This study builds a reproducible detector of earnings manipulation in Iraqi banks using a bank-year panel from 2010 to 2024 sourced from audited annual reports, IFRS 9 credit risk notes, Iraq Stock Exchange disclosures, and Central Bank of Iraq publications. The feature set aligns with banking mechanics discretionary loan loss provisioning residuals scaled by lagged loans, a three-year smoothing index between changes in NPL and provisions, asset growth, fee share dynamics, and leverage changes. The label flags the top quintile of discretionary provisioning within each year to focus on relative deviations. Data are winsorized within year, standardized on the training sample, and split chronologically into training 2010–2021 and testing 2022–2024. Two classifiers are compared a class-weighted logistic regression and a class-weighted SVM. Evaluation uses ROC-AUC, PR-AUC, F1, accuracy, and Brier score, with thresholds tuned on validation folds and probabilities calibrated. Results show that the SVM delivers stronger ranking and better operating tradeoffs than the logistic baseline when inputs are standardized and the decision threshold targets screening objectives. Out-of-sample gains appear in ROC-AUC and PR-AUC with a lower Brier score. Confusion matrices confirm higher specificity and controlled false alarms at useful recall. SHAP analysis validates economic interpretability delta leverage, asset growth, and DLLP drive the score, followed by fee share changes and smoothing. The framework supports an audit workflow that screens bank-years, routes alerts to document-level review of allowance movements and write-offs, and updates models annually with rolling windows while preserving time integrity and comparability.

earnings manipulation detection, Iraqi banks, discretionary provisioning, support vector machine, IFRS 9

Abusharbeh, M., & Zakarneh, E. N. (2024). Earnings manipulation behavior in the non-financial listed firms of Palestine: the implication of Beneish model. EuroMed Journal of Business.

Alakkari, K., Ali, B., Abotaleb, M., Abttan, R. A., & Dutta, P. K. (2024). advanced machine learning approaches for enhanced GDP nowcasting in Syria through comprehensive analysis of regularization techniques. Mesopotamian Journal of Big Data, 2024, 102-117.

Alakkari, K., Subhi, A. A., Alkattan, H., Kadi, A., Malinin, A., Potoroko, I., ... & El-kenawy, E. S. M. (2024). A Comprehensive Approach to Cyberattack Detection in Edge Computing Environments. Journal of Cybersecurity and Information Management (JCIM), 13(01), 69-75.

Alakkari, K., Yadav, S., & Mishra, P. (2022). Measuring economic uncertainty in Syria: An approach to the stochastic volatility model. Indian Journal of Economics and Development, 18(2), 281-291.

Ali, B., Alakkari, K., Abotaleb, M., Mijwil, M. M., & Dhoska, K. (2024). MLP and RBF algorithms in finance: predicting and classifying stock prices amidst economic policy uncertainty. Mesopotamian Journal of Big Data, 2024, 48-67.

Dbouk, B., & Zaarour, I. (2017). Towards a machine learning approach for earnings manipulation detection. Asian Journal of Business and Accounting, 10(2), 215-251.

Divya, D., Bhasi, V. M., & Arunkumar, O. N. (2025). Detection of earnings manipulation in financial reports: a data-driven approach. International Journal of Accounting, Auditing and Performance Evaluation, 21(3-4), 499-512.

G. Harb, E., Nasrallah, N., El Khoury, R., & Hussainey, K. (2023). Applying Benford's law to detect accounting data manipulation in the pre-and post-financial engineering periods. Journal of applied accounting research, 24(4), 745-768.

Grammatikos, T., & Papanikolaou, N. I. (2021). Applying Benford’s law to detect accounting data manipulation in the banking industry. Journal of Financial Services Research, 59(1), 115-142.

Hamed, R. S., Al-Shattarat, W. K., Al-Shattarat, B. K., & Mejri, M. (2024). Exploring the linkages between anti-money laundering guidelines and earnings manipulation techniques. Humanities and Social Sciences Communications, 11(1), 1-10.

Khatun, A., Ghosh, R., & Kabir, S. (2022). Earnings manipulation behavior in the banking industry of Bangladesh: the strategical implication of Beneish M-score model. Arab Gulf Journal of Scientific Research, 40(3), 302-328.

Mangala, D., & Singla, N. (2021). Earnings Management in Banking Industry: A Systematic Review of Literature. SCMS Journal of Indian Management, 18(1).

Maniatis, A. (2022). Detecting the probability of financial fraud due to earnings manipulation in companies listed in Athens Stock Exchange Market. Journal of Financial Crime, 29(2), 603-619.

Nguyen, T. T. H., Ibrahim, S., & Giannopoulos, G. (2023). Detecting earnings management: a comparison of accrual and real earnings manipulation models. Journal of Applied Accounting Research, 24(2), 344-379.

Nguyen, T. T., Nguyen, H. T. T., & Nguyen, N. T. H. (2023). Examine manipulation of financial statements of commercial banks–Evidence from an emerging country. In Analytics in Finance and Risk Management (pp. 281-291). CRC Press.

Nyakarimi, S. (2022). Probable earning manipulation and fraud in banking sector. Empirical study from East Africa. Cogent Economics & Finance, 10(1), 2083477.

Sharif, D. M. J. (2023). Detecting Earnings Manipulation Practice by the M-Score Model: Evidence from the Listed Power Companies of Bangladesh.

Svabova, L. (2021). Detecting the manipulation of earnings in the company: triangulation of methods. In SHS Web of Conferences (Vol. 92, p. 02061). EDP Sciences.

Tahmina, A., & Naima, J. (2016). Detection and analysis of probable earnings manipulation by firms in a developing country. Asian Journal of Business and Accounting, 9(1), 59-82.

Vladu, A. B., Amat, O., & Cuzdriorean, D. D. (2017). Truthfulness in accounting: How to discriminate accounting manipulators from non-manipulators. Journal of business ethics, 140(4), 633-648.

Zaarour, B. D. I. (2017). Financial statements earnings manipulation detection using a layer of machine learning. International Journal of Innovation, Management and Technology, 8(3), 172-179.

Bishop, C. M. (2006). Pattern recognition and machine learning. Springer.

Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder–decoder for statistical machine translation. arXiv preprint arXiv:1406.1078.

Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.

Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning (2nd ed.). Springer.

Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. International Conference on Learning Representations (ICLR).

Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems (NeurIPS), 30.

Niculescu-Mizil, A., & Caruana, R. (2005). Predicting good probabilities with supervised learning. Proceedings of the 22nd International Conference on Machine Learning, 625–632.

Platt, J. (1999). Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in Large Margin Classifiers, 61–74.

Vapnik, V. N. (1998). Statistical learning theory. Wiley.

Aggelopoulos, E., Georgopoulos, A., & Kolias, G. (2025, March). Monthly income patterns and earnings management in banking. In Accounting Forum (Vol. 49, No. 2, pp. 498-522). Routledge.