Detecting money laundering transactions with machine learning

TLDR

This study is among the few published AML models applied to a realistically sized dataset of suspicious transactions. The paper develops and validates a machine learning model to prioritize financial transactions for manual investigation of potential money laundering, and introduces a new performance measure to compare it with the bank’s existing AML system. The authors train a supervised machine learning model on a large Norwegian bank dataset, using normal legal transactions, internally flagged suspicious alerts, and reported money laundering cases, to predict the probability that a new transaction should be reported based on sender/receiver background, prior behavior, and transaction history. The study shows that excluding non‑reported alerts and normal transactions from training yields sub‑optimal results, and that the proposed method outperforms the bank’s current AML approach according to a fair performance metric.

Abstract

Purpose The purpose of this paper is to develop, describe and validate a machine learning model for prioritising which financial transactions should be manually investigated for potential money laundering. The model is applied to a large data set from Norway’s largest bank, DNB. Design/methodology/approach A supervised machine learning model is trained by using three types of historic data: “normal” legal transactions; those flagged as suspicious by the bank’s internal alert system; and potential money laundering cases reported to the authorities. The model is trained to predict the probability that a new transaction should be reported, using information such as background information about the sender/receiver, their earlier behaviour and their transaction history. Findings The paper demonstrates that the common approach of not using non-reported alerts (i.e. transactions that are investigated but not reported) in the training of the model can lead to sub-optimal results. The same applies to the use of normal (un-investigated) transactions. Our developed method outperforms the bank’s current approach in terms of a fair measure of performance. Originality/value This research study is one of very few published anti-money laundering (AML) models for suspicious transactions that have been applied to a realistically sized data set. The paper also presents a new performance measure specifically tailored to compare the proposed method to the bank’s existing AML system.