Modeling tax evasion with genetic algorithms

Abstract

The U.S. tax gap is estimated to exceed $450 billion, most of which arises from non-compliance on the part of individual taxpayers (GAO 2012; IRS 2006). Much is hidden in innovative tax shelters combining multiple business structures such as partnerships, trusts, and S-corporations into complex transaction networks designed to reduce and obscure the true tax liabilities of their individual shareholders. One known gambit employed by these shelters is to offset real gains in one part of a portfolio by creating artificial capital losses elsewhere through the mechanism of "inflated basis" (TaxAnalysts 2005), a process made easier by the relatively flexible set of rules surrounding "pass-through" entities such as partnerships (IRS 2009). The ability to anticipate the likely forms of emerging evasion schemes would help auditors develop more efficient methods of reducing the tax gap. To this end, we have developed a prototype evolutionary algorithm designed to generate potential schemes of the inflated basis type described above. The algorithm takes as inputs a collection of asset types and tax entities, together with a rule-set governing asset exchanges between these entities. The schemes produced by the algorithm consist of sequences of transactions within an ownership network of tax entities. Schemes are ranked according to a "fitness function" (Goldberg in Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, Boston, 1989); the very best schemes are those

Detecting tax evasion: a co-evolutionary approach

“…In contrast our model does not require taxpayer data (it is similar to a minmax search in a game of chess) and has the added advantage of alleviating any data privacy concerns. The current paper specifically extends the prior efforts (Warner et al 2014;Hemberg et al 2015;Rosen et al 2015) that describe tax evasion detection through evolutionary search.…”

Tax evasion, technology, and inequality

“…For example, some recent applications of AI include the development of self-driving cars and of computers that can beat the world's best chess or Jeopardy players. In the context of tax enforcement, recent research has demonstrated that AI can anticipate particular modes of tax evasion, by identifying those tax schemes that taxpayers and their advisers employ to engage in tax evasion, as demonstrated and analyzed by Warner et al (2015), Hashimzade et al (2015), Hemberg et al (2016), and . AI is especially helpful in seeing detecting patterns of individual use of tax code regulations that can then be used collectively to create a sophisticated -and illegal -tax avoidance scheme.…”

Big Data and Dahl’s Challenge of Democratic Governance

“…The “Global Pulse” program set up by the UN in 2009 monitors big data to understand the impact of global crises on vulnerable populations by analyzing the correlations between different trends such as participation in health programs and the growth of food prices in developing countries (United Nations Global Pulse, ). Similarly, control and efficiency can be achieved in the tax policy area such as monitoring tax participation to track avoidance behavior and, in particular, address the ability of wealthier taxpayers to dodge taxes (Warner et al, ).…”