Iranian Journal of Accounting, Auditing and Finance

Iranian Journal of Accounting, Auditing and Finance

A Comparative Study of XGBoost and Artificial Neural Networks for Earnings Management Prediction

Document Type : Original Article

Authors
Maedeh Moayeri
Mohammad Arabmazar Yazdi
Vahid Menati
Department Of Accounting, Faculty Of Management and Accounting, Shahid Beheshti University, Tehran, Iran
10.22067/ijaaf.2026.47746.1579
Abstract
The present study was conducted to compare the accuracies for ANN and XGBoost algorithms on predicting earnings management in listed companies of Tehran Stock Exchange. Earnings management is one way for managers to mislead their stakeholders, which can result in financial losses; therefore, accurate detection methods are important for earnings management and beyond statistical models. The present study used 2016–2021 quarterly financial data from 103 publicly traded companies in basic metals, automotive, chemical, food and pharmaceutical producing industries (5076 year−firm). Discretionary accruals were used and calculated by the Kasznik model to capture earnings management and split them into three groups: Increasing Accruals (+1), Decreasing Accruals (-1), and Near-Zero Accrual (0). A Confusion Matrix was used to perform the model evaluation. The results showed that the XGBoost algorithm is significantly superior to the ANN with an overall accuracy of 98.4%. With very few errors, all earnings management categories XGBoost had near to perfect results. In contrast, ANN demonstrated significant weaknesses leading to an overall accuracy of 63.1%. The study found that the model performance of XGBoost can further predict earning management with more accuracy thereby securing a process for financial institutions. Inspired by the relatively rare occurrence of applying XGBoost model, used for trilateral classification of increasing, decreasing and near-zero earnings management in emerging markets including Tehran Stock Exchange. This research contributes significantly to the literature by demonstrating the superior predictive power of ensemble learning methods over traditional neural networks in detecting financial misconduct, which offers a robust, high-accuracy tool for regulators and investors to enhance market transparency and reduce financial risk.
Keywords
Artificial Neural Network (ANN)
Earnings Management
Kasznik Model
Machine Learning
XGBoost
Subjects
  1. Adomat, V., Ehrhardt, J., Kober, C., Ahanpanjeh, M. and Wulfsberg, J. P. (2023). A machine learning approach for revenue management in cloud manufacturing. Procedia CIRP, 118, pp. 342-347. https://doi.org/10.1016/j.procir.2023.06.059
  2. Ahmadpoor, A. and Montazeri, H. (2011). Type of earnings management and the impact of company size, ownership structure and corporate governance onearnings management. Journal of Accounting Advances, 3(2), pp. 1-35. https://doi.org/10.22099/jaa.2012
  3. Ali, A. A., Khedr, A. M., El-Bannany, M. and Kanakkayil, S. (2023). A powerful predicting model for financial statement fraud based on optimized XGBoost ensemble learning technique. Applied Sciences, 13(4), A. 2272. https://doi.org/10.3390/app13042272
  4. Artene, A. E. and Domil, A. E. (2025). Neural networks in accounting: bridging financial forecasting and decision support systems. Electronics, 14(5), p. 993. https://doi.org/10.3390/electronics14050993
  5. Boutaba, R., Salahuddin, M. A., Limam, N., Ayoubi, S., Shahriar, N., Estrada-Solano, F. and Caicedo, O. M. (2018). A comprehensive survey on machine learning for networking: evolution, applications and research opportunities. Journal of Internet Services and Applications, 9(1), pp. 1-99. https://doi.org/10.1186/s13174-018-0087-2
  6. Burzykowski, T., Geubbelmans, M., Rousseau, A. J. and Valkenborg, D. (2023). Validation of machine learning algorithms. American Journal of Orthodontics and Dentofacial Orthopedics, 164(2), pp. 295-297. https://doi.org/10.1016/j.ajodo.2023.05.007
  7. Chakri, P., Pratap, S. and Gouda, S. K. (2023). An exploratory data analysis approach for analyzing financial accounting data using machine learning. Decision Analytics Journal, 7(1), A. 100212. https://doi.org/10.1016/j.dajour.2023.100212
  8. Chen, X., Cho, Y. H., Dou, Y. and Lev, B. (2022). Predicting future earnings changes using machine learning and detailed financial data. Journal of Accounting Research, 60(2), pp. 467-515. https://doi.org/10.1111/1475-679X.12429
  9. Chen, X., Mao, Z. and Wu, C. (2025). Multi-class financial distress prediction based on feature selection and deep forest algorithm. Computational Economics, 66(4), pp. 2715-2754. https://doi.org/10.1007/s10614-024-10761-8
  10. DeAngelo, H., DeAngelo, L. and Skinner, D. J. (1996). Reversal of fortune dividend signaling and the disappearance of sustained earnings growth. Journal of financial Economics, 40(3), 341-371. https://doi.org/10.1016/0304-405X(95)00850-E
  11. Dechow, P. M., Sloan, R. G. and Sweeney, A. P. (1995). Detecting earnings management. Accounting Review, 70(2), pp. 193-225.
  12. Esfahanipour, A., Goodarzi, M. and Jahanbin, R. (2016). Analysis and forecasting of IPO underpricing. Neural Computing and Applications, 27(3), pp. 651-658. https://doi.org/10.1007/s00521-015-1884-1
  13. Faghani Makrani, K., Salehnejad, S. H. and Amin, V. (2016). Predicting earnings management based on modified jones model using artificial neural network model and genetic algorithm. Financial Engineering and Securities Management (Portfolio Management), 7(28), pp. 117-136.https://dorl.net/dor/20.1001.1.22519165.1395.7.28.7.2
  14. Fereydouni, F., Darabi, R. and Anvari Rostami, A. (2020). Application of artificial intelligence algorithms in predicting earnings smoothing. Financial Accounting and Auditing Research, 12(45), pp. 103-134.
  15. Hamidian, M. and Esmaeili, M.(2024).Forecasting earnings management using support vector machine and decision tree methods.Research in Accounting and Economic Sciences, 40(8), pp. 29-38.
  16. Hammami, A. and Hendijani Zadeh, M. (2022). Predicting earnings management through machine learning ensemble classifiers. Journal of Forecasting, 41(8), pp. 1639-1660. https://doi.org/10.1002/for.2885
  17. Hassani, H., Malekian Kallehbasti, E. and Kamyabi, Y. (2024). Explaining the earnings management prediction model using the hybrid of machine learning methods. Financial Accounting Research, 16(2), pp. 53-88. https://doi.org/10.22108/far.2025.143145.2076
  18. Healy, P. M. (1985). The effect of bonus schemes on accounting decisions. Journal of Accounting and Economics, 7(1-3), pp. 85-107. https://doi.org/10.1016/0165-4101(85)90029-1
  19. Healy, P. M. and Wahlen, J. M. (1999). A review of the earnings management literature and its implications for standard setting. Accounting Horizons, 13(4), pp. 365-383. https://doi.org/10.2308/acch.1999.13.4.365
  20. Huy, T. P., Hong, T. P. and Quoc, A. B. N. (2025). Leveraging tree-based machine learning for predicting earnings management. Journal of International Commerce, Economics and Policy, 16(02), A. 2550008. https://doi.org/10.1142/S1793993325500085
  21. Jain, E., Neeraja, J., Banerjee, B. and Ghosh, P. (2022). A diagnostic approach to assess the quality of data splitting in machine learning. ArXiv, Cornell University, Ithaca, New York. https://doi.org/10.48550/arXiv.2206.11721
  22. Jones, J. J. (1991). Earnings management during import relief investigations. Journal of Accounting Research, 29(2), pp. 193-228. https://doi.org/10.2307/2491047
  23. Kasznik, R. (1999). On the association between voluntary disclosure and earnings management. Journal of Accounting Research, 37(1), pp. 57-81. https://doi.org/10.2307/2491396
  24. Kordestani, G. and Tatli, R. (2014). Identification the efficient and opportunistic earnings management approaches in the earnings quality levels. Accounting and Auditing Review, 21(3), pp. 293-312 (In Persian).
  25. Liashchynskyi, P., and Liashchynskyi, P. (2019). Grid search, random search, genetic algorithm: a big comparison for NAS. ArXiv, Cornell University, Ithaca, New York. https://doi.org/10.48550/arXiv.1912.06059
  26. Maleki Kakler, H., Bahri Sales, J., Jabbarzadeh Kangarlooee, S., and Ashtab, A. (2021). Efficiency of statistical models and machine learning algorithms in predicting fraudulent financial reporting. Financial Economics, 15(54), pp. 267-292.
  27. Montazeri, M., and Khodamoradi, M. (2017). Investigating earnings management models in various industries. First National Conference on New Researches of Iran and the World in Management, Economics, Accounting and Humanities, Shiraz, Iran (In Persian).
  28. Mosalla Nejad, A., and Nazemi, A. (2019). Investigating the accuracy of financial information in Rahavard Novin database. 17th National Accounting Conference of Iran, Qom, Iran (In Persian).
  29. Muraina, I. (2022). Ideal dataset splitting ratios in machine learning algorithms: general concerns for data scientists and data analysts. In 7th international Mardin Artuklu scientific research conference, Adeniran Ogunsanya College of Education, Lagos, Nigeria (pp. 496-504).
  30. Patro, V. M., and Patra, M. R. (2014). Augmenting weighted average with confusion matrix to enhance classification accuracy. Transactions on Machine Learning and Artificial Intelligence, 2(4), pp. 77-91.
  31. Rahman, R. A., Masrom, S., Zakaria, N. B., Nurdin, E., and Abd Rahman, A. S. (2021). Prediction of earnings manipulation on Malaysian listed firms: A comparison between linear and tree-based machine learning. International Journal of Emerging Technology and Advanced Engineering, 11(8), pp. 111-120. https://doi.org/10.46338/ijetae0821_13
  32. Rahmani, A. and Bashirimanesh, N. (2013). Investigating the detection power of earnings management models. Accounting and Auditing Research, 5(19), pp. 54-73 (In Persian).
  33. Rahnama Roodposhti, F., Banimehdi, B., Rezaei, S., and Salehi, A. (2014). Evaluation of the ability and explanation of discretionary accruals models and discretionary revenue model for detecting earnings management. Journal of Financial Accounting and Auditing, 6(21), pp.1-22.
  34. Rashidpour, R., and Zare Bidaki, A. M. (2024). Spam page detection using xgboost algorithm. Iranian Journal of Electrical and Computer Engineering, 22(4), pp. 287-294 (In Persian).
  35. Ronen, T., and Yaari, V. (2002). On the tension between full revelation and earnings management: a reconsiderastion of the revelation principle. Journal of Accounting, Auditing & Finance, 17(4), pp. 273-294. https://doi.org/10.1177/0148558X0201700401
  36. Saberi Gahrouei, P., Saberi Gahrouei, S., and Daghani, R. (2023). Investigating the difference in the quality of audit and profit management in bankrupt and healthy companies: matched groups method using machine learning. Professional Auditing Research, 3(10), pp. 56-71. https://doi.org/10.22034/jpar.2023.562123.1117
  37. Saghafi, A., and Pouryanasab, A. (2010). Theory of earnings management. Accounting and Auditing Research, 2(6), pp. 34-53 (In Persian).
  38. Salehi, A., and Salehi, B. (2015). A review of earnings management measurement models: discretionary accruals and discretionary revenue. Knowledge of Accounting and Management Auditing, 4(16), pp. 103-118 (In Persian).
  39. Salehi, M., and Farokhi Pile Rood, L. (2018). Predicting of earnings management using neural network and decision tree. Quarterly Journal of Financial Accounting and Auditing Research, 10(37), pp. 1-24 (In Persian).
  40. Sarker, I. H., Kayes, A. S. M., Badsha, S., Alqahtani, H., Watters, P., and Ng, A. (2020). Cybersecurity data science: an overview from machine learning perspective. Journal of Big Data, 7(1), p. 41. https://doi.org/10.1186/s40537-020-00318-5
  41. Sarmad, Z., Bazargan, A., and Hejazi, E. (2004). Research methods in behavioral sciences. Tehran: Agah Publication, Tehran, Iran, pp. 7-132 (In Persian).
  42. Scott, W. R. (2015). Financial accounting theory. Seventh Edition. Pearson, United States: Canada Cataloguing, Canada.
  43. Siekelova, A. (2021). Historical development of earnings management models. In SHS Web of Conferences (Vol. 92, p. 02058). EDP Sciences, Les Ulis cedex A France.
  44. Sun, L., and Rath, S. (2010). Earnings management research: a review of contemporary research methods. Global Review of Accounting and Finance, 1(1), pp. 121-135.
  45. Veganzones, D., and Séverin, E. (2025). Earnings management visualization and prediction using machine learning methods. International Journal of Accounting Information Systems, 56, A. 100743. https://doi.org/10.1016/j.accinf.2025.100743
  46. Wiens, M., Verone‐Boyle, A., Henscheid, N., Podichetty, J. T., and Burton, J. (2025). A tutorial and use case example of the eXtreme gradient boosting (XGBoost) artificial intelligence algorithm for drug development applications. Clinical and Translational Science, 18(3), A. e70172. https://doi.org/10.1111/cts.70172
  47. Yadav, S., and Shukla, S. (2016). Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification. In 2016 IEEE 6th International conference on advanced computing (IACC) (pp. 78-83). IEEE. New York
  48. Ying, X. (2019). An overview of overfitting and its solutions. In Journal of physics: Conference series (Vol. 1168, p. 022022). IOP Publishing, Bristol, England. https://doi.org/10.1088/1742-6596/1168/2/022022
Send comment about this article
Enter Name.
Enter a valid email address.
Enter a vaid affiliation.
Enter comments (At leaset 10 words)
CAPTCHA Image
Enter Security Code Correctly.