A New Fraud Tool Clusters Attack Patterns Across Industries

The ever-shifting attacks from online criminals has prompted Sift to launch ThreatClusters, a tool to detect similar fraud patterns across industries to better identify risk patterns.

San Francisco-based Sift says traditional fraud-detection models too narrowly focus on a single organization’s data or apply insights too broadly across diverse industries. It says ThreatClusters accounts for these challenges by clustering companies with similar fraud patterns into cohorts to account for risk-pattern nuance and to improve the client’s ability to make fraud-related decisions.

“Fraud actors are deploying increasingly sophisticated attacks, including AI-powered threats, that can overwhelm and outsmart many fraud prevention tactics,” Sift says.

Among these attacks is the use of synthetic identities, which was the fastest-growing form of digital fraud, according to TransUnion LLC’s 2024 State of Omnichannel Fraud Report, totaling $1.3 billion in fraud losses in 2023.

Among ThreatCluster’s features are improved fraud-detection accuracy, a quicker way to tap into the service’s benefits, and an improved detection flow that can introduce friction without compromising the customer experience and conversion rates, Sift says.

“By introducing industry-specific consortium models, we can provide our customers with unprecedented insights into the fraud patterns that are unique to their industry while protecting against emerging ones from other industries,” Raviv Levi, Sift’s chief product officer, says in a statement.

In a blog post, Levi says, based on 1 trillion annual events happening on its Global Network, Sift “has seen simultaneous fraud attacks across different industries originating from the same group of related IP addresses with other common attributes.” ThreatClusters combines the precision of customer-specific risk models with the broad data capture that comes from a global model, he says.