Data analysis and tax compliance

The aim of this course is to introduce students to the main statistical techniques used nationally and internationally to estimate tax risk and control tax evasion. The course will range from classification and regression models to group analysis segmentation models and will also make reference to modern machine learning models, highlighting pros and cons. The course will also explore AI tools used by tax authorities at different stages of the tax procedure, focusing on the the need to balance the general interest of raising revenue with the protection of taxpayers' rights.

At the end of the course, students will be able to understand which models and statistical tools have been used to support the determination of risk classes and estimates of tax evasion. Students will also learn how to interpret statistical outputs resulting from the application of complex models. To manage these tools, students are expected to master the legal requirements of tax assessment methods and tax compliance procedures. They will be able to critically assess the threats and opportunities related to automated decision making by tax authorities and propose appropriate improvements.