Claims processing · Production
L'olivier Assurance uses Shift Technology's Force AI to automate claims fraud detection
The problem
L'olivier Assurance recognized it needed a new solution to fight claims fraud in order to continue offering competitive pricing and high levels of customer service.
Workflow diagram · grounded in source
1
Force detects suspicious claims
ai_action
“L'olivier now automatically receives alerts from Force for potentially fraudulent claims”
2
Alert with suspicion reasons
output
“Each alert specifies the reasons why the claim was deemed suspicious”
3
Claims handler investigates
human_review
“reducing the time it takes the claims handlers to conduct the fraud investigation”
Reported outcome
Force improved L'olivier's ability to detect fraud by reducing false positives and provided claims handlers with the right tools for investigations, reducing the time needed to conduct them.
Reported metrics
False positivesreducing the number of false positives
Fraud investigation timereduce the time it takes
Deployment timeless than five months
Reported stack
Force
Source
https://www.shift-technology.com/resources/case-studies/customer-stories/lolivier-assurance-sought-new-solution-to-fight-claims-fraud
Read source ↗Frequently asked questions
What did this team achieve with this AI workflow?
Force improved L'olivier's ability to detect fraud by reducing false positives and provided claims handlers with the right tools for investigations, reducing the time needed to conduct them.
What tools did this team use?
Force.
What results were reported?
False positives: reducing the number of false positives; Fraud investigation time: reduce the time it takes; Deployment time: less than five months (source-reported, not independently verified).
How is this claims processing AI workflow structured?
Force detects suspicious claims → Alert with suspicion reasons → Claims handler investigates.