial distress prediction with machine learning: Incorporating financial, management, textual, and social responsibility features into index system. Journal of Forecasting 43(3): 593-614.

22. Suganda, T.R., & J. Kim. (2023). An empirical study on the relationship between corporate social responsibility and default risk: Evidence in Korea. Sustainability 15(4): 3644.

23. Tron, A., M. Dallocchio, S. Ferri & F. Colantoni. (2023). Corporate governance and financial distress: lessons learned from an unconventional approach. Journal of Management and Governance 27(2): 425-456.

24. Yazdanfar, D., & P. Ohman. (2020). Financial distress determinants among SMEs: empirical evidence from Sweden. Journal of Economic Studies 47(3): 547-560.

26. Younas, N., Sh. UdDin, T. Awan & M.Y. Khan. (2021). Corporate governance and financial distress: Asian emerging market perspective. Corporate Governance 21(4): 702-715.

Send email to the article author

Add your comments about this article

Mendeley

Zotero

RefWorks

Alidoosti P, Dastgir M, Soroushyar A. A Multi-Stage Machine Learning Approach to Financial Distress Prediction: The Role of Corporate Social Responsibility and Corporate Governance with Emphasis on the Audit Committee. fa 2026; 17 (68) : 4
URL: http://qfaj.mobarakeh.iau.ir/article-1-2952-en.html

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

year 17, Issue 68 (2026)

Back to browse issues page

Persian site map - English site map - Created in 0.2 seconds with 37 queries by YEKTAWEB 4732