An Empirical Method for Discovering Tax Fraudsters

Matos, Tales; Macêdo, José Antônio Fernandes de; Monteiro, José Maria

doi:10.1145/2790755.2790759

Cited by 13 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A detecc ¸ão de fraudes tem sido amplamente explorada na literatura, embora poucos trabalhos abordem técnicas específicas para as notas fiscais eletrônicas. No que concerne auditoria fiscal, pode-se citar um método para mensurar e ranquear o potencial de fraude de contribuintes baseando-se na análise dos principais tipos de indicadores de fraude [Matos et al 2015], um estudo de caso de auditoria [Kieckbusch et al 2020] e uma classificac ¸ão baseada em Redes Neurais Convolucionais para definir a categoria do produto comercializado [Kieckbusch et al 2021]. Ademais, foi publicado um conjunto de dados de notas fiscais com descric ¸ões rotuladas em categorias específicas [Di Oliveira et al 2022], no entanto, não existem rótulos quanto à ocorrência de fraude.…”

Section: Revisão Bibliográficaunclassified

Estratégias Computacionais Baseadas em Similaridade de Textos e Visualização Exploratória para a Identificação de Inconsistências em Notas Fiscais Eletrônicas

Marinho,

Weigang,

Oliveira

et al. 2024

Anais Estendidos Do XX Simpósio Brasileiro De Sistemas De Informação (SBSI 2024)

View full text Add to dashboard Cite

A detecção de fraudes em notas fiscais é um desafio considerável para os órgãos de controle, dada a quantidade expressiva de documentos gerados diariamente. Buscando soluções para esse desafio, esta pesquisa propõe uma abordagem inovadora que combina rotulação automática de notas fiscais baseada em similaridade de texto e técnicas de visualização exploratória. O objetivo é auxiliar especialistas na tarefa de auditoria fiscal, trazendo equilíbrio entre automatização e autonomia por meio de um sistema de visualização web interativo denominado NFViz. O NFViz permite investigar as notas fiscais em busca de incompatibilidades que podem sinalizar possíveis fraudes, otimizando as atividades de auditoria fiscal ao reduzir o escopo de busca por notas suspeitas.

show abstract

Section: Revisão Bibliográficaunclassified

Estratégias Computacionais Baseadas em Similaridade de Textos e Visualização Exploratória para a Identificação de Inconsistências em Notas Fiscais Eletrônicas

Marinho,

Weigang,

Oliveira

et al. 2024

Anais Estendidos Do XX Simpósio Brasileiro De Sistemas De Informação (SBSI 2024)

View full text Add to dashboard Cite

show abstract

“…The resulting model was assessed using non-compliant VAT declarations collected in Taiwan from 2003 to 2004. Similarly, the Apriori algorithm was adapted in [18,19] to mine hidden patterns underlying fraudulent tax behaviors. Specifically, it was associated with Principal Component Analysis (PCA) [20] and Singular Value Decomposition (SVD) [21], as dimensionality reduction techniques, in order to determine the relevant fraud indicators and learn a fraud scale to rank Brazilian taxpayers based on the risk they represent for the tax administration.…”

Section: Related Workmentioning

confidence: 99%

Simultaneous Classification and Regression for Zakat Under-Reporting Detection

Ismail

Alsadhan

2023

Applied Sciences

View full text Add to dashboard Cite

Tax revenue represents an essential budget source for most countries around the world. Accordingly, the modernization of relevant technological infrastructure has become a key factor of tax administration strategy for improving tax collection efficiency. In particular, the fiscal consolidation of the Kingdom of Saudi Arabia has been supported by considerable development in tax policy and administration, aimed at raising more taxes from non-oil activities. In fact, non-Saudi investors are liable for income tax in Saudi Arabia. On the other hand, Saudi citizen investors (and citizens of the GCC countries) are liable for Zakat, an Islamic assessment. Typically, taxpayers are in charge of preparing and accurately reporting their Zakat declaration. This allows tax authorities to overview and audit their business activities. However, despite administration efforts to increase taxpayer compliance, considerable revenue remains at under-reporting risk. In this paper, we introduce a novel intelligent approach to support tax authority efforts in detecting under-reporting among Zakat payer declarations. In particular, the proposed solution aims at improving detection accuracy and determining the fraud cases that correspond to a higher revenue at risk. Specifically, we formulate Zakat under-reporting detection as a supervised machine learning task through the design of a deep neural network that performs simultaneous classification and regression tasks. In particular, the proposed network contains an input layer, five hidden layers, and two output layers for classification and regression. Zakat declarations are mapped into the predefined “under-reporting” or “actual declaration” classes. Moreover, the revenue at risk caused by the predicted fraud cases is learned by the designed model. This allows the proposed approach to prioritize the auditing of specific Zakat payers based on the corresponding predicted revenue at risk. A real dataset including 51,919 Zakat declarations was used to validate and assess the designed model. Further, the Synthetic Minority Oversampling Technique (SMOTE) boosted the proposed model performance in terms of classification and prioritization.

show abstract

“…In addition, neural networks has been applied to enhance the efficiency of machine learning, such as for the detection of fraud in tax declarations using Ensemble ISGNN [64], Personal Income Tax evasion [65], and transaction-based tax evasion [66]. Unsupervised learning has been applied to detect tax fraud using association rules and dimensionality reduction [67], to identify underreporting declarations using the clustering approach [68], and to detect VAT fraud by computing the anomaly score using Fixed-Width Anomaly Detection (FWAD) and Local Outlier Factor (LOF) [69]. Furthermore, several complex algorithms have been developed to efficiently detect tax evasion cases, such as Hybrid Unsupervised Outlier Detection (HUNOD) using K-means clustering, autoencoder-based outlier detection [12], and unsupervised conditional adversarial networks (UCAN) using a generative model to detect tax evasion [70].…”

Section: F Related Workmentioning

confidence: 99%

Synthesis of Tax Return Datasets for Development of Tax Evasion Detection

Visitpanya,

Samanchuen

2023

IEEE Access

View full text Add to dashboard Cite

Datasets are an essential part of data science processes. However, retrieving a dataset, especially a tax return dataset, is challenging as privacy becomes more evident in our daily lives. Thus, data synthesis is an approach selected for our work by utilizing publicly available data and augmenting it using Generative Adversarial Network (GAN) and Synthetic Minority Oversampling TEchnique (SMOTE). The evaluation is performed using a Correlation Matrix, Principal Component Analysis (PCA), and Quality Score. In addition, fundamental machine learning models are utilized to detect tax evasion based on a literature review. The data are gathered from the financial statements of companies registered within the Stock Exchange of Thailand (SET). Our results indicate that synthetic datasets with 0.87 average Quality Score can train models that yield approximately 0.95 Accuracy and 0.91 F1-Score. Additionally, by increasing more instances, the effect of class imbalance and high variance can be mitigated. The expected benefits include the use of open data for analysis and application of synthetic datasets. Forthcoming research could consider the statistical behavior of different business sectors, multiclass labeling for advanced recommendations, and implementation of unsupervised models.

show abstract

An Empirical Method for Discovering Tax Fraudsters

Cited by 13 publications

References 8 publications

Estratégias Computacionais Baseadas em Similaridade de Textos e Visualização Exploratória para a Identificação de Inconsistências em Notas Fiscais Eletrônicas

Estratégias Computacionais Baseadas em Similaridade de Textos e Visualização Exploratória para a Identificação de Inconsistências em Notas Fiscais Eletrônicas

Simultaneous Classification and Regression for Zakat Under-Reporting Detection

Synthesis of Tax Return Datasets for Development of Tax Evasion Detection

Contact Info

Product

Resources

About