Use Case Intelligence RSS Search use cases Search
AWS Software / SaaS Estonia

Veriff

Fraud Detection · Security and Compliance

In today’s connected world, knowing who’s on the other side of a screen isn’t a luxury—it’s a requirement. Every online transaction, every new account sign-up, and every access request hinges on making sure that people are who they say they are.

Read the original story Explore all use cases
1 second
2 weeks
27 percent

Reported impact

Business outcome

On AWS, Veriff has achieved further enhancements in its identity verification workflows, resulting in heightened efficiency and performance. With cost-effective ML and AI services, it has saved resources that it can invest in new projects, accelerating its speed of innovation. Thanks to this evolution, users benefit from a more seamless and reliable verification process, an advantage that will continue to improve.

  • Cost Reduction
  • Productivity Improvement
  • Risk Reduction

Solution

In today’s connected world, knowing who’s on the other side of a screen isn’t a luxury—it’s a requirement. Every online transaction, every new account sign-up, and every access request hinges on making sure that people are who they say they are. One of Veriff’s most foundational ML models is responsible for detecting document specimens quickly and accurately. Before deploying this model, the process could take up to 2 weeks. Veriff reduced this time to less than a day by adopting multimodel endpoints for Amazon SageMaker, which provide a scalable and cost-effective solution for deploying large numbers of ML models. Amazon SageMaker has become a key tool for cost-effective model training, and engineers can deploy multiple ML models on AWS, facilitating rapid experimentation. Key services included Amazon SageMaker supports model training, tuning, deployment, or managed ml inference; Amazon Rekognition performs image or identity analysis inside verification workflows.

Solution architecture

2 components · 1 layer
  1. Compute
    • Amazon SageMaker Supports model training, tuning, deployment, or managed ML inference.
    • Amazon Rekognition Performs image or identity analysis inside verification workflows.

Architecture clues

  • Veriff can verify user faces within 1 second, exceeding its latency targets.
  • “Now, we’re migrating to specific tools so that we can fully take advantage of what AWS has to offer.

Evidence from the source

Before deploying this model, the process could take up to 2 weeks.
Every online transaction, every new account sign-up, and every access request hinges on making sure that people are who they say they are.
In today’s connected world, knowing who’s on the other side of a screen isn’t a luxury—it’s a requirement.
One of Veriff’s most foundational ML models is responsible for detecting document specimens quickly and accurately.
Veriff understands this importance and continually takes steps to improve its identity verification solution.
Without a high-performing identity verification solution, businesses can face revenue loss, reputational damage, and noncompliance penalties.
Transparency Evidence & methodology 85/100 reference value · 85% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value85/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth15/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    2 metrics describe measurable impact.
  • Deployment scale5/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence85%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 direct source quotes retained.
  • Date provenance8/10
    The publication date comes from publisher-controlled metadata.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. AWS

    Veriff customer story

    First-party
    https://aws.amazon.com/solutions/case-studies/veriff-case-study/
    Source type
    Vendor-published customer story
    Published
    Jan 17, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Databricks Apr 23, 2026 Elliptic Software / SaaS Global Elliptic's clients—compliance teams at crypto exchanges, banks, payment providers, and institutional custody platforms—face rising alert volumes and stringent regulation, and analysts must document each decision by… 2x faster resolution of high-risk screenings Fraud DetectionRisk Management Agent Bricks / Mosaic AI · Databricks Foundation Model APIs · Databricks Model Serving OpenAI Oct 28, 2025 Doppel Software / SaaS North America Doppel needed to detect, classify, and stop phishing, impersonation, and other social-engineering threats at internet speed, long before human analysts could keep up with the volume and variation created by generative… 3x threat handling capacity Fraud DetectionRisk Management GPT-5 · LLM-driven pipeline · o4-mini OpenAI Sep 9, 2025 SafetyKit Software / SaaS North America SafetyKit needed to review huge volumes of risky multimodal content for fraud, prohibited activity, and compliance violations with higher nuance and lower cost than legacy moderation systems or manual review could… 10+ point performance gains on hardest vision tasks with GPT-5 Fraud DetectionRisk Management Computer Using Agent · GPT-4.1 · GPT-5