Predicting fraud in financial statements using supervised methods: An analytical comparison

Document Type : Research Paper

Authors

1 Department of Accounting, Zanjan Branch, Islamic Azad University, Zanjan, Iran

2 Department of Computer Engineering, Ardabil Branch, Islamic Azad University, Ardabil, Iran.

Abstract

The current era is known as the "age of information," and the capital market is built on information as the economy's primary engine. The system of financial statements of corporations, which is the most significant source of information used in the capital market, produces an information system called accounting. Fraud and manipulation in these financial statements raise corporate risk, erode investor confidence, and cast doubt on the objectivity of accounting experts. Owing to the significance of fraud, this study aims to offer a way to foretell the likelihood of fraud in the financial statements of businesses admitted to the Tehran Stock Exchange between 2014 and 2021. 180 enterprises listed on the stock exchange make up the statistical sample (532 years of companies - suspected fraud years and 908 years - of non-fraudulent companies). According to the independent auditor's assessment, the existence of dormant assets and items, the doubting of the assumption of continuity of activity, the presence of tax discrepancies with other tax areas, and the dearth of adequate performance tax reserves led to the selection of the companies suspected of fraud. 96 financial ratios have been compiled by examining the theoretical foundations and research. In this research, the supervised methods of support vector machine, K-nearest neighbor, Bayesian network, neural network, decision tree, logistic regression, random forest and the hybrid method (bagging) have been used. The results of the research showed that the performance evaluation criteria of precision, accuracy, sensitivity, and F-Measure and efficiency (ROC) and the accuracy result of the confusion matrix in the combined method (bagging) were 72.45, 61.21, 64.74, 62.93, 73.50, and 72.45 percent, respectively, which indicates the better performance and greater ability of this method to predict the possibility of fraud in financial statements compared to other proposed methods.

Keywords

[1] M. Belgiu and L. Dragut, Random forest in remote sensing: A review of applications and future directions. J. Photogram. Rem. Sen. 114 (2016), 24-31.
[2] C.B. Rjeily and G. Badr, A.H. El Hassani, and E. Andres, Medical data mining for heart diseases and the future of sequential mining in medical field, Machine Learning Paradigms, Springer, 2019, pp. 71–99.
[3] Committee of Audit Standards. Standards and Principles of Accounting and Auditing: Audit Standards, Audit Organisation Publications: Tehran, Iran, 2015.
[4] S. Dua and X. Du, Data mining and machine learning in cybersecurity, CRC Press, 2016.
[5] M. Ebrahimi and Sh. Khajavi, Modeling variables affecting fraud detection in financial statements through data mining techniques, Financ. Account. 33 (2017), 41–62.
[6] P. Goldmann and H. Kaufman, Anti-Fraud Risk and Control Workbook, John Wiley & Sons, 2009.
[7] S. Gupta and S.K. Mehta, Data mining-based financial statement fraud detection: Systematic literature review and meta-analysis to estimate data sample mapping of fraudulent companies against non-fraudulent companies, Glob. Bus. Rev. (2021), https://doi.org/10.1177/0972150920984857
[8] J. Han, M. Kamber, and J. Pei, Data Mining Concepts and Techniques, Third Edition, University. Ill. Urb. Mic. Kam. J. P. S. F. Uni., 2012.
[9] S. Hidayattullah, I. Surjandari, and E. Laoh, Financial statement fraud detection in Indonesia listed companies using machine learning based on meta-heuristic optimization, Int. Workshop Big Data In. Sec. (IWBIS). IEEE, 2020, pp. 79–84.
[10] H. Kamrani and B. Abedini, Formulation of financial statement fraud detection model using artificial neural network and support vector machine approaches in companies listed in Tehran Stock Exchange, J. Manag. Account. Audit. Knowl. 11 (2022), no. 41, 285–314.
[11] T. Kazemi, Identifying cases of fraud risk in financial statements of Iran and evaluating fraud detection methods, Doctoral thesis, 2016.
[12] A. Khorasani, Investigating the effects of applying auditing standards in information disclosure in fraudulent financial reporting, Doctoral thesis, 2017.
[13] M.J. Kranacher and R. Riley, Forensic Accounting and Fraud Examination, John Wiley & Sons, 2011.
[14] L.I. Kuncheva, Combining pattern classifiers: Methods and algorithms, John Wiley & Sons, 2014.
[15] K.M. Leung, Naive Bayesian classifier, Poly. Uni. Dep. Com. Science/Finance and Risk Engin. 2007 (2007), 123–156.
[16] Fraud, Occupational, A Report to the nations, ACFE: https://acfepublic. s3. us-west-2. Amazonas. com/2022+Report+ to+ the+ Nations. pdf, 8 (2023).
[17] N. Omar, Z.A. Johari, and M. Smith, Predicting fraudulent financial reporting using artificial neural network, J. Finan. Crime. 24 (2017), no. 2, 362–387.
[18] A. Pradhan, Support vector machine-a survey, Int. J. Emer. Tech. Adv. Engin. 2 (2012), no. 8, 82–85.
[19] Y. Park and D. Reeves, Deriving common malware behavior through graph clustering, In Proc. 6th ACM Symp. Info. Com. Commu. Sec., 2011, March, pp. 497–502.
[20] A.M.R. Nafchi and M. Dastgir, Proposing a Model for Identification of Risk Factors Affecting Fraud in Banks. Financ. Account. 41 (2018), 23-–45.
[21] M. Ramos, Auditors responsibility for fraud detection, J. Account. 195 (2003), no. 1, 28–36.
[22] P. Ranganathan, C.S. Pramesh, and R. Aggarwal, Common pitfalls in statistical analysis: Logistic regression, Perspect. Clinic. Res. 8 (2017), no. 3, 148.
[23] S. Rastatter, T. Moe, A. Gangopadhyay, and A. Weaver, Abnormal Traffic Pattern Detection in Real-Time Financial Transactions, Technical Report, EasyChair, 2019.
[24] M. Rezaei, M.N. Ardakani, and A.N. Sadrabadi, Fraud detection in financial statements through audit reports of financial statements, Manag. Account. 13 (2020), no. 45, 141—153.
[25] I. Sadgali, N. Sael, and F. Benabbou, Performance of machine learning techniques in the detection of financial frauds, Procedia Comput. Sci. 148 (2019), 45–54.
[26] A. Shinde, A. Sahu, D. Apley, and G. Rutger, Preimages for variation patterns from kernel PCA and bagging, Iie Trans. 46 (2014), no. 5, 429–456.
[27] E. Tashdidi, S. Sepasi, H. Etemadi, and A. Azar, A novel approach to prediction and detection of fraud in financial statements through bee colony optimisation algorithm. Account. Knowledge 12 (2019), 139-–167.
[28] W. Xiuguo and D. Shengyong, An analysis on financial statement fraud detection for Chinese listed companies using deep learning, IEEE Access 10 (2022), 22516–22532.
[29] J. Yao, Y. Pan, S. Yang, Y. Chen, and Y. Li, Detecting fraudulent financial statements for the sustainable development of the socio-economy in China: A multi-analytic approach, Sustainability 11 (2019), no. 6, 1579.
[30] J. Yao, J. Zhang, and L. Wang, A financial statement fraud detection model based on hybrid data mining methods, Int. Con. Art. Int. Big Data (ICAIBD) IEEE., 2018, May, pp. 57–61.
[31] M.Y. Alghiani, J.S. Bahri, S.J. Kangarlouei, and A.Z. Rezaei, Explaining financial tax cross reporting of companies: Hybrid method of classic data mining, ANFIS, and metaheuristic algorithms, Empir. Stud. Financ. Account. 18 (2021), no. 71, 89-–111.
[32] M.J.Z. Bahmanmiri and E.M. Kalebastani, Ranking the factors affecting financial fraud probability, according to audited financial statements, J. Empir. Res. Account. 6 (2016), no. 3, 1–18.
Volume 15, Issue 8
August 2024
Pages 259-272
  • Receive Date: 21 April 2023
  • Revise Date: 16 May 2023
  • Accept Date: 12 June 2023