How Bercy uses artificial intelligence to target its tax audits

AI, artificial intelligence

New technologies boost the results of tax audits. Technological developments allow the tax administration to make decisive progress.

Bercy has given priority to the search for information in the context of the fight against fraud. It is a question of detecting the mechanisms of fraud, collecting, centralizing and enriching external information and the information dispersed in the services to propose the commitment of tax audits.

The advantages of data mining

The work of the tax administration teams on the databases makes it possible to increase the efficiency of tax audits. The use of databases (data mining) is optimized through the use of artificial intelligence. In 2021, nearly one out of two checks was carried out following an analysis of data mining. According to the latest report from the DGFiP published in May 2022, the productions from the datamining project Targeting fraud and valuation of requests (CFVR) represented, at the end of December 2021, more than 44% of the programming of tax audits, with an objective of 50% in 2022. The CFVR is a large-scale project developed in 2014 which aims to improve the efficiency of tax audit operations and is part of the modernization of data analysis work and targeting. Financed by the public action transformation fund, it explores information from 11 databases, such as Sirius-Pro, the tax audit software of the Directorate General of Public Finances (DGFiP), or the Official Bulletin of Civil Announcements and commercial (Bodacc). By relying on exploratory methods based on statistics and algorithms and by making it possible to model behavior, this tool uses artificial intelligence techniques to automatically identify cases of possible tax fraud.

A dedicated incubator

To innovate further, the tax administration relies on an internal incubator. With the Digital Factory, the delegation for digital transformation created in early 2021 has set up an experimentation laboratory, the Digital Factory, an incubator dedicated to DGFiP agents who wish to develop new digital public services. In 2021, it made it possible to develop two new projects: a range of tools to support small communities in setting up their investment projects and a new application to facilitate the collection of tourist tax by making reliable and pooling data from rental of furnished tourist accommodation, specifies the latest activity report of the Directorate General of Public Finance in June 2022. Indeed, data or data and their mass exploitation thanks to artificial intelligence are indeed now one of the main priorities from Bercy.

Building a data lake

The constitution of a data lake was initiated in 2021. It will eventually include all the data of the DGFiP, to optimize their use thanks to easy, centralized and secure access. The purpose of this project is to gradually bring, and depending on the pilot projects, a good part of the data available from the DGFiP into an infrastructure dedicated to the processing of large volumes of data, which is accompanied by services and additional tools dedicated to datascience, visualization or query tools, allowing users to better value the data available in the data lake. The data lake is therefore a Big Data processing tool. The initial work on real estate transactions made it possible to identify under- or over-valued transactions and to recall more than 2.7 million euros. The Innovative Land project is developed within this framework.

The experimentation of the Innovative Land project

In order to guarantee a better reliability of the bases of local direct taxation, the DGFiP uses, within the framework of this project, innovative technologies of artificial intelligence and valorization of data from aerial shots of the National Institute of geographic and forest information (IGN). It aims to detect on these aerial photographs, swimming pools and other undeclared buildings when they should be subject to direct local taxes. In concrete terms, the algorithms make it possible to extract public aerial images from the IGN, which can be consulted by everyone on the website, the contours of buildings and swimming pools. A computer processing then verifies, based in particular on the declarations of the owners made to the town planning and tax administration services, whether the elements thus detected on the images are correctly imposed on local direct taxes. A tax administration agent then systematically checks each anomaly detected before any follow-up operation of the owner of the property and ultimately of taxation. An experiment was launched in October 2021 in nine departments in the South-East (Alpes-Maritimes, Var, Bouches-du-Rhône, Ardèche, Rhône, Haute-Savoie) and West (Morbihan, Maine-et-Loire and Vendée), focusing first on the detection of swimming pools. The operation will then be extended to undeclared or incorrectly taxed buildings. This project aims, by optimizing the process of detecting undeclared constructions or developments, to make it possible to fight more effectively against declarative anomalies and thus better respond to citizens’ wishes for fairness and tax justice, through the fair taxation of goods. This project will also make it possible to improve the reliability of the bases of local direct taxation and to facilitate the representation on the cadastral map of buildings and swimming pools from aerial views.

A new Galaxie application, to optimize tax audits

The tax administration continues to develop new tools such as the Galaxie application, a computerized and automated processing of personal data. Third brick of the PILAT project (PILotage and Analysis of Control), GALAXIE has been deployed since April 5, 2022. The PILAT project started in 2018 is a major project to modernize the information system dedicated to tax control. Its objective is to constitute a single application for the entire tax audit chain, from programming to collection. The GALAXIE application was authorized by a decree of the Minister of the Economy (decree of March 11, 2022 authorizing by the DGFiP the processing of personal data called GALAXIE), after favorable opinion of the CNIL (deliberation n ° 2022- 025 of February 17, 2022 issuing an opinion on a draft order establishing by the DGFiP the processing of personal data called GALAXIE). It is a visualization tool, at the national level, on the one hand, of the links existing between professional entities (links of participation), and between professional entities and natural persons (links of manager, partner or shareholder), and on the other hand, elements of context on the financial and fiscal situation of these persons. For companies and legal persons or entities, these are data relating to VAT credit refunds, collective proceedings, fees paid, telephone number, e-mail address, sensitive persons indicator, data relating to tax compliance, management department of the tax file, data relating to the bank account, the links of managers and partners. For natural persons, this concerns data relating to indicators for sensitive persons, the service managing the tax dossier, and links between managers and partners. This tool is intended for authorized agents, for the purpose of improving compliance with tax obligations, to carry out research, investigation, programming, control and recovery of tax breaches. It will allow them to superimpose and cross-check a great deal of information, including the links between individuals and professional entities, manager, partner or shareholder links or between different entities such as the links of participation by putting them in contact with situations heritage and economics. This application will make it possible both to identify errors made by taxpayers in good faith and to facilitate the detection of tax evasion schemes and in particular to determine joint responsibilities in the organization of fraud thanks to a unification of tools which are now decompartmentalised .

Increase the use of artificial intelligence

The tools developed provide a gain in productivity and efficiency by providing all players in the tax audit chain with modern tools such as data visualization, automated and open to collection and litigation applications. It will also make it possible to strengthen and streamline the management of the activity in an integrated digital environment, to eliminate redundant tasks, while automating procedures. In general, the DGFiP intends to increase the use of artificial intelligence. The use of digital assistants frees departments from time-consuming and repetitive tasks, and offers agents the possibility of concentrating on missions where their expertise will be better valued. Thus, since March 2021, the deployment of digital assistants in the fine collection network has made it possible to automatically process the accounting posting of bank transfers received, and to agents to improve the results of forced collection thanks to the intensification of prosecutions. . The results recorded since commissioning are positive: the processing rate for bank transfers received by the DGFiP is over 50% on average, with peaks that can exceed 90% of transfers received for certain accounting items. In 2021, the DGFiP began using artificial intelligence to help contact center agents respond to user emails about payment difficulties. In this context, it has initiated a modernization of the standard response database, and the opening of access to all DGFiP documentation via a search engine. So many first steps in a paradigm shift within tax audit.

We would love to give thanks to the writer of this article for this outstanding web content

How Bercy uses artificial intelligence to target its tax audits

Explore our social media accounts and also other pages related to them