We study the extent to which ML techniques can be used to improve tax auditing efficiency using administrative data, without the need of randomized audits. Using Italy's population data on sole proprietorship tax returns, audits and their outcome, we develop a new approach to address the so...

To study the role of tax professionals, we merge tax records of 2.5 million taxpayers in Italy with the respective audit files from the tax revenue agency. Our data covers the entire population of sole proprietorship taxpayers in seven regions, followed over seven fiscal years. We first document...

To study the role of tax professionals, we merge tax records of 2.5 million taxpayers in Italy with the respective audit files from the tax revenue agency. Our data covers the entire population of sole proprietorship taxpayers in seven regions, followed over seven fiscal years. We first document...