HGS has introduced AMLens, an AI-powered solution aimed at accelerating Anti-Money Laundering (AML) investigations for banks and financial institutions. The platform is designed to reduce investigation time, lower false positives, and improve regulatory alignment as financial crime teams face increasing volumes of alerts and stricter compliance expectations.
According to HGS, AMLens applies machine learning and natural language processing (NLP) across the AML lifecycle—from detection and triage to contextualisation and reporting—while maintaining transparency and human oversight. The company positions the solution as an example of “realised AI”, where automation delivers measurable operational outcomes rather than experimental gains.
Addressing alert fatigue and fragmented data
AML teams globally continue to struggle with manual case resolution, alert fatigue, and siloed data sources. AMLens seeks to address these challenges by consolidating structured and unstructured information—such as transaction data, analyst notes, and external public records including Google and LexisNexis—into a single analyst-facing workflow.
Built as a modular, API-first platform, AMLens is designed to integrate with existing AML and compliance systems. HGS said the solution is applicable across multiple financial services segments, including retail and consumer banking, payments and fintech, credit cards and lending, and wealth management.
Explainable AI with human-in-the-loop controls
A key design principle behind AMLens is explainability. The platform combines AI-driven analysis with human validation to ensure regulatory defensibility and audit readiness. Automation is applied to repetitive tasks such as transaction monitoring, sanctions screening, and customer due diligence, while investigators retain decision-making control.
“In today’s regulatory environment, time is a critical weapon against financial crime. Legacy systems are drowning analysts in false positives and fragmented data, hindering their ability to act quickly,” said Eric Purdum, Head of Sales – Americas at HGS. “AMLens is a game-changer because it’s built on the principles of Explainable AI and human-in-the-loop validation that can automate routine tasks such as transaction monitoring, sanctions screening, and customer due diligence (CDD). We’re giving analysts speed, clarity, and confidence by providing transparent decision-making and automated, policy-aligned narratives. This allows them to focus on high-value and high-priority investigations, making a tangible difference in the fight against money laundering.”
Early deployment results show measurable gains
HGS said early client deployments of AMLens have demonstrated significant efficiency improvements. According to the company, average case analysis time was reduced by 75%, falling from roughly two hours to about 30 minutes. False positive rates declined by more than 60%, from around 18% to 7%.
These improvements translated into a threefold increase in investigator productivity, with daily case handling rising from eight to 24 cases per investigator. Overall turnaround time was reduced by 75%, from 48 hours to approximately 12 hours.
Streamlining investigations without removing judgment
AMLens incorporates a three-stage workflow that combines automated analysis with analyst intervention. For example, when a third-party monitoring system flags suspicious international wire transfers, AMLens initially scores the case using its adaptive risk engine. Analysts can then request additional information directly within the system before escalating the case, supported by AI-generated Suspicious Activity Report (SAR) narratives.
HGS said this approach enables faster resolution—often within about 55 minutes—while preserving the human judgment required for regulatory compliance.
Implications for financial crime operations
As regulators demand faster reporting, clearer audit trails, and stronger model transparency, explainable AI is increasingly becoming a requirement rather than an option in AML operations. HGS’s launch of AMLens reflects a broader shift in the financial services industry toward AI systems that can demonstrably reduce workload, improve accuracy, and stand up to regulatory scrutiny—without removing investigators from the decision loop.