Claims fraud detection
Flagging suspicious claims for review by the Special Investigations Unit (SIU). In US P&C, fraud leakage is estimated at 10% of total claim payouts, a headline number that has driven procurement of detection tools for three decades.
The three rungs
SIU analysts work from rules-of-thumb and historical red flags. Claims-admin systems add rule-based scoring in the early 2000s: repeated claimant names, high-severity events on low-value policies, claims filed within days of policy inception.
Built around deep learning or LLMs from day one; tools founded mostly post-2015.
The legacy-to-AI-native transition on this action is unusually clean, because no dominant modern pure-SaaS entrant emerged. Shift Technology, founded in Paris in 2014, moved the category to AI-native with graph analytics and anomaly detection over the full claim graph, and extended into subrogation and financial-crime detection in 2025. Shift reports 100+ customers across 25 countries; Liberty Mutual and CNA Financial are the named US carriers on public record.
Ranked comparison
- 13/2065%
AI platform for insurers focused on claims fraud detection, claims automation, subrogation, and financial-crime detection. 100+ customers across 25 countries; 2 billion claims analysed.
- traction
- 3/5
- maturity
- 4/5
- coverage
- 4/5
- recognition
- 2/5
- 13/2065%
Real-time fraud and risk detection platform for P&C insurers, covering the full policy lifecycle from underwriting risk assessment through claims fraud. 300+ implementations across 45+ countries.
- traction
- 2/5
- maturity
- 5/5
- coverage
- 4/5
- recognition
- 2/5
- 10/2050%
AI-native software suite for personal and commercial claims automation and fraud detection. Automates triage, coverage checks, and document review, accelerating settlement times while flagging fraud signals.
- traction
- 1/5
- maturity
- 3/5
- coverage
- 4/5
- recognition
- 2/5