Rep Data Adds Fraud Prevention Layer

In New Orleans, research data and fraud prevention solutions firm Rep Data has announced the launch of 'Second Shield', which it says 'identifies subtle, multivariate patterns that signal fraud, and blocks them with 97% accuracy.'

As the name suggests, the new machine learning-based feature forms an extra layer of protection - sitting between the firm's Research Defender fraud prevention software and live fieldwork. Second Shield learns from every survey response that is later overturned in reconciliation, using it as a labeled training point feeding a classifier that refreshes nightly across Research Desk and Research Defender traffic. The tool draws on several dozen signals, including CPI, open-end length, device/OS, geo, timestamps, supplier, and historical behavior across nearly 200 sample sources. It can also alert the company's services team about potential crossings of fraud thresholds, allowing them to pause, switch, or price-adjust supply before issues escalate.

Founder & CEO Pat Stokes (pictured) says the new tool 'transforms closed-'loop data from our DIY sampling platform, Research Desk and Research Defender into predictive power, blocking the sophisticated, hard-to-spot fraud patterns that slip past the current limits of fraud prevention technology.' CTO Vignesh Krishnan adds, 'Second Shield is a living system. The more data it sees, the smarter it gets, giving our clients a proactive edge in an arms race where yesterday's tactics won't win tomorrow's battles.'

The service is already operations for the firm's Research Services customers, and will add API-driven autonomous controls later in 2025.

Web site: www.repdata.com .

All articles 2006-23 written and edited by Mel Crowther and/or Nick Thomas, 2024- by Nick Thomas, unless otherwise stated.