Seminar: Detecting Suspicious Financial Activity Using Machine Learning
Vice President and Machine Learning Manager
Financial Intelligence Unit
Jie (Patrick) Xu
Assistant Vice President and Quantitative Model Analyst
Financial Intelligence Unit
Detecting unusual and suspicious money laundering and terrorist financing activity is an important problem faced by all financial institutions. The obligation of banks to report suspicious activity is mandated by the Bank Secrecy Act, the primary U.S. anti-money laundering law which includes provisions of the USA PATRIOT Act to detect, deter, and disrupt terrorist financing networks. Traditionally, banks have used rules-based programs to monitor transactions for suspicious activity. Although simple, these programs may not result in good accuracy, can generate redundant alerts, need to be manually updated, and cannot easily adapt to changes in the data. In this talk, we explore a machine learning-based approach to detecting suspicious financial activity. Inspired by the literature on class imbalance learning, we develop a hybrid method called 'EasyEnsembleRF' that deeply explores the data while retaining fast training speeds. Using the entire extent of transaction data available for training and testing, we compare EasyEnsembleRF to several benchmark predictive models, including random forests, logistic regression, and neural networks. The winning algorithm has by far the lowest false negative rates of all the models tested, while maintaining low false positive rates. Production versions of the algorithm are currently being piloted and are expected to result in enhanced detection of suspicious activity.
Sanjay Melkote is a Vice President and Machine Learning Manager in U.S. Bank’s Financial Intelligence Unit and based in Polaris, Columbus, Ohio. He oversees anti-money laundering-related machine learning development, iterative training, model comparison, and documentation for the Bank. His team focuses on the creation and evaluation of new models and tools to mitigate the risks of high-risk products, customers, and transaction channels.
Dr. Melkote has tackled many problems in the private and public sectors using machine learning, predictive analytics, and optimization. He has served in several positions in academia, government, and industry, and holds a Ph.D. in Industrial Engineering and Management Sciences from Northwestern University.
Jie (Patrick) Xu is an Assistant Vice President and Quantitative Model Analyst in U.S. Bank’s Financial Intelligence Unit and based in Polaris, Columbus, Ohio. He designs and develops anti-money laundering-related machine learning models, performs iterative training, model comparison, and analysis, and writes pertinent documentation for the Bank.
Dr. Xu has also developed and validated commercial and consumer credit risk models, economic capital models, and operational loss forecast models in the financial services industry. He holds a Ph.D. in Applied Statistics from the University of Alabama and has particular expertise in the design and implementation of ensemble models.