Detecting Tax Evasion Research Articles

The Scope of AI Applications to Tax Evasion in Enhancing Tax Enforcement Capabilities

This study explores the expansive scope of artificial intelligence (AI) applications in enhancing tax enforcement capabilities, specifically targeting tax evasion. Through a survey using Smart PLS version (4) to analyze the data. The study highlights how the scope of AI, which is an Exploration of new AI technologies (ENT), Integration with existing systems AI (IES), The overall scope of AI applications (OSA), Perceived scalability AI (PS), can significantly improve the detection and prevention of tax evasion. Findings demonstrate that AI can identify complex patterns of fraudulent activity and predict potential risks more accurately and efficiently than traditional methods. The study also found no statistically significant relationship between integration with existing systems AI and tax evasion in tax enforcement capabilities.

Artificial Intelligence Model for Detecting Tax Evasion Involving Complex Network Schemes

Tax evasion through complex network schemes poses a significant challenge to tax authorities, leading to substantial revenue losses. This paper aims to develop and evaluate an artificial intelligence model designed to detect tax evasion within complex corporate networks, providing a comprehensive overview and prediction of tax avoidance behaviors. Employing a systematic literature review and document analysis of applicable tax regulations, the study utilizes Social Network Analysis (SNA) as a primary technique for mapping and analyzing taxpayer networks. The process involves matching taxable identities, constructing taxpayer graphs, extracting features, and developing a machine learning model. The proposed architectures and processes demonstrate the potential for tax authorities to enhance their capabilities in detecting tax evasion involving complex networks, with the machine learning model effectively identifying features related to both individual and network characteristics of taxpayers. The findings suggest that the integration of artificial intelligence and big data analytics can significantly improve the detection of tax evasion in complex corporate structures, offering valuable tools for tax authorities to better enforce tax compliance.

TAX CONTROL AS AN ELEMENT OF INTERACTION BETWEEN TAX PAYERS AND TAX AUTHORITIES

The article analyzes the role and importance of tax control as a key element of interaction between taxpayers and tax authorities. It is determined that tax control is a key element of the tax system, since the functioning of the country's economy depends on its effectiveness, and forms of tax control contribute to the efficiency of tax relations. The elements and methods of tax control are considered, and it is determined that it operates within the framework of strict legal regulation and has a state character. It is established that in order to increase the activity of tax control, it is necessary to resolve the issue of interaction and mutual responsibility between taxpayers and the State. This is possible through the introduction of the basic principles of taxation and the formation of a tax policy that meets budget priorities and the organization of public expenditures. The article identifies the factors that complicate the implementation of tax control. Among them are the difficult financial situation of many taxpayers, the low level of tax culture and taxpayers' distrust of the tax authorities. These problems can be overcome by improving tax legislation, strengthening the responsibility of tax officials, and by taking measures to raise awareness and educate the public about the importance of paying taxes correctly. It is analyzed that the digital transformation of tax audits leads to a significant reduction in the time required for their conduct and an increase in the likelihood of detecting tax evasion. However, this process faces a number of problems that can be solved by amending the relevant legislative acts

Detecting Tax Evasion of Legal Entities Using Artificial Inteligence

Detecting Tax Evasion of Legal Entities Using Artificial Inteligence

TAX AUDIT IN THE CONDITIONS OF DIGITALIZATION: CURRENT STATE, PROBLEMS, PERSPECTIVES

The article examines the peculiarities of the functioning and development of tax audit in the conditions of digitalization. It is noted that the formation of the digital economy involves the active implementation of innovations and information and communication technologies in all types of economic activity and spheres of life, including tax audit. It has been proven that the State Tax Service of Ukraine is actively implementing digital tools in its work with taxpayers. Attention is drawn to the fact that the indisputable advantage of using tax electronic audit is a significant reduction in the time spent on tax audits and an increase in the probability of detecting tax evasion. It is noted that the use of digital tools during tax audits is accompanied by certain problems. Ways to solve them are proposed. The expediency of developing and displaying in the relevant legislative acts the algorithm of the Standard Audit File for Tax (SAF-T) electronic audit procedure is substantiated, which will increase its effectiveness, quality and reduce the time for its implementation.

Tax Fraud Reduction Using Analytics in an East European Country

Tax authorities face the challenge of effectively identifying companies that avoid paying taxes, which is not unique to European Union countries. Limited resources often constrain tax administrators, who traditionally rely on time-consuming and labour-intensive tax audit tools. As a result of this established practice, governments are losing a lot of tax revenue. The main objective of this study is to increase the efficiency of the detection of tax evasion by applying data mining methods in the East European country Lithuania, which has a rapidly developing economy, by applying data mining methods concerning affluence-related impacts. The study develops various models for segmentation, risk assessment, behavioral templates, and tax crime detection. Results show that the data mining technique can effectively detect tax evasion and extract hidden knowledge that can be used to reduce revenue losses resulting from tax evasion. This study’s methods, software, and findings can assist decision-makers, experts, and scientists in developing countries in predicting tax fraud detection.

An edge feature aware heterogeneous graph neural network model to support tax evasion detection

Tax evasion is an illegal activity that causes severe losses of government revenues and disturbs the economic order. To alleviate this problem, decision support systems that enable tax authorities to detect tax evasion efficiently have been proposed. Recent researches tend to use graph to model the tax scenario and leverage graph mining techniques to conduct tax evasion detection, as so to make full use of the rich interactive information between taxpayers and improve the detection performance. However, a more favorable graph mining solution, graph neural networks, has not yet been thoroughly investigated in such settings, leaving space for further improvement. Therefore, in this paper, we propose a novel graph neural network model, named Eagle, to detect tax evasion under the heterogeneous graph. Specifically, based on the guidance of our designed metapaths, Eagle can extract more comprehensive features through a hierarchical attention mechanism that fully aggregates taxpayers’ features with their relations. We evaluate Eagle on real-world tax dataset. The extensive experimental results show that our model performs 15.71% better than state-of-the-art tax evasion detection methods in the classification scenario, while improves 5.22% in the anomaly detection scenario.

Detection of tax evasion using tax audits in the Slovak Republic

Detection of tax evasion using tax audits in the Slovak Republic

Towards Tax Evasion Detection Using Improved Particle Swarm Optimization Algorithm

This paper employs machine learning algorithms to detect tax evasion and analyzes tax data. With the development of commercial businesses, traditional algorithms are not appropriate for solving the tax evasion detection problem. Hence, other algorithms with acceptable speed, precision, analysis, and data decisions must be used. In the case of assets and tax assessment, the integration of machine learning models with meta-heuristic algorithms increases accuracy due to optimal parameters. In this paper, intelligent machine learning algorithms are used to solve tax evasion detection. This research uses an improved particle swarm optimization (IPSO) algorithm to improve the multilayer perceptron neural network by finding the optimal weight and improving support vector machine (SVM) classifiers with optimal parameters. The IPSO-MLP and IPSO-SVM models using the IPSO algorithm are used as new models for tax evasion detection. Our proposed system applies the dataset collected from the general administration of tax affairs of West Azerbaijan province of Iran with 1500 samples for the tax evasion detection problem. The evaluations show that the IPSO-MLP model has a higher accuracy rate than the IPSO-SVM model and logistic regression. Moreover, the IPSO-MLP model has higher accuracy than SVM, Naive Bayes, k-nearest neighbor, C5.0 decision tree, and AdaBoost. The accuracy of IPSO-MLP and IPSO-SVM models is 93.68% and 92.24%, respectively.

Does Corporate Governance Support Tax Avoidance Practice in Indonesia?

Tax avoidance is an action taken by company management so that corporate tax payments are smaller than they should be. The practice of tax avoidance often occurs in companies in Indonesia related to the tax rate for business entities which is considered too high. This study was conducted to establish if the factors of corporate governance, sales growth and leverage have an impact on the practice of tax avoidance. Corporate governance in this study is divided into five, namely independent board of commissioners, institutional ownership, managerial ownership, audit committee, and audit quality. The sample in this study is mining companies listed on the Indonesia Stock Exchange. The method used to take the sample was purposive sampling. This study used multiple linear regression. The results showed that independent board of commissioners, institutional ownership, audit quality, sales growth, and leverage had no effect on tax avoidance, whereas managerial ownership and audit committee had a positive effect on tax avoidance. This shows the impasse of corporate governance in preventing tax avoidance and even the audit committee actually encourages tax avoidance. The implication of this research is that it is very important to have strict supervision of mining companies in Indonesia in respect of tax avoidance practices by relevant agencies such as the tax office so that it has an impact on the need for technical skills for tax officers to detect tax evasion by companies.

The Impacts of Value-Added Tax Audit on Tax Revenue Performance: The Mediating Role of Electronics Tax System, Evidence from the Amhara Region, Ethiopia

Governments worldwide cannot collect the required tax revenue for their planned activities. This study aims to assess how inefficient VAT audit function and related factors affect tax revenue performance in Amhara Region, Ethiopia. The study used primary data sources from 377 VAT registered taxpayers in Amhara Region. It also used the Ability to Pay theory of taxation, structural equation model, path diagram, and multiple regression with SPSS/AMOS software for data analysis to identify the relationship between VAT audit and tax revenue performance. Even though the Amhara Region has revenue potential to cover its expenditures, because of inefficient VAT audit functions, poor system of tax education, lack of tax resources, and long time served tax rate, the tax revenue performance is inefficient. The study assured that VAT audit and tax education significantly affect tax revenue performance. The scarcity of resources for the VAT audit function is a critical problem. Even if the existed technology networked up to woreda levels, tax auditors did not use this system appropriately. Long-time-served tax rates also greatly influence tax revenue performance. The study recommended that there should be a chain mentor relationship between experienced auditors to new and ineffective auditors. The government should supply appropriate technology that is simple to use and quickly detect tax evasion. The existed tax rate and the system of tax education should be revised. The above findings are essential for taxpayers, policymakers, and tax authorities to understand, analyze, and use the main causes of VAT audit problems on tax revenue performance.

АНАЛІЗ ВПЛИВУ ТІНЬОВОЇ ЕКОНОМІКИ НА ПАРАМЕТРИ ІНКЛЮЗИВНОГО РОЗВИТКУ РЕГІОНУ

The article defines the results of modeling the influence of thelevel of the shadow economy on the parameters of the inclusive development of the regions of Ukraine. For the analysis, the level of the shadow economy calculated on the basis of monetary and sectoral methods was used. Based on the results of the analysis, it was determined that the presence of strong inclusive institutions, by defini-tion, leads to faster economic development in the long term, while exploitative institutions of the econ-omy cannot achieve long-term development, which occurs only in the short term and ceases to exist.As a result of the conducted research, the influence of the growth of the shadow sector of the economy on the reduction of the economic security of the state was revealed, and a number of recom-mendations were developed to overcome this problem.For Ukraine, the shadow economy, according to various estimates, is from 35% to 50% of GDP. The purpose of this article is to determine the main factors that contribute to the development of the shad-ow economy, and the means of their neutralization. Through state regulation, it is necessary to neutralize the factors that contribute to the growth of the shadow economy, in particular: measures to mitigate the effects of crisis phenomena should be provided for the population; legalization and removal of informal economic relations from the shadows; strict repressive measures against corrupt and criminal structures.Considering the issue of detinization, it should be noted that in Ukraine for a long time insuffi-cient attention was paid to the issue of reducing the share of the shadow economy. In recent years, this issue has become increasingly relevant on the political agenda. The government's action program contains several points to reduce the shadow economy.In order to reduce tax evasion, careful adjustments are necessary, such as ensuring the trans-parency of the tax legislation, preventing tax discrimination, increasing the possibility of detecting tax evasion, and, above all, taking action against the perpetrators. We emphasize that, in order to in-crease the number of prosecutors and fines for negligence, it is necessary to improve democratic institutions, strengthen the anticorruption fight, and eliminate the shameful phenomenon of politicians and bureaucrats ruling with anger.

Legal, Administrative and Judicial Framework in Pakistan to Combat Tax Evasion and Money Laundering: An Analytical Study

Purpose: The main objective of this research paper is to look at Pakistan's legal, administrative, and judicial framework in terms of countering money laundering and tax evasion. Money laundering and tax evasion are two financial crimes that have been linked, either directly or indirectly, to one other. Money laundering was formerly solely associated with the crimes of narcotics trafficking and terrorism financing. At present, it has been also associated with tax evasion.
 Methodology: The framework regarding tax evasion and money laundering is varied. In Pakistan, two different mechanisms exist to combat both crimes. This article analytically studies the parliamentary statutes and ordinance, the working of investigating and prosecuting agencies and judicature structure concerning tax evasion and money laundering in Pakistan.
 Findings: This article concludes that the problem of tax evasion and money launder are causing financial instability in Pakistan. There is an urgent need of revamping the current tax administration to detect tax evasion and frauds.
 Implication: this article recommends potential reforms in the existing legal, administrative and judicial framework to control and curb both crimes more effectively.

Tax Evasion Detection with FBNE-PU Algorithm Based on PnCGCN and PU Learning

Tax evasion is an illegal activity in which individuals or entities avoid paying their true tax liability. It has always been a crucial issue for both governments and academic researchers to efficiently detect tax evasion. Recent research has proposed the use of machine learning technology to detect tax evasion and has shown good results in some specific areas. Regrettably, there are still two major obstacles to detect tax evasion. First, it is hard to extract powerful features because of the complexity of tax data. Second, due to the complicated process of tax auditing, labeled data are limited. Such obstacles motivate the contributions of this work. In this paper, we propose a novel tax evasion detection framework named FBNE-PU, a multi-stage method to detect tax evasion in real-life scenarios. In this paper, we perform an in-depth analysis of the characteristics of the transaction network and propose a novel network embedding algorithm, the PnCGCN. It significantly improves detection performance by extracting powerful features from basic features and the tax-related transaction network. Moreover, we utilize nnPU to assign pseudo labels for unlabeled data. Finally, a MLP is trained as the decision function. Experiments on three real-world datasets demonstrate that our method significantly outperforms the comparison methods in the tax evasion detection task.

Changes in the Structure of International Trade And Services in the Context of Tax Fraud and Tax Evasion

The EU and the Member States have been forced in recent years to take a stronger position against the growing trend of tax fraud, tax evasion, and tax avoidance. The EU legislative and non-legislative acts in this area have resulted from political attitudes, economic intentions, proposals, and compromises reached between the individual Member States, on the one hand, and the EU, on the other, in their effort to combat fraudulent behaviour in the taxation area. The fight against fraudulent behaviour in the taxation area, be it tax fraud, tax evasion or tax avoidance, has become a real global challenge not only for the EU and its Member States but also for the entire world. These are different forms and methods for misusing tax systems both within the EU and abroad. This paper is part of the project: “Electronic methods for detecting unusual business transactions in the business environment” (ITMS code: 313022W057), co-financed by the European Regional Development Fund (ERDF) and also the project “VEGA1 / 0194/19 — Research on process-oriented financial management with a focus on to detect tax evasion in international trade”.

Fraud Detection by a Multinomial Model: Separating Honesty from Unobserved Fraud

In this paper we investigate the EM-estimator of the model by Caudill et al. (2005). The purpose of the model is to identify items, e.g. individuals or companies, that are wrongly classified as honest; an example of this is the detection of tax evasion. Normally, we observe two groups of items, labeled fraudulent and honest, but suspect that many of the observationally honest items are, in fact, fraudulent. The items observed as honest are therefore divided into two unobserved groups, honestH, representing the truly honest, and honestF, representing the items that are observed as honest, but that are actually fraudulent. By using a multinomial logit model and assuming commonality between the observed fraudulent and the unobserved honestF, Caudill et al. (2005) present a method that uses the EM-algorithm to separate them. By means of a Monte Carlo study, we investigate how well the method performs, and under what circumstances. We also study how well bootstrapped standard errors estimates the standard deviation of the parameter estimators.

Evaluating risk-based selection methods for tax audits in Poland

Penalty rates and probability of fraud detection are among the most important factors shaping taxpayer’s compliance. While the first of those factors may be directly controlled by tax authorities the second is usually indirectly influenced by the amount and efficiency of resources employed to detect tax evasion (Allingham, Sandmo 1972, p. 330). In order to increase fraud detection rate tax authorities may implement diversified strategies. They include inter alia the application of various methods to select taxpayers for tax audits. In most of the cases these methods are used interchangeably or complement each other. Although applied quite often in practice by tax authorities they are comparatively rarely addressed by the economists in their publications. In fact, literature sources on this topic are sparse and published mainly by the OECD. One of the methods used to select taxpayers for tax audits is based on the so-called external risk areas. In Poland, this method was introduced shortly after accession to the European Union as a tool of the external risk management strategy in the public administration. Both this strategy and audit targeting tools have evolved tremendously since its first implementation. This article attempts to evaluate the application of external risk areas to select taxpayers for tax audits in Poland. The author uses various indicators to measure the efficiency of tax audits and compare this efficiency taking into account different tax audit selection methods.

TaxThemis: Interactive Mining and Exploration of Suspicious Tax Evasion Groups.

Tax evasion is a serious economic problem for many countries, as it can undermine the government's tax system and lead to an unfair business competition environment. Recent research has applied data analytics techniques to analyze and detect tax evasion behaviors of individual taxpayers. However, they have failed to support the analysis and exploration of the related party transaction tax evasion (RPTTE) behaviors (e.g., transfer pricing), where a group of taxpayers is involved. In this paper, we present TaxThemis, an interactive visual analytics system to help tax officers mine and explore suspicious tax evasion groups through analyzing heterogeneous tax-related data. A taxpayer network is constructed and fused with the respective trade network to detect suspicious RPTTE groups. Rich visualizations are designed to facilitate the exploration and investigation of suspicious transactions between related taxpayers with profit and topological data analysis. Specifically, we propose a calendar heatmap with a carefully-designed encoding scheme to intuitively show the evidence of transferring revenue through related party transactions. We demonstrate the usefulness and effectiveness of TaxThemis through two case studies on real-world tax-related data and interviews with domain experts.

Modeling the Probability of the Detection Process of Tax Evasion Taking into Account Quality and Quantity Indicators

Aims: In contrast to the classical approaches of the standard model of tax evasion based on game theory, our manuscript has considered the detection of tax evasion as one of the main function of tax administration and has proposed a model for assessing the probability of tax evasion taking into consideration qualitative and quantitative indicators.
 Study Design: This investigation has been carried out on the basis of research methods such as scientific abstraction and systematic analysis, expert evaluation, logical generalization, statistical analysis.
 Place and Duration of Study: Department of Mathematical provision of economic researches, between November 2019 and May 2020.
 Methodology: For the evaluating of the probability of tax evasion’s detection firstly, efficiency indicators of tax administration were selected including 3 groups such as internal environmental, external micro, and external macro-environmental factors. These indicators consist of both quantitative as well as qualitative indicators. Quantitative indicators were assessed on the base on statistics information base. Quantitative indicators were assessed on the base of expert skills, knowledge, and experiences in accordance with under investigation countries. The objectiveness of obtained data that characterize qualitative indicators was checked and used both these as well as quantitative indicators for formulating the tax efficiency index. The next step is consists of using these formulations for evaluating the probability of detection of tax evasion under uncertainty. The impact degrees (membership functions) of the parameters that characterize the influence of 3 groups-environmental factors, in the detection of tax evasion were defined, and taking them into account in the fuzzy inference system probability of detection of tax evasion was assessed.
 Limitations: Lack or uncertainties of the information base cause difficulties in applying our model.
 Results: The probability of detection of tax evasion in the Republic of Azerbaijan was assessed with the proposed model and depends on the results recommendations have been consulted for improving appropriate tax system. As a result of model the probability of detection of tax evasion was defined 29%. The result shows that tax administration mechanism in Azerbaijan Republic need to be improved.
 Conclusion: Proposed model drives practical significance as a providing effective activity of tax institutions by defining the level of tax administration, as well as, as an impacting remarkably the revenue of state budget by determining the probability of tax evasion's detection.

ВПЛИВ ТІНЬОВОЇ ЕКОНОМІКИ НА ПОДАТКОВУ СИСТЕМУ КРАЇНИ

Проблема тіньової економіки є глобальною для всього світу, але серед європейський країн Україна є серед лідерів, тому детінізація економіки країни має стати головним пріоритетом державної політики. Визначено фактори, які впливають на тінізацію економіки. Встановлено, що тіньова економіка країни тісно пов’язана із рівнем розвитку її податкової системи, можливостями уникнення оподаткування і, як наслідок, недоотриманням надходжень фінансових ресурсів до державного бюджету країни. Здійснено оцінку втрати бюджету через ухилення від податків. Розраховано податковий коефіцієнт та його складники. Визначено, що високий рівень тіньової економіки та суттєві обсяги податкових втрат внаслідок її функціонування призводять до зменшення фінансових можливостей держави та провокують бюджетний дефіцит, що є характерним для України. Запропоновано низку практичних заходів, спрямованих на зниження тіньового сектору економіки країни.