THE POWER OF MACHINE LEARNING MODELS IN EARLY DETECTION OF FRAUDULENT FINANCIAL STATEMENTS: THE EXAMPLE OF BORSA ISTANBUL

Öz

Detecting and preventing fraudulent financial statements is crucial to maintaining the reliability of financial markets, as such statements undermine stakeholders and disrupt healthy market functioning. This study develops an artificial intelligence–supported model to detect fraudulent financial statements of companies listed on Borsa Istanbul. Using financial and non-financial data, Random Forest, Naive Bayes, and K-Star classification analyses were applied to firms identified as preparing fraudulent statements according to Capital Markets Board bulletins between 01.01.2022 and 01.01.2025. Results indicate that the K-Star algorithm achieved 99% accuracy in detecting fraudulent statements one period in advance, compared with 92% for Random Forest and 62% for Naive Bayes. Specifically, K-Star classified fraudulent firms with 100% accuracy and non-fraudulent firms with 98% accuracy. These results highlight that combining financial and non-financial indicators offers a novel and effective approach to fraud detection and provides significant contributions to the literature.

Anahtar Kelimeler

• Fraudulent financial statement
• Financial fraud detection
• Machine learning
• Borsa Istanbul

Proje Numarası

yok

Etik Beyan

No ethical clearance required.

THE POWER OF MACHINE LEARNING MODELS IN EARLY DETECTION OF FRAUDULENT FINANCIAL STATEMENTS: THE EXAMPLE OF BORSA ISTANBUL

Öz

Finansal tabloların hileli düzenlenmesinin tespiti ve önlenmesi, finansal piyasaların güvenilirliğinin korunması açısından kritik öneme sahiptir. Hileli tablolar, tüm paydaşlara zarar vermekte ve piyasaların sağlıklı işleyişini bozmaktadır. Bu çalışma, Borsa İstanbul’da işlem gören şirketlerin hileli finansal tablolarının tespitine yönelik yapay zekâ destekli bir model geliştirmeyi amaçlamaktadır. Bu kapsamda, 01.01.2022–01.01.2025 döneminde Sermaye Piyasası Kurulu bültenlerine göre hileli finansal tablo hazırladığı belirlenen şirketler üzerinde finansal ve finansal olmayan verilerle Random Forest, Naive Bayes ve K-Star sınıflandırma analizleri uygulanmıştır. Bulgular, K-Star algoritmasının hileli finansal tabloları bir dönem önceden %99 doğrulukla tespit ettiğini; Random Forest’ın %92, Naive Bayes’in ise %62 doğruluk sağladığını göstermektedir. En yüksek performansa sahip K-Star algoritması, hileli şirketleri %100, hilesizleri ise %98 doğrulukla sınıflandırmıştır. Bu sonuçlar, finansal ve finansal olmayan verilerin birlikte kullanımının hileli finansal tabloların tespitinde yenilikçi ve etkili bir yaklaşım sunduğunu ortaya koymaktadır.

Anahtar Kelimeler

• hileli finansal tablo
• finansal hilelerin tesbiti
• makine öğrenmesi
• Borsa İstanbul

Proje Numarası

yok

Etik Beyan

Etik kurul izni gerekmemektedir.

Kaynakça

1. Abu-Dabaseh, F., Khtatbeh, M. M., Al'Ararah, K., & Alassuli, A. (2025). Exploring the role of digital transformation in mitigating accounting fraud: A cybersecurity perspective. International Review of Management and Marketing, 15(3), 398. https://doi.org/10.32479/irmm.18490
2. Aksoy, B. (2021). Predicting financial statement frauds using machine learning methods and logistic regression: The case of Borsa Istanbul. Journal of Finance Letters, 115, 27–58. https://doi.org/10.33203/mfy.733855
3. Ashtiani, M. N., & Raahemi, B. (2023). An efficient resampling technique for financial statements fraud detection: A comparative study. In 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME). (pp. 1–7). IEEE. https://doi.org/10.1109/ICECCME57830.2023.10253185
4. ACFE (Association of Certified Fraud Examiners). (2024). Occupational fraud 2024: A report to the nations. https://www.acfe.com/-/media/files/acfe/pdfs/rttn/2024/2024-report-to-the-nations.pdf
5. Beasley, M. S. (1996). An empirical analysis of the relation between the board of director composition and financial statement fraud. The Accounting Review, 71(4), 443–465. https://www.jstor.org/stable/248566
6. Beaver, W. H. (1966). Financial ratios as predictors of failure. Journal of Accounting Research, 4, 71–111. https://www.jstor.org/stable/2490171
7. Blanquero, R., Carrizosa, E., Ramírez-Cobo, P., & Sillero-Denamiel, M. R. (2021). Variable selection for Naïve Bayes classification. Computers and Operations Research, 135, 105456. https://doi.org/10.1016/j.cor.2021.105456
8. CMB (Capital Markets Board of Türkiye). (2025). Bülten [Bulletin]. https://www.spk.gov.tr/Bulten

9. Carpenter, T. D. (2007). Audit team brainstorming, fraud risk identification, and fraud risk assessment: Implications of SAS No. 99. The Accounting Review, 82(5), 1119–1140. https://doi.org/10.2308/accr.2007.82.5.1119
10. Chen, H., Hu, S., Hua, R., & Zhao, X. (2021). Improved Naive Bayes classification algorithm for traffic risk management. EURASIP Journal on Advances in Signal Processing, 2021, 30. https://doi.org/10.1186/s13634-021-00742-6
11. Chen, S. (2016). Detection of fraudulent financial statements using the hybrid data mining approach. SpringerPlus, 5, 89. https://doi.org/10.1186/s40064-016-1707-6
12. Chen, S., Goo, Y. J. J., & Shen, Z. D. (2014). A hybrid approach of stepwise regression, logistic regression, support vector machine, and decision tree for forecasting fraudulent financial statements. The Scientific World Journal, 2014, 968712. https://doi.org/10.1155/2014/968712
13. Chimonaki, C., Papadakis, S. P., Vergos, K., & Shahgholian, A. (2019). Identification of financial statement fraud in Greece by using computational intelligence techniques. In N. Mehandjiev & B. Saadouni (Eds.), Enterprise applications, markets and services in the finance industry (Lecture Notes in Business Information Processing, Vol. 345, pp. 39–52). Springer. https://doi.org/10.1007/978-3-030-19037-8_3
14. Code of Civil Procedure. (2011). Law No. 6100, Official Journal No. 27836
15. Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37–46. https://doi.org/10.1177/001316446002000104
16. Cotton, D. L. (2002, October 20). Fixing CPA ethics can be an inside job. The Washington Post. https://www.washingtonpost.com/archive/opinions/2002/10/20/fixing-cpa-ethics-can-be-an-inside-job/b7441564-e0a6-431b-9280-8c27c6267ebc/
17. Deng, Q. (2009). Application of support vector machine in the detection of fraudulent financial statements. In 2009 4th International Conference on Computer Science & Education, (pp. 1056–1059). IEEE. https://doi.org/10.1109/ICCSE.2009.5228542
18. Ebrahim, M., Sedky, A. A. H., & Mesbah, S. (2023). Accuracy assessment of machine learning algorithms used to predict breast cancer. Data, 8(2), Article 35. https://doi.org/10.3390/data8020035
19. Firayani, F. (2026). Analysis of the effectiveness of the integrated digital audit & financial control system in minimizing fraud risk and improving corporate liquidity efficiency. Research in Finance and Accounting, 1(1), 1–9.
20. Garcia-Gallego, A., & Mures-Quintana, M. J. (2012). Business failure prediction models: Finding the connection between their results and the sampling method. Economic Computation and Economic Cybernetics Studies and Research, 3, 157–168.
21. Jaafar, M. A. (2025). The impact of artificial intelligence in detecting manipulations in financial statements. Futurity Economics & Law, 5(2), 51–72. https://doi.org/10.57125/FEL.2025.06.25.03
22. Jackins, V., Vimal, S., Kaliappan, M., & Lee, M. Y. (2021). AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes. The Journal of Supercomputing, 77, 5198–5219. https://doi.org/10.1007/s11227-020-03481-x
23. Kara, S., & Karan, L. (2023). Fraud audit approaches and a case study. Denetişim, 14(28), 75–87. https://doi.org/10.58348/denetisim.1233039
24. Kara, S., & Özcan, P. (2025). Detecting accounting fraud in Borsa Istanbul: A logistic regression approach based on the Beneish model and SMOTE. Journal of Accounting and Finance, (107), 89–114. https://doi.org/10.25095/mufad.1686877
25. Kasztelnik, K., & Jermakowicz, E. K. (2024). Financial statement fraud detection in the digital age. The CPA Journal, 94(3/4), 32–39.
26. Kiracı, M. (2005). The role of fraud risk assessment and fraud detection in the effectiveness of audit and a study on audit firms in Turkey. Perspective on Accounting and Auditing, (14), 103–126. https://dergipark.org.tr/tr/download/article-file/1869599
27. Kırda, K., & Katkat-Özçelik, M. (2021). Identifying the companies with the risk of financial statement fraud by data mining. Journal of Accounting and Taxation Studies, 14(2), 609–639. https://doi.org/10.29067/muvu.802703
28. Kirkos, E., Spathis, C., & Manolopoulos, Y. (2007). Data mining techniques for the detection of fraudulent financial statements. Expert Systems with Applications, 32(2007), 995–1003. https://doi.org/10.1016/j.eswa.2006.02.016
29. Koçak, H. (2022). Performance comparison of classification algorithms in rainfall prediction. Journal of Intelligent Systems: Theory and Applications, 5(1), 16–26. https://doi.org/10.38016/jista.979285
30. Li, X., Xu, W., & Tian, X. (2014, October). How to protect investors? A GA-based DWD approach for financial statement fraud detection [Paper presentation]. 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 3548–3554. https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=6974480
31. Lin, C. C., Chiu, A., Huang, S. Y., & Yen, D. C. (2015). Detecting the financial statement fraud: The analysis of the differences between data mining techniques and experts' judgments. Knowledge-Based Systems, 89, 459–470. https://doi.org/10.1016/j.knosys.2015.08.011
32. Lokanan, M., Tran, V., & Vuong, N. H. (2019). Detecting anomalies in financial statements using machine learning algorithm: The case of Vietnamese listed firms. Asian Journal of Accounting Research, 4(2), 181–201. https://doi.org/10.1108/AJAR-09-2018-0032
33. McKee, T. E. (2009). A meta-learning approach to predicting financial statement fraud. Journal of Emerging Technologies in Accounting, 6(1), 5–26. https://doi.org/10.2308/jeta.2009.6.1.5
34. Naidu, G., Zuva, T., & Sibanda, E. M. (2023). A review of evaluation metrics in machine learning algorithms. In R. Silhavy, & P. Silhavy (Eds.), Lecture notes in networks and systems: Vol. 724. Artificial intelligence application in networks and systems (pp. 15–25). Springer. https://doi.org/10.1007/978-3-031-35314-7_2
35. Painuli, S., Elangovan, M., & Sugumaran, V. (2014). Tool condition monitoring using K-star algorithm. Expert Systems with Applications, 41(2014), 2638–2643. https://doi.org/10.1016/j.eswa.2013.11.005
36. Perols, J. (2011). Financial statement fraud detection: An analysis of statistical and machine learning algorithms. Auditing: A Journal of Practice & Theory, 30(2), 19–50. https://doi.org/10.2308/ajpt-50009
37. PDP (Public Disclosure Platform). (2025). KAP bildirim sorgu [Public disclosure notification inquiry]. https://www.kap.org.tr/tr/bildirim-sorgu
38. Ravisankar, P., Ravi, V., Rao, G. R., & Bose, I. (2011). Detection of financial statement fraud and feature selection using data mining techniques. Decision Support Systems, 50(2), 491–500. https://doi.org/10.1016/j.dss.2010.11.006
39. Rezaee, Z. (2005). Causes, consequences, and deterrence of financial statement fraud. Critical Perspectives on Accounting, 16(2005), 277–298. https://doi.org/10.1016/S1045-2354(03)00072-8
40. Riany, M., Sukmadilaga, C., & Yunita, D. (2021). Detecting fraudulent financial reporting using artificial neural network. Journal of Accounting Auditing and Business, 4(2), 60–69. https://doi.org/10.24198/jaab.v4i2.34914
41. Sarker, I. H. (2021). Machine learning: Algorithms, real-world applications and research directions. SN Computer Science, 2, 160, 1-21. https://doi.org/10.1007/s42979-021-00592-x
42. Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing and Management, 45(2009), 427–437. https://doi.org/10.1016/j.ipm.2009.03.002
43. Song, X. P., Hu, Z. H., Du, J. G., & Sheng, Z. H. (2014). Application of machine learning methods to risk assessment of financial statement fraud: Evidence from China. Journal of Forecasting, 33(8), 611–626. https://doi.org/10.1002/for.2294
44. Temponeras, G. S., Alexandropoulos, S. A. N., Kotsiantis, S. B., & Vrahatis, M. N. (2019). Financial fraudulent statements detection through a deep dense artificial neural network. In 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), (pp.1–5). IEEE. https://doi.org/10.1109/IISA.2019.8900741
45. Turkish Commercial Code. (2011). Law No. 6102, Official Journal No. 27846.
46. Vakharia, V., Pandya, S., & Patel, P. (2018). Tool wear rate prediction using discrete wavelet transform and K-star algorithm. Life Cycle Reliability and Safety Engineering, 7, 115–125. https://doi.org/10.1007/s41872-018-0057-5
47. Xiuguo, W., & Shengyong, D. (2022). An analysis on financial statement fraud detection for Chinese listed companies using deep learning. IEEE Access, 10, 22516–22532. https://doi.org/10.1109/ACCESS.2022.3153478
48. Yeh, C. C., Chi, D. J., Lin, T. Y., & Chiu, S. H. (2016). A hybrid detecting fraudulent financial statements model using rough set theory and support vector machines. Cybernetics and Systems, 47(4), 261–276. https://doi.org/10.1080/01969722.2016.1158553
49. Yue, D., Wu, X., Shen, N., & Chu, C. H. (2009). Logistic regression for detecting fraudulent financial statement of listed companies in China. In 2009 International Conference on Artificial Intelligence and Computational Intelligence (pp.104-108). IEEE. https://doi.org/10.1109/AICI.2009.421