Comparison of Decision Tree (C5.0 Algorithm and Random Forest) and Support Vector Machine in the Validation of Taxpayers

Khoramniya, Hoshang; Fallahshams, Mirfeiz; Zomorodian, Gholamreza; Asghar Anvary Rostami, Ali

doi:10.61186/taxjournal.33.59.50

Volume 33, Issue 59 (2023) J Tax Res 2023, 33(59): 50-74 | Back to browse issues page

‎ 10.61186/taxjournal.33.59.50

Mendeley

Zotero

RefWorks

Khoramniya H, Fallahshams M, Zomorodian G, Asghar Anvary Rostami A. Comparison of Decision Tree (C5.0 Algorithm and Random Forest) and Support Vector Machine in the Validation of Taxpayers. J Tax Res 2023; 33 (59) :50-74
URL: http://taxjournal.ir/article-1-2320-en.html

Comparison of Decision Tree (C5.0 Algorithm and Random Forest) and Support Vector Machine in the Validation of Taxpayers

Hoshang Khoramniya

, Mirfeiz Fallahshams ^*

¹, Gholamreza Zomorodian

, Ali Asghar Anvary Rostami

1- , fallahshams@gmail.com

Abstract: (344 Views)

Today, the risk-based audit method is emphasized in modern tax systems, so explaining a comprehensive model for rating the risk of taxpayers is one of the basic steps of implementing a comprehensive tax plan. Therefore, in this article, we aim to measure the performance of decision tree algorithms and support vector machine in the validation of taxpayers. The statistical population of this research is the companies accepted in the Tehran Stock Exchange, which were active during the years 2012-2017 and for the selection of the sample was made using the screening method (elimination). In this research, first, using Delphi technique and meta synthesis, 164 effective components in the validation of taxpayers were identified, then the data needed to measure the variables of the research were extracted from the Kodal website and by examining tax files, and finally by using the collected data, we investigated the accuracy of the decision tree (C5.0 algorithm and random forest) and support vector machine in validating taxpayers. The findings showed that based on the results of the AUC value, the C5.0 algorithm and the random forest have a better fit, however, the research hypothesis that it is possible to predict the risk of taxpayers using the SVM algorithm is not rejected.

Keywords: Taxpayer Validation, Conservatism, Operating Cash Flow, Tax Compliance

Full-Text [PDF 1011 kb] (293 Downloads)

Type of Study: Research | Subject: Management
Received: 2023/12/20 | Accepted: 2023/12/1 | Published: 2023/12/1

References

1. رفرنس های متنی مثل خروجی کراس رف را در اینجا وارد کرده و تایید کنید 1. Alabede, James O., Zaimah Zainol Ariffin and Kamil Md Idris. (2011). Individual Taxpayers' Attitude and Compliance Behavior in Nigeria: The Moderating Role of Financial Condition and Risk Preference", Journal of Accounting and Taxation Vol. 3(5), pp. 91- 104.

2. Bagherpour M. A. Bagheri M. Khadem H. Hosieni Pour R. (2012). Examine the Effects of Financial and Non-Financial Variables on Tax Evasion Using of Data Mining Techniques: Automotive and Parts Manufacturing Industry. Empirical Studies in Financial Accounting Quarterly34: 103- 12, (Persian)

3. Brealey, R. and s. Myers (1991). Principles of Corporate Finance, Furth Edition, New York, McGraw-Hill, Inc.

4. Dastgir M, Izadinia N, Askari A, Ramezani M M. (2015). Providing a Model for Corporate Risk- based Audit Selection in Iran. Journal of Tax Research. 23 (25), (Persian).

5. Dastgir M, Qaribi M. (2016). Using Data Mining Techniques to Enhance Tax Evasion Detection Performance. J Tax Res. 23 (28), (Persian).

6. Francisco J. Delgado, Elena Fernández-Rodrígue, Roberto García-Fernández, Manuel Landajo, Antonio Martínez-Arias (2023). Tax Avoidance and Earnings Management: a Neural Network Approach for the Largest European Economies, Financial Innovation volume 9, Article number: 19. [DOI:10.1186/s40854-022-00424-8]

7. Gallemore, J., and E. labro. (2015). The Importance of the Internal Information Environment for Tax Avoidance. Journal of Accounting and Economics. 60(1): 149-167. [DOI:10.1016/j.jacceco.2014.09.005]

8. Hosieni Pour R. Bagherpour M. Lashani M. A. Salehi M. (2017). Identify Financial and Non-Financial Variables Affecting the Basis of Auditing Report Adjustment Related to Accounting Estimates: A Data Mining Approach. Audit Science. 17(66): 107-130, (Persian).

9. Iranian National Tax Administrations Research Database (2022). Approaches to Deal with Tax Evasion and Avoidance in Selected Countries, (Persian).

10. Khoramnia H., khoramnia A A, Mehrkam M. (2017). The Influence of Conservatism on Relationship between Operational Cash Flow and Definitive Taxable Income. Journal of Tax Research. 25 (35) :128-156, (Persian).

11. Masihi M, Yaghobnejad A, Kaighobadi A, Torabi T, (2019). Using Data Mining Techniques to Measure Tax Risk, Value Added Taxpayers, Iranian Financial Engineering Association, (Persian).

12. Namazi M, Sadeghzadeh Maharluie M. (2018). Predicting Tax Evasion by Decision Tree Algorithms. Quarterly Financial Accounting Journal. 9 (36) :76-101. (persian)

13. Neuman, S., T. Omer and A. Schmidt (2013). Risk and Return: Dose Tax Risk Reduce Firms' Effective Tax Rates?, Working Paper, Texas A&M University and North Carolina State University. [DOI:10.2139/ssrn.2215129]

14. OECD, (2004). Compliance Risk Management: Audit Case Selection System, 2004, (Persian).

15. Pourzamani Z, Shamsi Jamkhaneh A. (2009). Factors Involved in the Difference between Taxable Income Declared by Business Corporations and Taxable Income Assessed by Tax Authorities: Case of West Tehran Tax Affairs Head Office . Journal of Tax Research. 17 (5) :9-26, (Persian).

16. Rahimikia E, Mohamadi S, Ghazanfari M. (2015). Tax Evasion Detection by Using Combinatory Elligent System. Journal of Tax Research. 23 (26) :136-164. (Persian).

17. Countries Experience . Journal of Tax Research. 21 (18) :77-114, (Persian)

18. Taghavi Fard M, Raeesi Vanani I, Panahi R. (2017). A Predictive Analytics for Detection of VAT Taxpayers Evasion through Classification & Clustering Algorithms. Journal of Tax Research. 25 (35) :11-36, (Persian).

19. Watts, R. (2003). Conservatism in Accounting Part I: Explanations and Implications. Accounting Horizons 17(3): 207-222. [DOI:10.2308/acch.2003.17.3.207]

20. Kirchler, E. (2007). The Economic Psychology of Tax Behavior. Cambridge: Cambridge University Press. [DOI:10.1017/CBO9780511628238]

21. De Ghanbari nia. Mihir A., Alexander Dyckb, Luigi Zingalesc,ch. (2007).

22. Theft and Taxes. Journal of Financial Economics 84591-623, (Persian).