Articolo pubblicato su FiscoOggi (

Tax Pills

Green light from the EU to finance the Revenue Agency project in the field of Artificial Intelligence, network science and data visualization

intelligenza artificiale

Space for new methodologies and high tech-tools, with the utmost attention to privacy and data protection, to prevent and combat VAT frauds and the improper use of tax credits also implemented through complex corporate structures and multifaceted transactional schemes. With the green light of the European Union to finance the Italian Revenue Agency project, "A data driven approach to tax evasion risk analysis in Italy" a significant step forward in the fight against tax evasion and avoidance will be made.

Fighting evasion is not just a question of data, requires innovative tools - With network science, artificial intelligence and data visualization, the Agency intends to make the most of the vast wealth of data available to it, such as, for each single year, 42 million of tax returns, 750 million information communicated by third parties, 400 million active financial relationships, 197 million F24 payments, approximately 2 billion electronic invoices and over 150 million registered properties.

The Project - The strategic vision of the new Revenue, that will also see the collaboration of the technological partner Sogei, aims to innovate the non-compliance risk assessment processes. Basically, we will introduce, test and use innovative techniques of network analysis, machine learning and data visualization, in order to create a new scheme to support the processes of identifying taxpayers at high risk of tax fraud. The Project is part of the European programs in support of structural reforms in response to the Covid-19 emergency. The general goal is to make the EU economies more sustainable, resilient and prepared for the challenges posed by the green and digital transitions.

Methodology and areas of intervention of tackling tax evasion by modeling the co-evolution of tax schemes with auditing policies. - In recent years, all over the world, including in Italy by the Agency, various innovative and increasingly sophisticated tools have been created dedicated to the analysis of the risk for tax compliance. With a view to an increasingly strategic and widespread digitalization, with the current project the Agency aims to innovate and further integrate within the processes and activities related to the fight against tax evasion what has already been carried out in recent years in the field of advanced data analysis, in terms of methodologies, processes and technologies.

How the new anti-tax evasion scheme will work - Let image an algorithm that can anticipate tax evasion by modeling the co-evolution of tax schemes with auditing policies. Malicious tax non-compliance, or evasion, accounts for billions of lost revenue each year and an arrays of fraudulent schemes could finally be identified and closed. How? By modeling both the tax schemes and auditing policies within a single framework. In particular, new tools can serve as an early warning system to help focus enforcement efforts. In addition, the audit policies can be fine tuned to help improve tax scheme detection. It’s a new approach expressly called co-evolution system between tax evasion and audit policy.

The kit of new highly technological tools – First of all, network science, which implies the representation of data in the form of networks, making it easier bring out indirect and not evident relationships between subjects (for example relations between companies) that can be correlated to tax evasion and avoidance schemes. Then. visual analysis of information, that allows to enhance the skills of analysts, accelerating and making their process of acquiring and processing data more intuitive and natural. Finally, artificial intelligence, whose main function is to accelerate decision-making processes, always under control or by analysts, and increases its accuracy and effectiveness.

Stefano Latini