Carpe Data Reveals Insurance Fraud Frequency Dips as Claim Severity and Costs Surge

Insurance carriers are facing a significant shift in the fraud landscape as the financial severity of suspicious claims rises despite a marginal decline in overall referral frequency. New data indicates that while fraud rates in disability, workers’ compensation, and auto lines have dipped, the total value of contradictory evidence alerts has surged to over $263 million.

What was announced

Carpe has released its second annual Online Fraud Insights Report, which examines insurance claims fraud activity across the United States between 2024 and 2025. The findings reveal a paradox for claims departments: fraud referral rates decreased across three major lines of business, yet the cost associated with these claims is climbing. Specifically, referral rates fell by 1.7% in disability, 0.7% in workers’ compensation, and 0.4% in auto insurance. Despite these declines, the modeled value of contradictory alerts on the Carpe platform increased from $230.6 million in 2024 to $263.8 million in 2025, based on carrier-reported outcomes.

The report identifies critical geographic and demographic trends that challenge traditional assumptions. The highest concentration of fraud alerts per 100,000 residents was found in Connecticut, Nevada, South Carolina, Delaware, and Georgia, rather than in the most populous states. Demographically, claimants aged 35 to 44 were responsible for the highest volume of fraud alerts, accounting for 25.2% of the total. The data also highlights the dominance of specific digital platforms in fraud investigation:

• Facebook: Remains the primary source of social media evidence, representing 60.5% of contradictory flags.
• Other Platforms: Instagram (13.8%), LinkedIn (7.8%), TikTok (3.2%), and X (0.3%) combined account for significantly less evidence than Facebook alone.
• Claim Types: Disability recorded the highest referral rate at 7.2%, followed by workers’ compensation at 6.2% and auto at 5.3%.
• Timing: Approximately 36% of referrals involving contradictory evidence are identified within the first two months following a reported loss.

"AI is helping insurers identify which fraud alerts need further evidence review and which don’t, reducing both the time spent on analysis and increasing the value of their efforts," said Tom Rasmussen, VP of Claims Product at Carpe. "The decline in referral rates across three major lines is an encouraging sign, but it does not mean the risk is going away. Fraud tactics are evolving quickly, and the data shows that where and how suspicious activity appears can shift just as fast. Carriers need to assess claims early and continuously, so they find contradictory evidence before it drives unnecessary payouts or costly litigation."

Tom Rasmussen, VP of Product - Claims at Carpe.

The companies involved

Carpe is an insurance technology provider that specializes in automating complex data analysis for both underwriting and claims functions. The company’s platform is designed to help carriers, MGAs, and other insurance professionals surface contradictory evidence by monitoring a wide range of digital and social media sources. By providing modeled values for fraud alerts, the firm allows claims teams to prioritize investigations that represent the highest potential financial loss, rather than simply processing alerts based on volume.

The organization focuses on providing defensible data signals that can be used to mitigate unnecessary payouts and litigation costs. Its tools are integrated into the claims lifecycle to provide continuous monitoring, reflecting a shift away from point-in-time fraud checks. Carpe’s market presence is defined by its ability to handle unstructured data from platforms like Facebook and LinkedIn, converting digital footprints into actionable insights for special investigation units (SIUs) and claims adjusters across the United States.

What FF News has reported before

FF News has previously covered Carpe’s expansion into the commercial insurance sector, specifically regarding its efforts to streamline the front end of the insurance lifecycle. In August 2026, the company introduced a new tool for the market, as reported in Carpe Launches Minerva Reasoning Engine to Automate Small Commercial Underwriting. That development focused on helping small commercial insurers scale their operations by utilizing automated reasoning to handle underwriting tasks that were previously manual.

This prior reporting highlights a consistent technological trajectory for the company, moving from underwriting automation to sophisticated claims fraud detection. By applying similar reasoning engines to different stages of the insurance value chain, the firm has sought to address the industry-wide need for faster, data-driven decision-making that reduces manual intervention for carriers and MGAs.

What this means from an insurtech perspective

From an insurtech perspective, the rise in fraud severity despite falling frequency places immense pressure on legacy claims systems and manual investigation workflows. Carriers and reinsurers are facing a "quality over quantity" challenge; the priority is no longer just spotting a lie, but quantifying the financial risk of that lie early in the claim lifecycle to protect loss ratios. The dominance of Facebook as an evidence source highlights a persistent reliance on unstructured social data, which is increasingly difficult to verify manually as digital manipulation tools become more accessible. This creates a clear necessity for automated, defensible evidence gathering that can withstand litigation. For brokers and MGAs, these trends suggest that continuous monitoring is becoming a standard requirement for maintaining capacity and customer trust, moving the industry away from static fraud checks at the point of first notice of loss.