Using data mining technique to enhance tax evasion detection performance

Wu, Richard S. L.; Ou, Chin S.; Lin, Hui-ying; Chang, She-I; Yen, David C.

doi:10.1016/j.eswa.2012.01.204

Cited by 78 publications

(36 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In agreement with the ideas presented by Wu et al [23], we believe that the tax authorities are equipped with limited resources, and traditional tax auditing methods/strategies are time-consuming and tedious. Consequently, there is a pressing need to have further inputs to a tax avoidance database and additional information resources from big data (e.g.…”

Section: Introductionsupporting

confidence: 86%

“…Generally, manual case selection [23], computer-based case selection (data-mining-based methods [24], [7]), and whistle-blowing-based selection are three frequently used ways of tax inspection. However, many researchers believed that manual case selection and whistle-blowingbased selection are time-consuming and tedious, while data mining techniques used by tax administrations to detect tax fraud are considered to be the most promising approaches [7].…”

Section: The State-of-art Tax Inspection Methods Used In Many Countrimentioning

confidence: 99%

“…However, many researchers believed that manual case selection and whistle-blowingbased selection are time-consuming and tedious, while data mining techniques used by tax administrations to detect tax fraud are considered to be the most promising approaches [7]. Mechanisms, such as neural networks, decision trees [8], logistic regression, SOM (Selforganizing map), K-means, support vector machines, visualization techniques, Bayesian networks, rough set [3], K-nearest neighbor, association rules [24], fuzzy rules, Markov chains, time series, regression and simulations [2], have been used to check tax evasion [23], [12]. For example, Wu et al [23] used a data mining technique and developed a screening framework to filter possible noncompliant value-added tax (VAT) reports that may be subject to further auditing.…”

Section: The State-of-art Tax Inspection Methods Used In Many Countrimentioning

confidence: 99%

“…Mechanisms, such as neural networks, decision trees [8], logistic regression, SOM (Selforganizing map), K-means, support vector machines, visualization techniques, Bayesian networks, rough set [3], K-nearest neighbor, association rules [24], fuzzy rules, Markov chains, time series, regression and simulations [2], have been used to check tax evasion [23], [12]. For example, Wu et al [23] used a data mining technique and developed a screening framework to filter possible noncompliant value-added tax (VAT) reports that may be subject to further auditing. Chen and Cheng [3] proposed a hybrid model, which combines the Delphi method with rough sets classifier approaches, for intelligently classifying the vehicle license tax payment (called VLTP) to solve real-world problems faced by taxation agencies.…”

Section: The State-of-art Tax Inspection Methods Used In Many Countrimentioning

confidence: 99%

“…The sharing of data has prepared the ground for deep mining and analysis of tax data. At the same time, three ways of tax inspection, manual case selection [23], computer-based case selection (data-mining-based methods [24], [7]), and whistle-blowing-based selection were adopted by China Taxation Administration in their daily operation of tax inspection. As a result of using these methods, the traditional tax evasion behaviors, such as writing false value added tax (VAT) invoices, fake invoices and the manipulation of accounts were restrained more than ever, and the number of tax evasion cases has been decreasing dramatically.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Mining Suspicious Tax Evasion Groups in Big Data

Tian

Lan

Chao

et al. 2016

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

There is evidence that an increasing number of enterprises plot together to evade tax in an unperceived way. At the same time, the taxation information related data is a classic kind of big data. The issues challenge the effectiveness of traditional data mining-based tax evasion detection methods. To address this problem, we first investigate the classic tax evasion cases, and employ a graph-based method to characterize their property that describes two suspicious relationship trails with a same antecedent node behind an Interest Affiliated Transaction (IAT). Next, we propose a colored network-based model (CNBM) for characterizing economic behaviors, social relationships and the IATs between taxpayers, and generating a Taxpayer Interest Interacted Network (TPIIN). To accomplish the tax evasion detection task by discovering suspicious groups in a TPIIN, methods for building a patterns tree and matching component patterns are introduced and the completeness of the methods based on graph theory is presented. Then, we describe an experiment based on real data and a simulated network. The experimental results show that our proposed method greatly improves the efficiency of tax evasion detection, as well as provides a clear explanation of the tax evasion behaviors of taxpayer groups.

show abstract

Section: Introductionsupporting

confidence: 86%

Section: The State-of-art Tax Inspection Methods Used In Many Countrimentioning

confidence: 99%