A crucial aspect of an effective AML compliance program involves monitoring transactions to detect suspicious activity. This encompasses various types of transactions, such as deposits, withdrawals, fund transfers, purchases, merchant credits, and payments. Typically, monitoring begins with a rules-based system that scans customer transactions for signs of potential money laundering. When a transaction matches a predefined rule, an alert is generated, and the case is referred to the bank's internal investigation team for manual review. If the investigators determine that the behavior is indicative of money laundering, a SAR is filed with FinCEN.


Join us as we uncover the incredible potential of machine learning in Anti-Money Laundering (AML) alert scoring, where data-driven insights make a tangible difference in the fight against money laundering.


About this Accelerator

Our primary goal with this accelerator is to develop a powerful predictive model that utilizes historical customer and transactional data, enabling us to identify suspicious activities and generate crucial Suspicious Activity Reports (SARs).


The model will assign a suspicious activity score to future alerts, improving the effectiveness and efficiency of an AML compliance program by prioritizing alerts based on their ranking order according to the score.


What you will learn  

  • To ensure a smooth and efficient machine learning process, we rely on the DataRobot Workbench. This remarkable tool enables us to analyze, clean, and curate the data, ensuring its quality and suitability for modeling.
  • By utilizing the DataRobot API, we can seamlessly create and manage experiments, exploring a wide range of machine learning algorithms tailored for the AML alert scoring task. The flexibility and ease of use of the API make it a valuable asset for data scientists throughout the process.
  • With just a few lines of code, we can train multiple machine learning models simultaneously, saving valuable time and computational resources. The model insights offered through the API provide invaluable interpretability.
  • Additionally, the DataRobot API allows us to compute predictions on new data before deploying the model into production. This pre-deployment testing phase enables us to evaluate the model's performance in real-world scenarios and make necessary adjustments to address any potential issues.
Version history
Last update:
‎09-05-2023 10:00 PM
Updated by: