LexisNexis Risk Solutions, the data analytics and risk intelligence provider, has rolled out a fraud scoring tool that retrains itself automatically, a move that could reduce how much fraud teams rely on manually maintained rules.
The product, named Emailage Adaptive, is built entirely on AI models. During trials, it examined signals including email, IP, phone and address data and identified roughly 90% of fraud cases among the riskiest transactions. It also cut false positives by over 80%.
The tool learns on an ongoing basis from the transaction records, fraud trends and sector context specific to each client. From this, it generates successive fraud prevention models customised to that organisation, which update without human input to produce sharper risk scores and stronger predictive performance.
LexisNexis Risk Solutions has designed the offering for use across multiple industries and in high-risk situations such as opening new accounts, managing existing accounts and processing payments.
Email data sits at the core of the approach. Consumers worldwide hold 7.9bn email accounts, and a third of people retain the same address for over a decade. When combined with wider risk intelligence, the history and behaviour linked to these addresses can reveal distinctive insights.
Dell Technologies offers an early proof point. Since adopting Emailage Adaptive to inform its risk decisions, the company has doubled the rate at which it catches high-risk fraud and lowered manual reviews of low-risk transactions by 83%.
The launch arrives as fraud pressures intensify. Research from the company’s Cybercrime Report 2026 found that one in every 11 attempts to create a new account globally is fraudulent.
Explainability underpins the system’s design. Its models draw on a steady supply of client transaction data, sector trends and newly identified fraud behaviour to feed a cycle of ongoing improvement.
As the models mature, they deliver risk scores accompanied by reason codes that show whether a given factor raised or lowered the output. The firm says its responsible AI framework supports transparency, helps limit bias and helps safeguard data privacy by using dependable data sources. Customer feedback that has been verified also triggers automatic recalibration once new patterns are confirmed.
Dell Technologies director, business operations Jeremy Cole said, “The self-calibrating AI model has helped us modernise fraud prevention by minimising reliance on static rules and manual policy adjustments. Our fraud team can now calibrate less, act faster and approve more legitimate transactions with confidence.”
LexisNexis Risk Solutions global head of fraud and identity Kimberly Sutherland said, “As generative AI scales, fraud attacks are now happening at a faster rate than most manual prevention strategies can keep pace with, overwhelming systems and exposing businesses to ever greater risk.
“By continuously learning from fraud outcomes, backed by cross industry risk intelligence, a self-calibrating fraud model can adjust instantly to subtle changes in fraud patterns, removing the lag between when patterns emerge and when defences calibrate. This allows fraud teams to continually enhance predictive accuracy while reducing manual workload.”
Copyright © 2026 RegTech Analyst
Copyright © 2026 RegTech Analyst
