AML Alert Triage

Quickly integrate alert prioritization into an existing AML process with agile model review capabilities.

The goal of this adapt and apply solution is to show Financial Crime analysts how Dataiku can be used to support initial assessment through risk likelihood prioritization and review effectiveness of used business rules.  More details on the specifics of the solution can be found on the knowledge base. This solution is only available on installed instances.

Business Overview

Anti-money laundering processes are complex and multifaceted, and generate large numbers of alerts which must be investigated. Most generated alerts are ultimately not escalated for further review. Reducing the total number of false-positive alerts is a complex and heavily regulated process. Failures in anti-money laundering set-ups are under tight regulatory scrutiny and led to +10bn$ in fines in 2020. At the same time, analyses suggest that above 85% of generated alerts are false positives. Which, considering regulatory duty to provide systematic analysis, lead to a significant gap in efficiency and focus. 

Improvements in AML processes must occur at many points in the chain, and a modular solution that can be readily incorporated into existing flows to more efficiently process existing alerts is a means to improve detection rates and reduce alert fatigue, acting as a first step to AML set-up efficiency. Thanks to this Solution, Financial Crime analysts are supported in initial assessment through risk likelihood prioritization. Insights delivered by the Solution also include other elements  which can be used as a starting point to review effectiveness of used business rules, paving the road to further AML set-up reinforcement.


  • Easy to integrate modular design allows any existing AML process to gain this capability quickly and without disruption.
  • Simple data requirements ensure that teams can begin seeing benefits rapidly.
  • Integrated model re-evaluation and streamlined redeployment means the module can remain fully operational over the long term with minimal maintenance.
  • Business-friendly explainable AI allows for rapid and intelligent review of the prioritization model, and informs potential future enhancements of underlying business rules.