Share these talks and lectures with your colleagues
Invite colleaguesPractice paper
Applications of machine learning in the identification, measurement and mitigation of money laundering
Journal of Financial Compliance,
4
(2),
140-166
(2020)
Abstract
The cost of financial crimes compliance continues to grow, locked in step with increasing regulatory expectations and volumes of low-productivity work items. Financial institutions cannot afford to wait for entirely new paradigms and instead are investing in solutions that provide near-term relief and can orient institutions towards the future. Technologies like artificial intelligence and machine learning (ML) — well entrenched in applications like credit risk modelling and fraud detection — are gaining traction within the broader financial crimes domain, and anti-money laundering (AML) in particular. To obtain the business value of these ML and other technologies, financial institution managers need the toolset to succinctly understand these methods and assess what approaches are appropriate and effective for their institutions. The twofold goals of this paper to equip institutional stakeholders with this information are:
1. Describe the high-level applicability of ML to AML, with a focus on transaction monitoring.
2. Provide an overview of the AML ML practices that are already in place within the industry; are on the immediate horizon; or are promising opportunities actively being investigated for the future.
Keywords: anti-money laundering; financial crimes; analytics; machine learning; artificial intelligence; algorithms; models; RegTech
The full article is available to subscribers to the journal.
Author's Biography
Nikhil Aggarwal is a Managing Director at Promontory Financial Group, an IBM Company and a Member of the IBM Industry Academy. Nikhil advises clients on antimoney-laundering issues, financial-crime compliance and other regulatory matters. He has extensive experience in programme design and review, with a focus on applying machine learning and analytics to risk assessments, models for rating client risks, transaction-monitoring system optimisation, suspicious-activity reporting, metrics and reporting and model validation. His client engagements focus primarily on improving the efficiency and effectiveness of transaction-monitoring systems by deploying machine-learning models, undertaking rule design and threshold tuning/calibration and deploying case/alert risk-scoring models. Nikhil holds a master of business administration degree from the University of California, Los Angeles, and an master of arts degree in economics from the University of Southern California.
Sean Wareham is an associate at the Promontory Financial Group, an IBM Company, who specialises in antimoney laundering analytics and controls. He has a background in helping financial institutions in designing antimoney laundering programmes, optimise transaction-monitoring systems and develop the next generation of machine learning-based monitoring. Sean holds a bachelor of sciences degree in computer science from Duke University.
Rasmus Lehmann is a Data Scientist with the IBM Client Innovation Center located in Copenhagen, Denmark, specialised in machine learning. He has a background in academic research, working on natural language processing while employed at the IT University of Copenhagen. Rasmus holds a master of sciences degree within computer science specialised in business intelligence and machine learning from the IT University of Copenhagen, and a bachelor of sciences degree in business and communications from Copenhagen Business School.
