Volume 33, Issue 65 (2025)
J Tax Res 2025, 33(65): 1-45 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Ahmadpour A, Jafari S M, Sarraf F. Modeling tax evasion of related party transactions A hybrid approach of graph mining and deep neural network. J Tax Res 2025; 33 (65) :1-45
URL: http://taxjournal.ir/article-1-2362-en.html
URL: http://taxjournal.ir/article-1-2362-en.html
1- Iranian National Tax Administration , Amin57ah@yahoo.com
2- Islamic Azad university
2- Islamic Azad university
Abstract: (78 Views)
Tax evasion based on related party transactions is a new strategy in tax evasion that is carried out through legal transactions, such as transactions between a group of companies that have heterogeneous, complex, and hidden interaction relationships for tax evasion. Existing studies cannot effectively identify tax evasion behaviors of related parties because the machine learning-based audit method can detect the abnormal financial status of individuals with high accuracy and efficiency. However, it is helpless when faced with heterogeneous, complex, and hidden interaction relationships and cannot identify tax evasion groups with related party transactions. The hybrid of graph mining and deep neural network approaches has the ability to detect anomalies in complex organizational structures. In this study, 1,780 companies with related party transactions, including 523 companies located in free trade zones and 1,257 companies located outside free trade zones, which have a common board member and economic activity of production or trade, were selected. In this study, financial and tax data from tax returns and the systems of the Iranian Tax Administration from 2016 to 2019 were used. This study is practical in terms of purpose. Python software and the NetworkX package were used to estimate the model. To predict tax evasion in related party transactions, three algorithms were used: Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Multilayer Perceptron Neural Network (MLP) in deep mode. To identify suspicious groups, three steps were taken; first: detecting tax rate differences, matching the topological pattern, and identifying tax burden anomalies; second: experimental tests based on data from 16,756 related party transaction purchases and sales in the country; third: estimating the coefficients and the relationship between the topological pattern in the two cases of profit retention and profit transfer based on the graph mining approach and deep neural network. The results show that both profit retention and profit shifting exist in tax evasion of related party transactions. However, based on the results, the intensity of the profit retention relationship in tax evasion of related party transactions is stronger than the profit shifting relationship. Based on the results, the graph mining approach was more accurate than the logit, probit, and linear probability models.
Type of Study: Research |
Subject:
Accounting
Received: 2024/04/27 | Accepted: 2025/05/31 | Published: 2025/05/31
Received: 2024/04/27 | Accepted: 2025/05/31 | Published: 2025/05/31
References
1. Tselykh, A., Knyazeva, M., Popkova, E., Durfee, A., & Tselykh, A. (2016, July). An Attributed Graph Mining Approach to Detect Transfer Pricing Fraud. Proceedings of the 9th International Conference on Security of Information and Networks )72-75). New York: Associate for Computing Machinery. [DOI:10.1145/2947626.2947655]
2. Al-Hagery, M. A. (2019). Extracting Hidden Patterns from Dates' Product Data Using a Machine Learning Technique. IAES International Journal of Artificial Intelligence, 8(3), 1-20. [DOI:10.11591/ijai.v8.i3.pp205-214]
3. Arab Mazar, A., Bagheri, B., & Jafar Parvar, M. (2013). Tax Approach to Transfer Pricing and Its Investigation in Iran. Tax Research Paper, 22(21), 9-38. [in Persian]
4. Asadi Yusufabad, M., Pifeh, A., & Ahmadzadeh, H. (1401). The Effect of Transactions with Related Parties on Company Value with an Emphasis on Social Responsibility. Accounting, Auditing and Financial Services in Islamic Environments, 1, 2(2), 100-129. [in Persian]
5. Cameron, A. C., & Trivedi, P. K. (2005). Microeconometrics Methods and Applications. Cambridge: Cambridge University Press. [DOI:10.1017/CBO9780511811241]
6. Chen, K., Zhou, Y., & Dai, F. (2015). An LSTM-Based Method for Stock Returns Prediction: A Case Study of China Stock Market. 2015 IEEE International Conference on Big Data (Big Data)(2823-2824). New York: IEEE Publication. [DOI:10.1109/BigData.2015.7364089]
7. Chong, E., Han, C., & Park, F. C. (2017). Deep Learning Networks for Stock Market Analysis and Prediction: Methodology, Data Representations, And Case Studies. Expert Systems with Applications, 83, 187-205. [DOI:10.1016/j.eswa.2017.04.030]
8. Tian, F., Lan, T., Chao, K. M., Godwin, N., Zheng, Q., Shah, N., & Zhang, F. (2016). Mining Suspicious Tax Evasion Groups in Big Data. IEEE Transactions on Knowledge and Data Engineering, 28(10), 2651-2664. [DOI:10.1109/TKDE.2016.2571686]
9. Gao, P., Zhang, R., & Yang, X. (2020). The Application of Stock Index Price Prediction with Neural Network. Mathematical and Computational Applications, 25(3), 53-69. [DOI:10.3390/mca25030053]
10. Garderodbari, M., Dadashi I., Mohseni Maleki, B., & Zabihi A. (1402). Predicting Tax Evasion of Legal Taxpayers with an Emphasis on Economic Components, Taxpayers and Tax Auditors; Relying on Artificial Intelligence. Tax Research Paper, 32(58), 131-164. [in Persian] [DOI:10.61186/taxjournal.32.58.6]
11. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Feedforward Networks. Deep Learning, 1, 161-217.
12. Gudelek, M. U., Boluk, S. A., & Ozbayoglu, A. M. (2017). A Deep Learning Based Stock Trading Model With 2-D CNN Trend Detection. In 2017 IEEE Symposium Series on Computational Intelligence (SSCI) (1-8). New York: IEEE. [DOI:10.1109/SSCI.2017.8285188]
13. Hazra, T., & Anjaria, K. (2022). Applications of Game Theory in Deep Learning: A Survey. Multimedia Tools and Applications, 81(6), 8963-8994. [DOI:10.1007/s11042-022-12153-2]
14. Heij, C. (2004). Econometric Methods with Applications in Business and Economics. Oxford: Oxford University Press. [DOI:10.1093/oso/9780199268016.001.0001]
15. Hensher, D. A., & Greene, W. H. (2003). The Mixed Logit Model: The State of Practice. Transportation, 30, 133-176. [DOI:10.1023/A:1022558715350]
16. Ruan, J., Yan, Z., Dong, B., Zheng, Q., & Qian, B. (2019). Identifying Suspicious Groups of Affiliated-Transaction-Based Tax Evasion in Big Data. Information Sciences, 477, 508-532. [DOI:10.1016/j.ins.2018.11.008]
17. Javadian Kotanaie, A., Pouraghajan Sarhamami, A., & Hosseini Shirvani, M. (2019). Presenting a Tax Fraud Detection Model Based on the Combination of the Improved ID3 Decision Tree Algorithm and Multilayer Perceptron Neural Networks. Management Accounting, 13(46), 53 -70. [in Persian]
18. Ji, L., Zou, Y., He, K., & Zhu, B. (2019). Carbon Futures Price Forecasting Based with ARIMA-CNN-LSTM Model. Procedia Computer Science, 162, 33-38. [DOI:10.1016/j.procs.2019.11.254]
19. Klassen, K. J., Lisowsky, P., & Mescall, D. (2017). Transfer Pricing: Strategies, Practices, and Tax Minimization. Contemporary Accounting Research, 34(1), 455-493. [DOI:10.1111/1911-3846.12239]
20. Hsu, K. W., Pathak, N., Srivastava, J., Tschida, G., & Bjorklund, E. (2014). Data Mining Based Tax Audit Selection: A Case Study of a Pilot Project at the Minnesota Department of Revenue. In Real World Data Mining Applications (221-245). Cham: Springer International Publishing. [DOI:10.1007/978-3-319-07812-0_12]
21. Karhunen, J., Raiko, T., & Cho, K. (2015). Unsupervised Deep Learning: A Short Review. Advances in Independent Component Analysis and Learning Machines, 2015, 125-142. [DOI:10.1016/B978-0-12-802806-3.00007-5]
22. Kolaczyk, E. D., & Csárdi, G. (2014). Statistical Analysis of Network Data with R (65). New York: Springer. [DOI:10.1007/978-1-4939-0983-4]
23. Liu, L., Schmidt-Eisenlohr, T., & Guo, D. (2020). International Transfer Pricing and Tax Avoidance: Evidence from Linked Trade-Tax Statistics in the United Kingdom. Review of Economics and Statistics, 102(4), 766-778. [DOI:10.1162/rest_a_00871]
24. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep Learning. Nature, 521(7553), 436-444. [DOI:10.1038/nature14539]
25. Lee, S. I., & Yoo, S. J. (2020). Threshold-based Portfolio: The Role of the Threshold and Its Applications. The Journal of Supercomputing, 76(10), 8040-8057. [DOI:10.1007/s11227-018-2577-1]
26. Leite, R. A., Gschwandtner, T., Miksch, S., Kriglstein, S., Pohl, M., Gstrein, E., & Kuntner, J. (2017). Eva: Visual Analytics to Identify Fraudulent Events. IEEE Transactions on Visualization and Computer Graphics, 24(1), 330-339. [DOI:10.1109/TVCG.2017.2744758]
27. Li, J., Wang, X., & Wu, Y. (2020). Can Government Improve Tax Compliance by Adopting Advanced Information Technology? Evidence from the Golden Tax Project III in China. Economic Modelling, 93, 384-397. [DOI:10.1016/j.econmod.2020.08.009]
28. Li, Y., & Dai, W. (2020). Bitcoin Price Forecasting Method Based on CNN-LSTM Hybrid Neural Network Model. The Journal of Engineering, 2020(13), 344-347. [DOI:10.1049/joe.2019.1203]
29. Livieris, I. E., Kiriakidou, N., Stavroyiannis, S., & Pintelas, P. (2021). An Advanced CNN-LSTM Model for Cryptocurrency Forecasting. Electronics, 10(3), 1-16. [DOI:10.3390/electronics10030287]
30. Livieris, I. E., Pintelas, E., & Pintelas, P. (2020). A CNN-LSTM Model for Gold Price Time-Series Forecasting. Neural Computing & Applications, 32(23), 17351-17360. [DOI:10.1007/s00521-020-04867-x]
31. Long, J. S., & Freese, J. (2006). Regression Models for Categorical Dependent Variables Using Stata (7). College Station: Stata Press.
32. Ferrantino, M. J., Liu, X., & Wang, Z. (2012). Evasion Behaviors of Exporters and Importers: Evidence from the US-China Trade Data Discrepancy. Journal of International Economics, 86(1), 141-157. [DOI:10.1016/j.jinteco.2011.08.006]
33. Maddala, G. S. (1983). Introduction to Econometrics (3rd Ed.). Ohio: Formerly Ohio State University
34. Myerson, R. B. (2013). Game Theory. Cambridge, MA: Harvard University Press.
35. Namazi, M., & Sadeghzadeh Maharloui, M. (2017). Investigating the Usefulness of the Relief Variable Selection Method in Improving the Results of Tax Evasion Prediction Using Data Mining. Applied Research in Financial Reporting, 7(13), 44-70. [in Persian]
36. Narahari, Y. (2014). Game Theory and Mechanism Design (4). Toh Tuck Link: World Scientific Publishing. [DOI:10.1142/8902]
37. Nasl Mousavi, H., Hosseini Shirvani, M., & Nazarpour, M. (1399). Presenting a Tax Evasion Prediction Model Based on ID3 Decision Tree Algorithm and Bayesian Network. Tax Research Paper, 28(45), 59-87. [in Persian]
38. OECD. (2017). Shining Light on the Shadow Economy: Opportunities and Threats. Retrieved 20 February from https://www.oecd.org/tax/crime/shining-light-on-the-shadow-economy-opportunities -and-threats.pdf [DOI:10.1787/e0a5771f-en]
39. Oliva, R. (2004). Model Structure Analysis Through Graph Theory: Partition Heuristics and Feedback Structure Decomposition. System Dynamics Review: The Journal of the System Dynamics Society, 20(4), 313-336. [DOI:10.1002/sdr.298]
40. González, P. C., & Velásquez, J. D. (2013). Characterization and Detection of Taxpayers with False Invoices Using Data Mining Techniques. Expert Systems with Applications, 40(5), 1427-1436. [DOI:10.1016/j.eswa.2012.08.051]
41. Pourzaker Arabani, S., & Ebrahimpour Komleh, H. (2018). Optimizing Cash Demand Forecasting of Atms in the Country's Banking Network Using LSTM Deep Recurrent Neural Network. Operations Research in Its Applications, 16(3), 69-88. [in Persian]
42. Wu, R. S., Ou, C. S., Lin, H. Y., Chang, S. I., & Yen, D. C. (2012). Using Data Mining Technique to Enhance Tax Evasion Detection Performance. Expert Systems with Applications, 39(10), 8769-8777. [DOI:10.1016/j.eswa.2012.01.204]
43. Rahimi Kia, I., Mohammadi, Sh., & Ghazanfari, M. (2014). Detection of Tax Evasion Using Hybrid Intelligent System. Research Journal of Taxation, 23(26), 136-164. [in Persian]
44. Sarker, I. H. (2021). Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. SN Computer Science, 2(6), 1-20. [DOI:10.1007/s42979-021-00815-1]
45. Sedaghati, S., Farhadi, R., & Fallah Shams, M. (1403). Contagion of Topological Dynamics in the Iranian Stock Market Network. Investment Knowledge, 13(49), 279-298. [in Persian]
46. Matos, T., de Macedo, J. A. F., & Monteiro, J. M. (2015). An Empirical Method for Discovering Tax Fraudsters: A Real Case Study of Brazilian Fiscal Evasion. In Proceedings of the 19th International Database Engineering & Applications Symposium (41-48). New York: Association for Computing Machinery. [DOI:10.1145/2790755.2790759]
47. Taye, M. M. (2023). Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions. Computers, 12(5), 91. [DOI:10.3390/computers12050091]
48. United Nations. (2017). Practical Manual on Transfer Pricing for Developing Countries. Retrieved from chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://www.un.org/esa/ffd/wp-content/uploads/2017/04/Manual-TP-2017.pdf
49. Liu, X., Pan, D., & Chen, S. (2010). Application of Hierarchical Clustering in Tax Inspection Case-Selecting. In 2010 International Conference on Computational Intelligence and Software Engineering (1-4). New York: IEEE. [DOI:10.1109/CISE.2010.5676711]
50. Lin, Y., Wong, K., Wang, Y., Zhang, R., Dong, B., Qu, H., & Zheng, Q. (2020). Taxthemis: Interactive Mining and Exploration of Suspicious Tax Evasion Groups. IEEE Transactions on Visualization and Computer Graphics, 27(2), 849-859. [DOI:10.1109/TVCG.2020.3030370]
51. Kim, Y. J., Baik, B., & Cho, S. (2016). Detecting Financial Misstatements with Fraud Intention Using Multi-Class Cost-Sensitive Learning. Expert Systems with Applications, 62, 32-43. [DOI:10.1016/j.eswa.2016.06.016]
52. Zhou, F., Zhou, H. M., Yang, Z., & Yang, L. (2019). EMD2FNN: A Strategy Combining Empirical Mode Decomposition and Factorization Machine Based Neural Network for Stock Market Trend Prediction. Expert Systems with Applications, 115, 136-151. [DOI:10.1016/j.eswa.2018.07.065]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
