Refining Public Policies with Machine Learning: The Case of Tax Auditing / Marco Battaglini, Luigi Guiso, Chiara Lacava, Douglas L. Miller, Eleonora Patacchini.

By:

Battaglini, Marco

Contributor(s):

Material type: Text

TextSeries: Working Paper Series (National Bureau of Economic Research) ; no. w30777.Publication details: Cambridge, Mass. National Bureau of Economic Research 2022.Description: 1 online resource: illustrations (black and white)Subject(s):

Other classification:

Online resources:

Available additional physical forms:

Hardcopy version available to institutional subscribers

Abstract: 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 called selective labels problem - the fact that a ML algorithm must necessarily be trained on endogenously selected data. We document the existence of substantial margins for raising revenue from audits by improving the selection of taxpayers to audit with ML. Replacing the 10% least productive audits with an equal number of taxpayers selected by our trained algorithm raises detected tax evasion by as much as 38%, and evasion that is actually payed back by 29%.

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings
Item type	Home library	Collection	Call number	Status	Date due	Barcode	Item holds
Working Paper	Biblioteca Digital	Colección NBER	nber w30777 (Browse shelf(Opens below))	Not For Loan

Total holds: 0

Collection: Colección NBER Close shelf browser (Hides shelf browser)

Previous	No cover image available	No cover image available	No cover image available	No cover image available	No cover image available	No cover image available	No cover image available	Next
Previous	nber w30774 Heterogeneous Downward Nominal Wage Rigidity: Foundations of a Static Wage Phillips Curve /	nber w30775 Search Frictions and Product Design in the Municipal Bond Market /	nber w30776 Lasting Scars: The Impact of Depression in Early Adulthood on Subsequent Labor Market Outcomes /	nber w30777 Refining Public Policies with Machine Learning: The Case of Tax Auditing /	nber w30778 Identification and Estimation of Discrete Choice Demand Models when Observed and Unobserved Characteristics are Correlated /	nber w30779 The Economics of the Public Option: Evidence from Local Pharmaceutical Markets /	nber w3078 Tax Compliance: An Investigation Using Individual TCMP Data /	Next

December 2022.

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 called selective labels problem - the fact that a ML algorithm must necessarily be trained on endogenously selected data. We document the existence of substantial margins for raising revenue from audits by improving the selection of taxpayers to audit with ML. Replacing the 10% least productive audits with an equal number of taxpayers selected by our trained algorithm raises detected tax evasion by as much as 38%, and evasion that is actually payed back by 29%.