A Time-Frequency based Suspicious Activity Detection for Anti-Money Laundering

TL;DR

This paper introduces a novel time-frequency analysis feature set for detecting suspicious financial transactions, significantly enhancing anti-money laundering systems by improving accuracy over traditional rule-based and CRM feature methods.

Contribution

The study presents a new 2-D time-frequency feature set combined with machine learning, demonstrating improved detection performance in real banking data environments.

Findings

Time-frequency features differentiate suspicious and non-suspicious entities effectively.

The proposed method improves detection precision over traditional approaches.

Simulated annealing optimizes hyperparameters for better model performance.

Abstract

Money laundering is the crucial mechanism utilized by criminals to inject proceeds of crime to the financial system. The primary responsibility of the detection of suspicious activity related to money laundering is with the financial institutions. Most of the current systems in these institutions are rule-based and ineffective. The available data science-based anti-money laundering (AML) models in order to replace the existing rule-based systems work on customer relationship management (CRM) features and time characteristics of transaction behaviour. However, there is still a challenge on accuracy and problems around feature engineering due to thousands of possible features. Aiming to improve the detection performance of suspicious transaction monitoring systems for AML systems, in this article, we introduce a novel feature set based on time-frequency analysis, that makes use of 2-D representations of financial transactions. Random forest is utilized as a machine learning method, and simulated annealing is adopted for hyperparameter tuning. The designed algorithm is tested on real banking data, proving the efficacy of the results in practically relevant environments. It is shown that the time-frequency characteristics of suspicious and non-suspicious entities differentiate significantly, which would substantially improve the precision of data science-based transaction monitoring systems looking at only time-series transaction and CRM features.