Audit Risk Prediction Using Deep Learning Algorithms: A Novel Approach to Enhancing Auditors’ Professional Judgment

Subject Areas : Behavioral reactions in the capital market

Rasha Mhmood Ali ¹ , Hamidreza Azizi ² , Siraj Razooqi Abbas ³ , Rahman Saedi ⁴

1 - Department of Accounting, Faculty of International Affairs, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran
2 - Department of Accounting, Ardabil Branch, Islamic Azad University, Ardabil, Iran
3 - Department of Accounting, Faculty of Finance and Accounting, Wasit University, Kut, Iraq
4 - Department of Accounting, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran

Received: 2025-06-29 Accepted : 2025-07-29 Published : 2025-08-11

Keywords: Audit Risk Prediction, Deep Learning, Support Vector Machine (SVM), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Auditors’ Professional Judgment, Financial and Non-Financial Data Analysis.,

Abstract :

Purpose: This study aims to develop an effective predictive model for audit risk using advanced deep learning algorithms and to evaluate its implications in supporting auditors’ professional judgment. Addressing the limitations of traditional audit risk assessment methods, this research explores how machine learning techniques-specifically deep neural networks-can enhance accuracy and reliability in detecting
audit risk.

Methodology: This applied research was conducted on a sample of 150 companies listed on the Tehran Stock Exchange during the period 2013–2023. Data were collected from reliable financial sources, including Codal, financial statements, and Central Bank statistics.

Audit risk was defined as a binary variable based on the occurrence of Type I and Type II errors in audit opinions. The study initially examined 40 financial, audit-specific, and macroeconomic predictors, of which 25 were selected through independent t-tests for final model implementation.

Three deep learning models were applied:

- Support Vector Machine (SVM)

- Convolutional Neural Network (CNN)

- Recurrent Neural Network (RNN)

Model evaluation was conducted using accuracy measures and confusion matrices across 50 random splits of training (75%) and testing (25%) data.

Findings: The RNN algorithm achieved the highest prediction accuracy (96.4%), followed by SVM (89.6%) and CNN (85.8%). RNN also had the lowest false negative rate (2.7%), reflecting superior capacity in capturing sequential patterns and complex nonlinear interactions among variables. Significant predictors included company size, liquidity, profitability, financial expertise of the board, audit independence, and inflation rate. Variables such as auditor change, audit firm ranking, and auditor specialization also showed significant relationships with audit risk.

Conclusions: The results suggest that deep learning algorithms—especially RNN—can serve as powerful tools for enhancing audit quality by enabling more precise audit risk assessments. The predictive models developed can support auditors in reducing judgment errors, optimizing audit planning, and improving stakeholder confidence in financial reporting.

From a practical standpoint, regulatory bodies (e.g., Audit Organization, Securities Exchange Organization) can leverage such models for enhanced oversight and policymaking. Investors and financial analysts may also benefit from more reliable audit risk indicators in their decision-making processes.

 

References:

اعتمادی، حسین؛ آذر، عادل؛ ناظمی اردکانی، مهدی (1389). بررسی نقش تخصص حسابرس در صنعت بر مدیریت واقعی سود و عملکرد عملیاتی آتی. دانش حسابداری، 1(1)، ص2-9.
حیدی‌نژاد، قدرت‌اله؛ جمشیدی نوید، بابک؛ قنبری، مهرداد (1400). ارتباط بین اثربخشی کمیته حسابرسی و ریسک حسابرسی. تحقیقات حسابداری و حسابرسی، 13(52)، ص185-206.
دارابی، رویا؛ علیزاده پیرعلی؛ فرخ، دبستانی، محمد (1399). مروری بر ادبیات نظری تجربی در خصوص تأثیر شرایط اقتصاد کلان بر ریسک حسابرسی. چشم‌انداز حسابداری و مدیریت، 3(37)، ص12-18.
زارعیان، حسین؛ حجازی، محسن (1402). ارائه مدل ریسک حسابرسی مالیاتی در طرح جامع مالیاتی با رویکرد ترکیبی ISM-ANP. پژوهش‌های تجربی حسابداری، 13(1)، ص61-80.
غلامی، حسین؛ دشتبانی، قاسم (1400). بررسی رابطه بین کیفیت حسابرسی و ریسک حسابرسی در شرکت‌های پذیرفته شده بورس اوراق بهادار تهران. چشم‌انداز حسابداری و مدیریت، 4(49)، ص122-135.
فریدی مایوان، مریم؛ مومنی، علیرضا؛ مقدم، عبدالکریم (1401). آزمون ارزیابی ریسک حسابرسی تحت تأثیر افشای مسئولیت اجتماعی شرکت‌ها. دانش حسابداری و حسابرسی مدیریت، 11(43)، ص321-309.
مهدوی، غلامحسین؛ نمازی، نویدرضا (1390). رتبه‌بندی عوامل مؤثر بر خطر حسابرسی با استفاده از تکنیکTOPSIS . دانش حسابرسی، 11(45) ص28-50.
نمازی، محمد؛ ابراهیمی، شهلا (1391). بررسی ارتباط بین ساختار رقابتی بازار محصول و بازده سهام. دانش حسابداری مالی، 2(3)، ص9-27.
همتی، داود؛ طلوعی اشلقی، عباس (1401). ارزیابی ریسک حسابرسی با استفاده رویکرد داده‌کاوی مبتنی بر شبکه‌های عصبی در شرکت‌های پذیرفته شده در بورس اوراق بهادار تهران. دانش حسابرسی، 5(89)، ص245-216.
همتی، داود؛ عرب‌صالحی، مهدی؛ طلوعی اشلقی، عباس (1399). ارزیابی ریسک حسابرسی با استفاده از رویکرد داده‌کاوی (مطالعه موردی: تسهیلات بانکی). دانش حسابداری و حسابرسی مدیریت، 9(34)، ص157-167.
Al-Din, S., Al-Hayik, Y. & Abu-Naser, S.S. (2023). Neural Network-Based Audit Risk Prediction: A Comprehensive Study. International Journal of Academic Engineering Research, 7(10), p. 43-51.
Becker, C.L., DeFond, M.L., Jiambalvo, J. & Subramanyam, K.R. (1998). The effect of audit quality on earnings management. Contemporary Accounting Research, 15(1), p. 1-24.
Behn, B.K., Choi, J.H. & Kang, T. (2008). Audit quality and properties of analyst earnings forecasts. The Accounting Review, 83(2), p. 327-349.
Blankley, J.S., Hurtt, R.K. & MacGregor, J.C. (2012). Abnormal audit fees and restatements. Auditing: A Journal of Practice & Theory, 31(1), p. 79-105. https://doi.org/10.2308/ajpt-50560
Bockus, K. & Gigler, F. (1998). A theory of auditor resignation. Journal of Accounting Research, 36(2), p. 191-208. https://doi.org/10.2307/2491474
Caramanis, C. & Lennox, C. (2008). Audit effort and earnings management. Journal of accounting and economics, 45(1), p. 116-138.
Chen, S., Sun, L. & Wu, D. (2010). Client importance, institutional improvements, and audit quality in China: An office and individual auditor level analysis. Accounting Review, 85(1), p. 127-158. https://doi.org/10.2308/accr.2010.85.1.127
Choi, J.H. & Wong, T.J. (2007). Auditors’ governance functions and legal environments: An international investigation. Contemporary Accounting Research, 24(1), p. 13-46.
DeAngelo, L.E. (1981). Auditor size and audit quality. Journal of Accounting and Economics, 3(3),
p. 183-199.
Dechow, P. M., Sloan, R. G., & Sweeney, A.P. (1995). Detecting earnings management: A new approach. Journal of Accounting Research, 33(2), p. 193-225.
DeFond, M. & Zhang, J. (2014). A review of archival auditing research. Journal of Accounting and Economics, 58(2), p. 275-326.
Deng, M., Lu, T. & Wen, X. (2023). Does Audit Risk Disclosure Improve or Impair Audit Quality and Investment Efficiency? http://dx.doi.org/10.2139/ssrn.4540951.
Fan, J.P. & Wong, T.J. (2005). Do external auditors perform a corporate governance role in emerging markets? Evidence from East Asia. Journal of Accounting Research, 43(1), p. 35-72.
Glover, S.M., Jiambalvo, J. & Kennedy, J. (2000). Analytical procedures and audit-planning decisions. Auditing: A Journal of Practice & Theory, no. 19, p. 27-46.
Glover, S.M., Prawitt, D.F., Schultz Jr., J.J. & Zimbelman, M.F. (2003). A test of changes in auditors' fraud-related planning judgments since the issuance of SAS No. 82. Auditing: A Journal of Practice & Theory, no. 22, p. 237-251.
Hagiha, Z. (2012). Application of Delphi method for determining the affecting factors upon audit risk model. Management Science Letters, 2(1), p. 379-390.
http://dx.doi.org/10.5267/ j.msl. 2011.07.006.
Hammersley, J.S., Johnstone, K. & Kadous, K. (2011). How do audit seniors respond to heightened fraud risk? Auditing: A Journal of Practice & Theory, 30(3), p. 81-101.
Hogan, C.E. & Wilkins, M.S. (2008). Evidence on the audit risk model: Do auditors increase audit fees in the presence of internal control deficiencies? Contemporary Accounting Research, 25(1), p. 219-242.
Huang, A.H., Zang, A.Y. & Zheng, R. (2014). Evidence on the information content of text in analyst reports. The Accounting Review, 89(5), p. 2151-2180. https://doi.org/10.2308/accr-50833
Jiambalvo, J. & Waller, W. (1984). Decomposition and assessments of audit risk. Auditing: A Journal of Practice & Theory, no. 3, p. 80-88.
Khurana, I.K. & Raman, K.K. (2004). Litigation risk and the financial reporting credibility of Big 4 versus non‐Big 4 audits: Evidence from Anglo‐American countries. The Accounting Review, 79(2), p. 473-495.
Kim, J.B., Lee, J.J. & Park, J.C. (2015). Audit quality and the market value of cash holdings: The case of office-level auditor industry specialization. Auditing: A Journal of Practice & Theory, 34(2),
p. 27-57.
Krishnan, G.V. (2003). Does Big 6 auditor industry expertise constrain earnings management? Accounting horizons, no. 17, p. 1-16.
Krishnan, J., Li, C. & Wang, Q. (2013). Auditor industry expertise and cost of equity. Accounting Horizons, 27(4), p. 667-691.
Kurt, A.C. (2022). Audit Risk and the Benefits of Employing Specialist Auditors: Evidence from Firms with Major Government Customers. http://dx.doi.org/10.2139/ssrn.4199751.
MohammadRezaei, F. & Mohd‐Saleh, N. (2018). Audit report lag: the role of auditor type and increased competition in the audit market. Accounting & Finance, 58(3), p. 885–920.
https://doi.org/10.1111/acfi.12237.
O. Abu-Mehsen, D., Abu Nasser, M.S., Hasaballah, M.A. & Abu-Naser, S.S. (2023). Predicting
Audit Risk Using Neural Networks: An In-depth Analysis. International Journal of Academic Information Systems Research, 7(10), p. 48-56.
O'Donnell, E. & Schultz, J.J. (2003). The influence of business-process-focused audit support software on analytical procedures judgments. Auditing: A Journal of Practice & Theory, no. 22, p. 265-279.
Palmrose, Z.-V. (1986). Audit fees and auditor size: Further evidence. Journal of Accounting Research, 24(1), p. 97-110. https://doi.org/10.2307/2490806
Porcuna-Enguix, L., Bustos-Contell, E., Serrano-Madrid, J. & Labatut-Serer, G. (2021). Constructing the Audit Risk Assessment by the Audit Team Leader When Planning: Using Fuzzy Theory. Mathematics, no. 9. https://doi.org/10.3390/math9233065
Robin, A., Wu, Q. & Zhang, H. (2017). Auditor quality and debt covenants. Contemporary Accounting Research, 34(1), p. 154-185.
Simunic, D.A. & Stein, M.T. (1996). Litigation risk and audit pricing. Auditing: A Journal of Practice & Theory, 15(2), p. 119-134.
Simunic, D.A. (1980). The pricing of audit services: Theory and evidence. Journal of Accounting Research, 18(1), p. 161-190.
Stanley, J.D. (2011). Is the audit fee disclosure a leading indicator of clients’ business risk? Auditing: A Journal of Practice & Theory, p. 30(3). https://doi.org/10.2139/ssrn.1750589
Watts, R.L. & Zimmerman, J.L. (1983). Agency problems, auditing, and the theory of the firm: Some evidence. Journal of law and Economics, 26(3), p. 613-633.
Wilks, T.J. & Zimbelman, M.F. (2004). Decomposition of fraud-risk assessments and auditors' sensitivity to fraud cues. Contemporary Accounting Research, no. 21, p. 719-745.
Wu, Y. & Wilson, M. (2016). Audit quality and analyst forecast accuracy: The impact of forecast horizon and other modeling choices. Auditing: A Journal of Practice & Theory, 35(2), p. 167-185.
Zimbelman, M.F. (1997). The effects of SAS No. 82 on auditors’ attention to fraud risk factors and audit planning decisions. Journal of Accounting Research, no.35, p. 75-97.