Predicting Internal Control Deficiencies with Deep Learning: Evidence from IPO Review Records
DOI:
https://doi.org/10.54097/dztsxd66Keywords:
Internal Control Deficiency Prediction, IPO Rejection, Deep LearningAbstract
Internal control is a core governance mechanism for improving information quality and reducing information risk. Identification of internal control deficiencies (ICDs) based on annual report disclosures or audit opinions suffers from reporting lags and sparse positives. Leveraging China’s issuance regime, this study uses IPO rejection outcomes as proxy labels and builds a financial-ratio–based prediction model. Incorporating proxy information lifts PR-AUC and ROC-AUC over the baseline by 22.78% and 4.52%; a full-parameter search yields gains of 24.05% and 5.32%. Under fixed thresholds, F1, precision, and recall also rise. Interpretability analyses show that ROA, OPM, and PPE retain persistent importance in identifying high-risk firms. The approach advances label construction and methodology, and offers an operational tool to target regulatory inquiries, optimize audit procedures, and support firms’ internal control self-assessments, with clear policy and theoretical value.
Downloads
References
[1] Donelson D C, Ege M, McInnis J M. Internal control weaknesses and financial reporting fraud[J]. Auditing: A Journal of Practice & Theory, 2017, 36(3): 45-69.
[2] Boulhaga M, Bouri A, Elbardan H. The effect of internal control quality on real and accrual-based earnings management: Evidence from France[J]. Journal of Management Control, 2022, 33(4): 545-567.
[3] Liu C, Lin B. Deep-Learning-Based Prediction of Internal Control Deficiencies in Listed Firms: New Theories and Methods[J]. Accounting Research (China), 2024, (06): 119-134.
[4] Doyle J T, Ge W, McVay S E. Accruals quality and internal control over financial reporting[J]. The Accounting Review, 2007, 82(5): 1141-1170.
[5] Ashbaugh-Skaife H, Collins D W, Kinney W R Jr, LaFond R. The effect of SOX internal control deficiencies on firm risk and cost of equity[J]. Journal of Accounting Research, 2009, 47(1): 1-43.
[6] Kim J-B, Song B Y, Zhang L. Internal control weakness and stock price crash risk[J]. Accounting & Finance, 2019, 59(2): 1197-1233.
[7] Costello A M, Wittenberg-Moerman R. The impact of financial reporting quality on debt contracting: Evidence from internal control weakness reports[J]. Journal of Accounting Research, 2011, 49(1): 97-136.
[8] Chen H, Wang S, Yang D, Zhou N. COSO-based internal control and comprehensive enterprise risk management: Institutional background and research evidence from China[J]. Encyclopedia, 2025, 5(3): 106.
[9] Cheng Q, Goh B W, Kim J-B. Internal control and operational efficiency[J]. Contemporary Accounting Research, 2018, 35(2): 1102-1139.
[10] Lee J, Cho E, Choi H. The effect of internal control weakness on investment efficiency[J]. Journal of Applied Business Research, 2016, 32(3): 649-662.
[11] Doyle J T, Ge W, McVay S E. Determinants of weaknesses in internal control over financial reporting[J]. Journal of Accounting and Economics, 2007, 44(1-2): 193-223.
[12] Lin B, Lin D, Hu W, et al. A Goal-Oriented Internal Control Index[J]. Accounting Research (China), 2014, (08): 16-24.
[13] Lin B, Lin D, Xie F, et al. An Information-Disclosure-Based Internal Control Index[J]. Accounting Research (China), 2016, (12): 12-20.
[14] Dechow P M, Ge W, Larson C R, Sloan R G. Predicting material accounting misstatements[J]. Contemporary Accounting Research, 2011, 28(1): 17-82.
[15] Cecchini M, Aytug H, Koehler G J, Pathak P. Detecting management fraud in public companies[J]. Management Science, 2010, 56(7): 1146-1160.
[16] Perols J. Financial statement fraud detection: An analysis of statistical and machine learning algorithms[J]. Auditing: A Journal of Practice & Theory, 2011, 30(2): 19-50.
[17] Bao Y, Ke B, Li B, Yu Y J, Zhang J. Detecting accounting fraud in publicly traded U.S. firms using a machine learning approach[J]. Journal of Accounting Research, 2020, 58(1): 199-235.
[18] Craja P, Kim A, Lessmann S. Deep learning for detecting financial statement fraud[J]. Decision Support Systems, 2020, 139: 113421.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
