Normalized claim
Cost: 27% decrease
ML training costs were reduced by 27%.
Veriff Makes Identity Verification Simple Using Amazon SageMaker and Amazon Rekognition
Use case typeDocument automationUpdated Jun 13, 2026
Veriff is an identity verification provider headquartered in Tallinn, Estonia that uses AWS AI services to optimize verification workflows. The company uses Amazon SageMaker to build, train, and deploy machine learning models for document identity verification and authentication. It uses Amazon Rekognition to compare identity document photos with user selfies to confirm identity.
Reported outcomes
−27%
costCost savings
1 secondsquantified impact
Strategic outcomes
Speed & agilityAccelerated model deploymentCost efficiencyReduced ML training costsNew product / capabilityEnabled fast face verificationScale & capacityImproved global verification scalability
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Quantified impact: 1 seconds decrease
User face verification latency was reduced to about 1 second.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Veriff
- Provider
- AWS
- Maturity
- Unknown
- Linked source
- AWS Customer Story
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 3 of 4
- 1Identity verification
- 2Fraud detection
- 3Document processing
- Veriff needed to improve the cost and performance of its identity verification platform as it scaled.
- The company had to reduce ML deployment time and support subsecond latency for user face verification.
- It also needed to help customers meet fraud prevention, KYC, age verification, and compliance requirements.
- Veriff migrated from a more internally managed approach to fully managed AWS AI services.
- Amazon SageMaker is used to train and deploy many ML models for document verification workflows.
- Amazon Rekognition is used to compare faces from identity documents with selfies, supported by AWS Face APIs.
- The AWS-based approach improved scalability and supported global verification operations.
Technologies
- Model deployment time dropped from up to two weeks to less than a day.
- ML training costs were reduced by 27%.
- User face verification latency was reduced to about 1 second.
- The company improved efficiency and scalability for its global identity verification service.
Architecture
Veriff uses Amazon SageMaker for training and deploying machine learning models used in document identity verification, and Amazon Rekognition for facial comparison between identity documents and user selfies. The article also references AWS Face APIs as part of the verification workflow.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: Apr 29, 2026Publisher: AWS Customer StoryEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
AI patterns
Browse the catalog
Was this useful?
Community
Comments
Loading comments...