Claims processing · Production
Pan-Asian insurer uses Shift Technology Force to identify 80% more fraud cases in real-time
The problem
A rapidly growing multi-line pan-Asian insurance company was experiencing increasing fraud, waste and abuse across its claims portfolio, with the vast majority of suspicious cases going undetected before claim settlement.
Workflow diagram · grounded in source
1
Claims submitted for processing
trigger
“Processing over 500,000 claims annually”
2
Real-time fraud detection
ai_action
“its ability to find fraud, waste and abuse cases quickly—prior to claim settlement and payment”
3
Straight-through claims processing
output
“increase straight-through claims processing by detecting fraud, waste and abuse in real time”
Reported outcome
Force enabled real-time fraud identification prior to claim settlement, with the insurer reporting that 80% of suspicious cases would previously have gone undiscovered, yielding considerable savings and increased straight-through processing.
Reported metrics
Annual claims volumeover 500,000
Previously undetected fraud cases now identified80%
Cost savings from fraud detectionconsiderable savings
Reported stack
Force
Source
https://www.shift-technology.com/resources/case-studies/customer-stories/pan-asian-insurance-company-improves-fraud-detection
Read source ↗Frequently asked questions
What did this team achieve with this AI workflow?
Force enabled real-time fraud identification prior to claim settlement, with the insurer reporting that 80% of suspicious cases would previously have gone undiscovered, yielding considerable savings and increased stra…
What tools did this team use?
Force.
What results were reported?
Annual claims volume: over 500,000; Previously undetected fraud cases now identified: 80%; Cost savings from fraud detection: considerable savings (source-reported, not independently verified).
How is this claims processing AI workflow structured?
Claims submitted for processing → Real-time fraud detection → Straight-through claims processing.