Hummingbird has acquired Quantimon, a machine learning platform focused on anti-money laundering risk detection, as it expands its AI-powered financial crime compliance platform.
The acquisition brings Quantimon’s machine learning models and federated learning technology into Hummingbird’s transaction monitoring offering, creating a tighter connection between alert generation, investigation, and model improvement.
Hummingbird said most AML transaction monitoring systems still rely heavily on rules, which can generate large numbers of false-positive alerts. Machine learning has historically been difficult to apply because training models requires labeled outcomes, while many institutions store those outcomes in unstructured case notes.
Hummingbird’s platform records alert dispositions from both compliance analysts and AI agents in structured form. By integrating Quantimon, those outcomes can feed back into detection models so they learn from how alerts are resolved.
Quantimon’s models are designed to learn from an individual institution’s own alert decisions, including whether activity is closed, escalated, or ultimately filed.
The company also developed a federated learning network intended to allow institutions to benefit from patterns observed across other organizations without sharing underlying customer data.
Hummingbird plans to use the combined technology to improve how transaction monitoring alerts are generated and ranked by risk.
The platform will continue supporting rule-based detection while adding machine learning models trained on each institution’s outcomes. Hummingbird said those models can help identify activity resembling previously confirmed cases even when no existing monitoring rule is triggered.
Over time, Hummingbird also plans to incorporate additional signals from third-party intelligence and patterns across its broader network.
The Quantimon team will join Hummingbird and work on expanding its transaction monitoring capabilities.
Hummingbird’s platform supports financial institutions across customer screening, transaction monitoring, investigations, and regulatory reporting. Its customers include Raymond James, Symetra, Crypto.com, DraftKings, and Etsy.
The acquisition reflects Hummingbird’s broader strategy of combining AI agents with human compliance teams while using the information generated during investigations to continuously improve financial crime detection.
KEY QUOTES:
“AI has changed how compliance teams investigate financial crime, but the systems generating the alerts have stayed largely the same. Today our customers can clear alerts faster than ever, but they shouldn’t have to spend that capacity on noise. With Quantimon, every alert worked by an AI agent or analyst sharpens detection, so more of the alerts that reach our customers will be ones worth their time.”
Joe Robinson, Co-Founder And CEO Of Hummingbird
“At Apple, Xoom, and PayPal, we watched our compliance teams spend their days working on seemingly endless alert backlogs. We started Quantimon to fix that at the source. I’m thrilled Quantimon is joining Hummingbird, where our technology can be at the center of a loop that makes both detection and investigation smarter.”
Ben Duranske, Co-Founder And CEO Of Quantimon
