Thinklytics

Mid-Market P&C Carrier · Insurance · Chicago, IL · 14 weeks

Fraud detection model flags $6.2M in suspicious claims a year

A mid-market property and casualty insurer was manually reviewing every claim for fraud, using 12 full-time employees but still missing about $6 million in fraud each year. We implemented a real-time fraud detection model that scored all claims instantly. This cut the claims needing manual review from 18 of every 100 to about 5, and uncovered $6.2 million in suspicious claims for further investigation.

Challenge

The carrier depended on adjusters’ gut feelings and an outdated set of 23 static rules last updated four years ago. These rules flagged 18 of every 100 claims, causing a backlog that slowed down valid payments and annoyed customers. At the same time, more complex fraud slipped through undetected because the rules didn’t catch new patterns.

Approach

We developed a fraud propensity model based on four years of claims data, including adjuster notes, claimant behavior, and network connections between involved parties. The model scores each claim at submission and places it into one of four review categories: auto-approve, standard review, enhanced review, or refer to SIU. This approach replaced the previous 23 static rules with a flexible, data-driven scoring system.

Outcome

We cut the claims needing manual review from 18 of every 100 to about 5 of every 100, freeing up team capacity. SIU referrals rose from 3 to 18 of every 1,000, with 74 of every 100 of those cases confirmed as suspicious. In the first year, we flagged $6.2 million in fraudulent claims. At the same time, we sped up legitimate claim payments, cutting the cycle from 8.4 days down to 5.1.

How We Dug Into Network Data and Caught Fraud Rings in Action

Alright, here’s the scoop: these fraud rings were pretty slick. They filed claims under a bunch of different names but kept using the same addresses, phone numbers, or providers. We built a network graph linking all the claimants and ran some graph analytics on it. That’s how we caught suspicious clusters that the usual rules completely missed.

We put together an easy, step-by-step review to spot mistakes and keep everyone in the loop.

We dropped the basic approve-or-reject step and moved to a four-level review using fraud risk scores. If a claim seemed low risk, it bypassed the adjusters and got paid immediately. That way, the adjusters could zero in on the tricky or suspicious claims that actually needed their attention.

Results

  • $6.2M Suspicious claims identified annually
  • 18 to 5 of 100 Claims requiring manual review
  • 74 of 100 SIU referral confirmation rate
  • 8.4 to 5.1 days Legitimate claim payment cycle

We used to manually check 18% of all claims and still missed $6 million in fraud. Thinklytics built a model that narrows that down to just 5%, but it catches more fraud than we ever did before. Now our adjusters spend their time on the cases that actually need it.

VP of Claims, Mid-Market P&C Carrier

In the client's terms

The question

Which of this work should a person still be doing?

The situation

Fraud detection ran on adjuster instinct plus 23 static rules last touched four years earlier. The rules flagged 18 of every 100 claims, which created a backlog that delayed legitimate payments, while more sophisticated fraud went through untouched.

What we found

The rules were catching the fraud of four years ago. They were also catching a large volume of ordinary claims, so the team's attention was spread across a queue whose composition had nothing to do with actual risk.

What it produced

Claims requiring manual review fell from 18 in 100 to around 5. SIU referrals rose from 3 per 1,000 to 18, with 74 in 100 of those confirmed as suspicious. $6.2M in suspicious claims identified in year one, while legitimate claims paid faster, from 8.4 days to 5.1.

The roadmap

A fraud propensity model built on four years of claims including adjuster notes, claimant behaviour and network relationships between parties. Every claim is scored at submission into one of four dispositions: auto-approve, standard review, enhanced review, or refer to SIU. That replaced the 23 rules rather than layering on top of them.

The work behind this result

Related case studies

Frequently asked questions

Why do rules-based fraud systems generate so many false positives?

Because rules accumulate and never get removed. This carrier ran 23 static rules last touched four years earlier, flagging 18 of every 100 claims when around 14 a day were actually fraudulent.

Does reducing fraud review volume mean missing fraud?

Not here. Manual review fell from 18 in 100 claims to around 5 while SIU referrals rose from 3 per 1,000 to 18, with 74 in 100 of those confirmed as suspicious, and $6.2M a year in suspicious claims identified.

How does fraud detection affect legitimate claimants?

At this carrier, payment on legitimate claims accelerated from 8.4 days to 5.1, because clear claims now pay without passing an adjuster and attention concentrates on the complex and the suspicious.