Technical Notes and Manuals

Generative Artificial Intelligence for Compliance Risk Analysis: Applications in Tax and Customs Administration

ByJoshua Aslett, Thomas Cantens, François Chastel, Emmanuel A Crown, Stuart Hamilton

August 8, 2025

Preview Citation

Format: Chicago

Joshua Aslett, Thomas Cantens, François Chastel, Emmanuel A Crown, and Stuart Hamilton. "Generative Artificial Intelligence for Compliance Risk Analysis: Applications in Tax and Customs Administration", Technical Notes and Manuals 2025, 013 (2025), accessed 12/5/2025, https://doi.org/10.5089/9798229012430.005

Export Citation

  • ProCite
  • RefWorks
  • Reference Manager
  • BibTex
  • Zotero
  • EndNote

Disclaimer: This Technical Guidance Note should not be reported as representing the views of the IMF. The views expressed in this Note are those of the author(s) and do not necessarily represent the views of the IMF, its Executive Board, or IMF management.

Summary

This technical note provides an introduction to generative artificial intelligence (GenAI) and its potential to support compliance risk analysis in tax and customs administration. Written primarily for a technical audience, it seeks to raise awareness of GenAI by explaining and demonstrating its capabilities. The note opens with a brief conceptual overview of GenAI technology. It then describes four generalized use cases where GenAI can augment the work of risk analysts. As experimental proofs of concept, a selection of worked examples is presented. Having demonstrated GenAI’s potential, the note then provides basic guidelines to help administrations that may be considering implementing the technology in an operational setting. It concludes with forward-looking statements on likely developments.

Subject: Artificial intelligence, Compliance risk management, Customs administration core functions, Machine learning, Revenue administration, Tax administration core functions, Taxes, Technology, Trade facilitation, Training and development in revenue administration

Keywords: advanced analytics, AI risk assessment methodology, artificial intelligence, ASYCUDA, compliance risk analysis, customs administration, Customs administration core functions, GenAI support compliance, generative artificial intelligence, information technology, tax administration, Tax administration core functions, Training and development in revenue administration, understanding artificial intelligence, use case