SingaporeFinance and insurance2025 – ongoingIgloo
Machine learning risk engines and automatic claims approval
Igloo's insurance platform approved 80% to 90% of low-risk claims in under a second with no human involved
Problem
Igloo is a Singapore-based insurtech that sells insurance in Southeast Asia through partners such as ecommerce platforms. Pricing each policy at checkout and handling claims by hand would not keep up with partner sales events, when its load rose more than 10 times.
Approach
Igloo built custom risk engines and machine learning models on Google Cloud that price each policy from data such as product details, user demographics and recent claims. Customers can file gadget damage claims from a phone with a photo. Vision AI and Vertex AI compare the photo with pictures from the start of the policy to estimate repair cost, and an appraiser follows up on significant damage.
Results
Takeaway
Automatic approval covered the low-risk claims, and larger damage still went to a human appraiser. The company did not say how it measured the approval share.
Categories
- Industry
- Finance and insurance
- Business function
- Production and quality
- Innovation type
- Product and service innovation
- AI technology
- Predictive analytics and MLComputer vision
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Company's own claim
Sources
Source summaries
Google Cloud's customer story describes how the insurtech Igloo prices policies with machine learning and handles photo-based gadget claims with Vision AI and Vertex AI. It quotes Igloo's chief actuary saying 80% to 90% of low-risk claims are approved in under a second without a human. The page carries no date; the Internet Archive first saved it on November 15, 2025.
Full details are in the original sources.
