From Prediction to Explanation: Earnings Management Analysis Using Explainable Machine Learning and the SHAP Approach

Document Type : Original Article

Authors

1 Department of Accounting, Ard.C., Islamic Azad University, Ardabil, Iran

2 Department of Mathematics, Ard.C., Islamic Azad University, Ardabil, Iran

10.22091/jdaid.2026.16254.1070

Abstract

Objective: This study aims to develop and evaluate an explainable machine learning framework for detecting earnings management and to compare its predictive performance with traditional accrual-based approaches in the Iranian capital market. Beyond improving prediction accuracy, the study explains the nonlinear relationships between financial, corporate governance, and market variables associated with earnings management using explainable artificial intelligence techniques.

Method: This applied study adopts a descriptive-analytical design based on machine learning and explainable artificial intelligence. The statistical population consists of firms listed on the Tehran Stock Exchange during 2016–2025. After applying the sample selection criteria, 1,620 firm-year observations were analyzed. Five machine learning algorithms—XGBoost, Random Forest, Support Vector Machine, Decision Tree, and Logistic Regression—were evaluated and compared with a traditional accrual-based approach. Model interpretation was performed using SHAP (SHapley Additive exPlanations), while predictive performance was assessed using Accuracy, Precision, Recall, F1-score, and AUC.

Results: XGBoost achieved the highest predictive performance, with an AUC of 0.90 and an F1-score of 0.86, significantly outperforming the traditional accrual-based approach and the other machine learning models. SHAP analysis revealed that operating cash flow volatility, financial leverage, market-to-book ratio, audit quality, and other financial and governance variables exert substantial nonlinear effects on earnings management prediction.

Conclusions: The findings demonstrate that explainable machine learning not only improves predictive performance but also enhances model transparency and theoretical interpretation. The proposed framework provides valuable analytical support for auditors, regulators, investors, and corporate decision-makers seeking to strengthen financial reporting quality, regulatory oversight, and earnings management monitoring.

Keywords

Main Subjects

References

Adadi, A., & Berrada, M. (2018). Peeking inside the black box: A survey on explainable artificial intelligence. IEEE Access, 6, 52138–52160. https://doi.org/10.1109/ACCESS.2018.2870052
Attia, E. F., Diab, A., Ezz Eldeen, H. H., & Abdou, H. A. (2025). Unravelling non linear dynamics between audit committees and financial reporting quality in emerging markets. Cogent Business and Management, 12(1). https://doi.org/10.1080/23311975.2025.2524045
Banerjee, A. K., Akhtaruzzaman, M., & Chatterjee, S. (2026). Earnings management: The influence of peer group and the corporate governance intervention. Journal of Accounting Literature, 48(1), 111–129. https://doi.org/10.1108/JAL-06-2023-0102
Bao, Y., & Datta, A. (2014). Simultaneously discovering and quantifying risk types from textual risk disclosures. Management Science, 60(6), 1371–1391. https://doi.org/10.1287/mnsc.2014.1930
Dechow, P. M., & Dichev, I. D. (2002). The quality of accruals and earnings: The role of accrual estimation errors. The Accounting Review, 77, 35–59. https://doi.org/10.2139/ssrn.277231
Dechow, P. M., Ge, W., Larson, C. R., & Sloan, R. G. (2010). Predicting material accounting misstatements. Contemporary Accounting Research, 28(1), 17–82. https://doi.org/10.1111/j.1911-3846.2010.01041.x
Dechow, P. M., Sloan, R. G., & Zang, A. Y. (2021). Earnings quality and earnings management: A review of the literature. Journal of Accounting and Economics, 71(2 to 3), 101–118. https://doi.org/10.15678/ier.2019.0504.03
Faccia, A. (2026). Explainable AI in Auditing: Bridging the gap between predictive fraud models and regulatory standards. Journal of Risk and Financial Management, 19(5), 311. https://doi.org/10.3390/jrfm19050311
Falahatkar, H., Ghojarbeigi, M., & Beytari, J. (2021). The effect of corporate governance on the relationship between earnings management and disclosure level in firms listed on the Tehran Stock Exchange. Journal of New Research Approaches in Management and Accounting, 5(17), 12–31. https://doi.org/10.2139/ssrn.2508727
Hashemi Golsefid, A., Lashgari, Z., & Hajihah, Z. (2021). Applying machine learning to develop a model for detecting accounting distortions. Accounting and Management Auditing Knowledge, 10(37), 271–283.
Healy, P. M., & Wahlen, J. M. (1999). A review of the earnings management literature and its implications for standard setting. Accounting Horizons, 13(4), 365–486. https://doi.org/10.2139/ssrn.156445
Huy, T. P., Hong, T. P., & Quoc, A. B. N. (2025). Leveraging tree based machine learning for predicting earnings management. Journal of International Commerce Economics and Policy, 16(2), 2550008. https://doi.org/10.1142/s1793993325500085
Imani, M., & Karimzadeh, R. (2025). Understanding various business strategy patterns and the tendency to use earnings management practices: Evidence from the Iranian capital market. Strategic Studies in Financial Management and Insurance, 2(1), 1–13. https://doi.org/10.22105/ssfmi.v1i1.70
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2021). An introduction to statistical learning. Springer.
Jensen, M. C., & Meckling, W. H. (2019). Theory of the firm: Managerial behavior, agency costs and ownership structure. In Corporate governance (pp. 77–132). Gower. https://doi.org/10.2139/ssrn.94043
Jones, J. J. (1991). Earnings management during import relief investigations. Journal of Accounting Research, 29(2), 193–228. https://doi.org/10.2307/2491047
Kasznik, R. (1999). On the association between voluntary disclosure and earnings management. Journal of accounting research, 37(1), 57–81. https://doi.org/10.2139/ssrn.15062
Khan, T., Hossain, S., Akhtar, R., Sanusi, Y., Nuhuyau, A., Zaw, T., & Alvi, J. (2025). Robustness of gradient boosted decision trees (XGBoost, LightGBM, and CatBoost) in detecting earnings management: Evidence from post-pandemic financial reporting. International Journal of Multi Discipline Science (IJ-MDS). https://doi.org/10.3390/toxins15100608
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774. https://doi.org/10.1109/iccv.1995.466919
Molnar, C. (2022). Interpretable machine learning. Lulu Press.
Phothong, L., Sukprasert, A., Boonlua, S., Chubsuwan, P., Seetha, N., & Kunsrison, R. (2026). An explainable voting ensemble framework for early warning forecasting of corporate financial distress. Forecasting, 8(1), 10. https://doi.org/10.3390/forecast8010010
Rejeb, A., Rejeb, K., & Treiblmaier, H. (2026). Explainable artificial intelligence in finance: A bibliometric and topic modeling analysis using BERTopic. Quality and Quantity, 1–25. https://doi.org/10.1007/s11135-026-02837-4
Roychowdhury, S. (2006). Earnings management through real activities manipulation. Journal of Accounting and Economics, 42(3), 335–370. https://doi.org/10.2139/ssrn.477941
Saadati, E., Yazdani, S., Khanmohammadi, M., & Gorjizadeh, D. (2025a). Analyzing the behavior of the pattern of factors affecting earnings management in organizations with the fraud diamond model using a mixed method. Applied Researches of Organizational Behavior, 2(2), 38–54.
Saadati, E., Yazdani, S., Khanmohammadi, M. H., & Gorjizadeh, D. (2024). Presentation of a quantitative model of factors affecting earnings management: Focusing on managers opportunistic manipulations of discretionary accruals. Business Marketing and Finance Open, 1(4). https://doi.org/10.61838/bmfopen.1.4.11
Saadati, E., Yazdani, S., Khanmohammadi, M. h., & Gorjizadeh, D. (2025b). Presenting a model for opportunistic earnings management: factors, motivations and techniques. Management Accounting, 17(63), 17–44.
Saghafi, A., Bolou, G., & Dana, M. M. (2015). The relationship between earnings quality and information asymmetry. Experimental Accounting Research, 5(2), 1–16. https://doi.org/10.22051/jera.2015.625
Saghafi, A., & Pouriansab, A. (2010). Earnings management theory. Accounting and Auditing Research, 2(6), 34–53. https://doi.org/10.22034/iaar.2010.105157
Vahrami, V., & Saradari, A. (2026). A comparative evaluation of econometric and machine learning models in forecasting Iran's economic growth. Finance and Economic Policy, 2(4), 1-14. https://doi.org/10.22034/efp.2026.733978
Yahaya, O. A. (2025). Board independence and earnings management. Journal of Business Ethics and Education. https://doi.org/10.2139/ssrn.5099242
Jafari, M., Akbari, A. H., & Akhavan, P. (2026). Leveraging Generative AI to Drive Supply Chain Resilience and Sustainable Performance: A Mediation Framework for Next-Generation Supply Chains. Technology in Society, 103444. doi: 10.1016/j.techsoc.2026.103444 
Jafari, M., Akhavan, P., & Akbari, A. H. (2026). A Data-Driven Multi-Objective optimization framework for dynamic job shop scheduling with order Acceptance, inventory and Energy-Aware decisions. Computers & Industrial Engineering, 111886. doi: 10.1016/j.cie.2026.111886 
Jafari, M., & Akbari, A. H. (2026). Deep reinforcement learning for dynamic cellular manufacturing systems with deterioration effect. International Journal of Computing Science and Mathematics, 23(1), 39-80. https://doi.org/10.1504/IJCSM.2026.151974 
Jafari, M., & Akbari, A. H. (2026). Efficient algorithms for cellular manufacturing systems with deterioration effect and inventory (case study: stone paper factory). International Journal of Industrial and Systems Engineering, 52(3), 345-383. https://doi.org/10.1504/IJISE.2026.152157 
Jafari, M., Akhavan, P., & Akbari, A. H. (2026). Enhancing supply chain agility and performance through big data analytics: the role of digitalization and top management support. International Journal of Productivity and Performance Management, 1-22. https://doi.org/10.1108/IJPPM-06-2025-0557 
Tavakkoli-Moghaddam, R., Akbari, A. H., Tanhaeean, M., Moghdani, R., Gholian-Jouybari, F., & Hajiaghaei-Keshteli, M. (2024). Multi-objective boxing match algorithm for multi-objective optimization problems. Expert Systems with Applications, 239, 122394. https://doi.org/10.1016/j.eswa.2023.122394 
Journal of Data Analytics and Intelligent Decision-making

Articles in Press, Accepted Manuscript
Available Online from 30 September 2026

Files

Share

How to cite

Statistics