FinlandFinance and insurance2024 – ongoingSampo
If insurance Watson claims-fraud detection
Sampo reported 5 times better fraud detection from If's Watson model
Problem
If used a rule-based model to identify suspicious insurance claims. It sought better detection to guide further investigation.
Approach
If used Watson, an AI model that predicted fraud risk for individual claims. The scores supported further investigation. Sampo reported savings in 2024 and expected further savings as country models were implemented.
Results
Takeaway
The model supported investigation rather than establishing fraud by itself. Sampo did not define the detection measure behind its comparison.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Finance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
Sampo described Watson as a claims-fraud risk model used to select claims for investigation. It reported 5 times better detection than its previous rules and a savings uplift in 2024.
Full details are in the original sources.
