Combining Network Visualization and Data Mining for Tax Risk Assessment

Abstract

This paper presents a novel approach, called MALDIVE, to support tax administrations in the tax risk assessment for discovering tax evasion and tax avoidance. MALDIVE relies on a network model describing several kinds of relationships among taxpayers. Our approach suitably combines various data mining and visual analytics methods to support public officers in identifying risky taxpayers. MALDIVE consists of a 4-step pipeline: (i) A social network is built from the taxpayers data and several features of this network are extracted by computing both classical social network indexes and domain-specific indexes; (ii) an initial set of risky taxpayers is identified by applying machine learning algorithms; (iii) the set of risky taxpayers is possibly enlarged by means of an information diffusion strategy and the output is shown to the analyst through a network visualization system; (iv) a visual inspection of the network is performed by the analyst in order to validate and refine the set of risky taxpayers. We discuss the effectiveness of the MALDIVE approach through both quantitative analyses and case studies performed on real data in collaboration with the Italian Revenue Agency. INDEX TERMS Tax risk assessment, tax evasion discovery, network visualization, data mining, human-computer interaction.

Tax Default Prediction Using Feature Transformation-Based Machine Learning

“…This approach is fast and scalable but could only identify 20 out of 30 investigated firms. The MALDIVE approach was proposed for tax risk assessment by combining social network visualization from taxpayer data with LR, MLP, SVM, and RF data analytic approaches [9]. The RF method performed best, with 74.3% accuracy in detecting the positive and negative outcomes of a fiscal audit.…”

“…The indicators of credit default and corporate bankruptcy have been extensively studied in earlier research [5], [6], but the indicators of tax default are still poorly understood despite the fact that corporate tax documents contain much multifaceted information for assessing tax default risk prediction [7]. Predicting a tax default differs from predicting a tax evasion (tax fraud) [4], [8] or a tax avoidance [9]. In tax evasion, a taxpayer supplies intentionally incorrect or partial information to tax agencies to lessen the tax burden, and in tax avoidance, the taxpayer arranges the affairs of a company in such a way that the tax burden is reduced relative to the pretax income.…”

TaxThemis: Interactive Mining and Exploration of Suspicious Tax Evasion Group

“…The Italian Revenue Agency proposed a decision support system for detecting specific patterns of tax evasion groups [3]. They later applied a system based on pattern matching and risk information diffusion to support public officers in identifying crafty taxpayers [4].…”

A Simple Visualization Method for Three-Dimensional (3D) Network

“…e network is a vital concept to understand modern society structure and components of the society. e concept of the network has been applied not only to people but also to social network [1][2][3][4][5][6][7], biological network [8][9][10][11][12], metabolic regulation network [13], online social network [14,15], sports social network [16,17], structure of neural network [18][19][20], etc. As a result, the data for storing network information has become complex and diverse.…”