Bibliographic details and abstracts are available to all. Downloads of full-text dissertations are restricted to University of Portsmouth members who must login. MPhils may be accessed by all.

Abstract

This paper aimed to examine how AI/ML are currently being used to address TBML risk and detected cases and improvements that need to be made to improve accuracy of these models and their applicability for law enforcement. By using a systematic review of the literature using relevant sources identified using the keywords; Trade-Based Money Laundering, risk indicators, over- and under- invoicing, customs, Artificial Intelligence, machine learning, and risk analysis, this paper qualitatively explores the complexities of TBML and the global effort to fight this risk, current AI/ML models and their advantages and limitations, and how these can be applied to the needs of law enforcement. This paper is split into an introduction and background information on TBML and AI/ML, followed by the research question, method, and limitations. A literature review is conducted in two parts, TBML and AI/ML, with a summary section to link the two, before going onto explaining the findings from this literature search and how they can be linked together to form recommendations for AI/ML models in this field. This paper goes on to make recommendations for future research and development of these tools, suggestions for future research, and finally a conclusion.

Course: Criminal Justice - MSc - C2681F

Date Deposited: 2024-11-21

URI/permalink: https://library.port.ac.uk/dissert/dis14564.html