GCPEvidence: Medium50/100

Delos Insurance Solutions uses Google Earth Engine and Vertex AI to underwrite wildfire insurance

Use case typeRisk assessmentUpdated Jul 15, 2026

Delos Insurance Solutions needed to make wildfire-risk underwriting viable for California homeowners who were often considered uninsurable by other carriers. The company built wildfire-behavior and geospatial risk models with Google Earth Engine, then used Colab notebooks and Vertex AI pipelines for model training and deployment, plus Google Maps Platform for a quote-to-buy underwriting portal. The solution let Delos price policies more accurately, offer coverage in high-risk areas, and support agents with a fast online underwriting workflow.

Industry
Insurance
Published
July 2026

Reported outcomes

−80%

data preparation timeTime & speed

−95.7%quote-to-buy underwriting time5 minutesquote-to-buy underwriting time+83%coverage area in California30,000 propertiesproperties insured

Strategic outcomes

Risk & complianceInsured homeowners deemed uninsurable by other carriersCompetitive differentiationLower-cost wildfire insurance in high-risk areasSpeed & agilityFaster research and product developmentCustomer experience & trustImmediate underwriting decisions for agents

Catalog median for time & speed deployments: −50% across 312 reported metrics. Compare benchmarks →

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Data preparation time: 80% decrease

Google Cloud Customer StoryJul 15, 2026Customer storyExplicit claimMedium evidence strength

reduced data preparation time by 80% compared with outsourcing

Normalized claim

Quote-to-buy underwriting time: 95.7% decrease

Google Cloud Customer StoryJul 15, 2026Customer storyInferred claimMedium evidence strength

Traditionally, underwriting homes can take specialty insurers anywhere from two days to two weeks; Delos reduces that time to under five minutes

Normalized claim

Quote-to-buy underwriting time: 5 minutes decrease

Google Cloud Customer StoryJul 15, 2026Customer storyExplicit claimMedium evidence strength

Delos reduces that time to under five minutes

Normalized claim

Coverage area in California: 83% increase

Google Cloud Customer StoryJul 15, 2026Customer storyExplicit claimMedium evidence strength

enables them to offer insurance to homeowners across 83% of the state

Normalized claim

Properties insured: 30,000 properties increase

Google Cloud Customer StoryJul 15, 2026Customer storyExplicit claimMedium evidence strength

Delos currently insures over 30,000 properties statewide

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
Customer
Delos Insurance Solutions
Provider
GCP
Maturity
Unknown

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 3

  • 1Risk assessment
  • 2Decision support
  • 3Workflow automation
  • Underwriting wildfire-prone homes was difficult because of rapidly changing climate and wildfire risk.
  • Traditional underwriting relied on slow, manual geospatial data preparation.
  • Many California homeowners faced high premiums or no coverage at all.
  • Used Google Earth Engine and AI-driven geospatial modeling to predict wildfire risk.
  • Built scripts in Colab notebooks and ran model training and deployment pipelines on Vertex AI.
  • Integrated Google Maps Platform and the Places API into an underwriting portal for accurate address entry and real-time quote generation.
  • Reduced data preparation time by 80% compared with outsourcing.
  • Generated online quotes in about 5 minutes instead of 2 days to 2 weeks.
  • Enabled coverage across 83% of California.
  • Delos currently insures over 30,000 properties statewide.
Architecture

Delos combines Google Earth Engine for geospatial data preprocessing and wildfire-risk modeling with Colab notebooks for scripting and Vertex AI pipelines for model training and deployment. Its underwriting portal also uses Google Maps Platform and the Places API to autocomplete addresses and generate real-time quotes without manual intervention.

Sources & evidence1
Evidence: Medium50/100Evidence strength
  • Customer explicitly identified
  • Primary source available
  • Quantified outcome available
  • Technical implementation details available
Type: Customer StoryPublished: Jul 15, 2026Publisher: Google CloudEvidence: PrimaryConfidence: High

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Was this useful?

Community

Comments

No published comments yet.