how the IRS uses artificial intelligence to fight fraud

Every year, the tax administration increases its use of artificial intelligence to combat fraud and improve the efficiency of its services. In 2021, the proportion of controls targeted by AI was 45% compared to 32.5% a year earlier.

In the last few weeks, the teams in the Directorate-General for Public Finance (DGFIP) have familiarized themselves with a new tool. Its name: Galaxy. Approved on March 11 by the National Commission on Computing and Liberties (Cnil), the use of this new computer software for automated taxpayer data processing should allow tax authorities to better track down fraudsters.

Its spread in DGFIP’s premises is part of the PILAT project, which was launched in 2018 to modernize the tax control system. The decree of 11 March describes this new weapon in the fight against fraud as “a visualization tool at national level on the one hand of the links between professional entities (links of participation) and between professional entities and natural persons (director, partner or shareholder relations). , and, on the other hand, contextual elements concerning the financial and tax situation of these persons “.

Galaxy thus makes it possible to aggregate data such as the reference tax income, the identity of the spouse or even the tax liabilities of individuals. But also the Siren number, the legal status, the category of turnover as well as the taxes and duties to which legal persons are subject.

The tax administration’s adoption of this new tool marks a further step in DGFIP’s desire to strengthen its digital arsenal to combat fraud. More generally, the service linked to Bercy, the Requests and Valuation Mission (MRV) created several years ago, funded by 5.2 million euros in the period 2018-2022. Objective: to develop artificial intelligence and data mining techniques in the processing of tax data and better target control and detect fraud profiles. Recently, an algorithm has enabled the tax authorities to mix and collect the information in the Internet users’ publications on social networks before processing them on a case-by-case basis.

45% of the controls are targeted at artificial intelligence

DGFIP is pleased with the results of this 2.0 switch. In 2021, € 13.4 billion in adjustments were notified to individuals and businesses, and € 10.7 billion was raised. A level close to the 2019 record (11 billion), which the tax administration largely attributes to “the use of data mining to better target tax audits”, while the share of audits targeted by artificial intelligence and data mining was almost 45% last year compared with 32.5% in 2020 and 21.95% in 2019. For 2022, it expects 50% of targeted controls thanks to artificial intelligence.

The tax authorities do not hide their intention “to increase the use of artificial intelligence”. And not just to fight fraud. Since March 2021, the deployment of digital assistants “by recovering fines has made it possible to automatically process the accounting posting of received bank transfers and to agents to improve the results of enforcement through the intensification of prosecution”, explains DGFIP.

Also in 2021, the IRS began using artificial intelligence to “help contact center agents respond to user emails about payment issues.” It has also implemented the “Weak Signals” project, which is based on an algorithm capable of “targeting companies’ weaknesses in order to establish support actions as early as possible”. This system made it possible to detect 23,227 companies in difficulty. Of these, 11,952 were selected to be contacted and offered support.

Discover swimming pools

In the pilot phase, DGFIP’s “Innovative Land” project aims to use artificial intelligence to automatically detect buildings and swimming pools that have not been declared from aerial photographs. Problem, the device tested in nine departments would not really be developed, with error rates of 30% at this stage.

The tool will e.g. identify taxable swimming pools when they are above ground non-taxable swimming pools. The unions also report situations where artificial intelligence sees “buildings to be taxed instead of tarpaulins, roads, sidewalks, parking lots, slabs”, indicated to Parisian Frédéric Scalbert, representative of the CGT.

Trade unions mixed about the results of artificial intelligence in the fight against tax evasion. In particular, a report by Attac and Solidaires, supported by CGT, emphasized that if this “tool is interesting”, it has not yet yielded all the expected results. down jobs, and argued that “digital would do better …”. With nearly 105,000 in 2017, the DGFIP workforce was 94,669 in 2021.

Leave a Comment