Designing a model to reduce tax evasion using the intelligent discovery system

Document Type : Original Article

Authors
narjes akbari 1
arefeh mohaghegh 2
Reza ziyari 2
samaneh ghods 2
1 Doctoral student of Accounting, North Tehran Azad University
2 Assistant Professor of Accounting Department, North Tehran Branch-Islamic Azad University-Tehran, Iran
10.22034/jik.2025.78058.4626
Abstract
Reducing tax evasion is one of the major challenges for governments around the world. The use of smart discovery systems can be used as an effective solution to deal with tax evasion. In this research, using the qualitative research method of the database, the model of tax evasion reduction was designed using the intelligent discovery system. Based on this, by conducting interviews with fourteen professors and experts of the country's tax system with 15 years of work experience and master's and doctorate degrees, 10 main categories were identified based on the paradigm model, which is structured in the form of six dimensions: policy Appropriate taxation and tax intelligence as "causal conditions", tax culture as "intervening conditions", high share of underground economy as "background conditions", reduction of collection cost, tax justice and tax compliance as "interactive dimension". Reducing tax evasion as a "central phenomenon" and increasing tax revenue and economic development as a "consequence dimension". Also, the highest frequency was related to the variables of appropriate tax policy, tax intelligence and tax culture, which shows the importance of these variables in the research model. According to the pattern obtained from the research, it was found that macro and structural factors have a significant impact on reducing tax evasion by using the intelligent detection system.
احمدی، وحیده، شهنازی، روح اله، اسلاملوییان، کریم، و صدرایی جواهری، احمد (1400). ارزیابی مدل های سنجش فرار مالیاتی از اقتصاد نئوکلاسیک تا اقتصاد رفتاری: رهیافت تحلیل سلسله مراتبی در اقتصاد ایران. برنامه ریزی و بودجه, 26(1 ), 115-141.
استراوس, ا., & کربین, ج. (1395). مبانی پژوهش کیفی فنون و مراحل تولید نظریه زمینه ای (ا. افشار, Trans. چاپ پنجم ed.). تهران: نشرنی.
صامتی، م.، و ایزدی، ا.، و فتحی، س. (1400). تعیین عوامل مؤثر بر فرار مالیاتی با استفاده از روش فرا تحلیل. اقتصاد باثبات و توسعه پایدار, 2(2 ), 1-22.
شفیعی, علی., & تات, سارا. (1399). روش تحقیق در مدیریت. (چاپ دوم), انتشارات بازاریابی, تهران.
محمدپور, ا. (1392). روش تحقیق کیفی ضد روش ( ویرایش دوم ed.). تهران: جامعه شناسان.
 
Alsadhan, N. J. C. S. S. E. (2023). A Multi-Module Machine Learning Approach to Detect Tax Fraud. 46(1), 241-253.
Anggareni, I. N., Mujiyati, M. J. I. J. o. E., & Research, M. (2024). The Effect of Understanding Taxation, Justice, Discrimination, Tax Rates, Taxation Systems, Tax Sanctions on Student Perceptions of Tax Evasion. 3(2), 30-50.
Bani-Mustafa, A., Nimer, K., Uyar, A., & Schneider, F. J. I. J. o. P. A. (2024). Effect of government efficiency on tax evasion: the mediating role of ethics and control of corruption. 47(2), 90-105.
Gaie, C. (2023). Struggling Against Tax Fraud, a Holistic Approach Using Artificial Intelligence. In Recent Advances in Data and Algorithms for e-Government (pp. 87-102): Springer.
Hashemi, M., Etemadi, H., & Rezazadeh, J. (2022). Modeling Tax Evasion in Value Added Tax, A Game Theory Approach %J Journal of Tax Research. 30(55), 0-0. doi:10.52547/taxjournal.30.55.2
Mojahedi, H., Babazadeh Sangar, A., & Masdari, M. (2022). Towards Tax Evasion Detection Using Improved Particle Swarm Optimization Algorithm. Mathematical Problems in Engineering, 2022, 1027518. doi:10.1155/2022/1027518
Murorunkwere, B. F., Tuyishimire, O., Haughton, D., & Nzabanita, J. J. F. I. (2022). Fraud detection using neural networks: a case study of income tax. 14(6), 168.
Nembe, J. K., Atadoga, J. O., Mhlongo, N. Z., Falaiye, T., Olubusola, O., Daraojimba, A. I., . . . Journal, A. R. (2024). The role of artificial intelligence in enhancing tax compliance and financial regulation. 6(2), 241-251.
Nuryani, N., Mutiara, A. B., Wiryana, I. M., Purnamasari, D., & Putra, S. N. W. J. A. T. o. T. (2024). Artificial Intelligence Model for Detecting Tax Evasion Involving Complex Network Schemes. 6(3), 339− 356-339− 356.
Ogunwole, A. E., Adebayo, A. M., & Jimoh, S. A. J. K. J. o. S. S. (2023). Illicit Financial Flows, Trade Misinvoicing and Multinational Tax Avoidance: Exploratory Approach. 8(4), 7-16.
Ruzgas, T., Kižauskienė, L., Lukauskas, M., Sinkevičius, E., Frolovaitė, M., & Arnastauskaitė, J. J. A. (2023). Tax Fraud Reduction Using Analytics in an East European Country. 12(3), 288.
Scientific, L. L. J. J. o. T., & Technology, A. I. (2024). OPTIMIZATION OF SMART TAXATION USING ARTIFICIAL INTELLIGENCE: RISKS AND OPPORTUNITIES. 102(5).
Shi, B., Dong, B., Xu, Y., Wang, J., Wang, Y., & Zheng, Q. J. E. S. w. A. (2023). An edge feature aware heterogeneous graph neural network model to support tax evasion detection. 213, 118903.
Siraj, F. A., Sudaryono, E. A., Aryani, Y. A., Setiawan, D. J. I. J. o. M., & Understanding, M. (2024). Literature Review: Smart Tax Evasion Strategies in Indonesia. 10(12), 562-576.
Xavier, O. C., Pires, S. R., Marques, T. C., & Soares, A. d. S. J. R. d. A. P. (2022). Tax evasion identification using open data and artificial intelligence. 56, 426-440.
Yalamati, S. J. T. o. L. T. i. A. I. (2024). Impact of Artificial Intelligence in supervision of enterprises reduce tax avoidance. 5(5).