Use Case Intelligence RSS Search use cases Search
Microsoft Financial Services Belgium

Belfius

Fraud Detection · Risk Management

Managed feature store increases agility in building models because users can discover and reuse features instead of starting every time from scratch. It encourages faster experimentation with the ability to do local development and testing of new features. Consistent feature definition across the organization increases the reliability of ML models and supports versioning, just as Belfius had imagined.

Read the original story Explore all use cases
Every year Belfius bank processes hundreds of millions of transactions, checking each one for potential money laundering activities.

Reported impact

Business outcome

Managed feature store increases agility in building models because users can discover and reuse features instead of starting every time from scratch. It encourages faster experimentation with the ability to do local development and testing of new features. Consistent feature definition across the organization increases the reliability of ML models and supports versioning, just as Belfius had imagined.

  • Cost Reduction
  • Customer Experience
  • Productivity Improvement
  • Risk Reduction

Solution

Belfius built this solution on Azure Machine Learning, Azure Databricks, Azure Synapse Analytics. Managed feature store increases agility in building models because users can discover and reuse features instead of starting every time from scratch. It encourages faster experimentation with the ability to do local development and testing of new features. Azure Machine Learning supports model training, evaluation, and deployment for machine learning workloads. Azure Databricks processes, transforms, and engineers large data sets for analytics and machine learning. Azure Synapse Analytics models and analyzes enterprise data for reporting, AI, and decision support. Belfius recognized the opportunity of its cloud transformation to further scale up technologies such as artificial intelligence (AI) and machine learning (ML). Lacking an overview of all features, Belfius data scientists were rewriting the same code repeatedly for different data models.

Data flow

Operational data is collected from line-of-business systems, engineered and transformed in Azure Databricks so business teams can act on a shared set of insights.

Solution architecture

3 components · 1 layer
  1. Compute
    • Azure Machine Learning Supports model training, evaluation, and deployment for machine learning workloads.
    • Azure Databricks Processes, transforms, and engineers large data sets for analytics and machine learning.
    • Azure Synapse Analytics Models and analyzes enterprise data for reporting, AI, and decision support.

Architecture clues

  • The solution is built around a governed cloud data foundation for shared analytics.

Evidence from the source

Belfius recognized the opportunity of its cloud transformation to further scale up technologies such as artificial intelligence (AI) and machine learning (ML).
Every year Belfius bank processes hundreds of millions of transactions, checking each one for potential money laundering activities.
Managed feature store increases agility in building models because users can discover and reuse features instead of starting every time from scratch.
Transparency Evidence & methodology 70/100 reference value · 82% 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 value70/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth20/25
    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 impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence82%
  • 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 evidence15/20
    3 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • 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. Microsoft

    Belfius customer story

    First-party
    https://www.microsoft.com/en/customers/story/1702060165230346513-belfius-azure-machine-learning-belgium
    Source type
    Vendor-published customer story
    Published
    Nov 13, 2023
    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

  • Published on source page Nov 13, 2023 · Microsoft · First-party
    Open date source
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
Microsoft May 23, 2023 Swift Financial Services Global Swift needed to improve fraud and anomaly detection for global financial transactions without copying or moving sensitive member data out of secure locations. Over 11,500 financial institutions worldwide Fraud DetectionRisk Management Azure Machine Learning · Azure confidential computing · Microsoft Purview In-house Sep 24, 2026 Mastercard Financial Services global Fraudsters are using AI to find vulnerabilities, adapt tactics, and scale attacks across more payment channels, while traditional transaction-by-transaction controls struggle to catch coordinated fraud and authorized… Last year, scam losses globally were estimated at $442 billion Fraud DetectionRisk Management NVIDIA Jun 2, 2026 Revolut Financial Services Global Revolut needed to replace siloed fraud, credit, marketing, and recommendation models that depended on months of feature engineering with a single behavioral foundation model that could learn from raw financial event… 16.1% improvement in credit risk prediction performance from NVIDIA Llama-Nemotron-Embed-1B-v2 Fraud DetectionMarketing Personalization NVIDIA H100 GPUs · NVIDIA Llama-Nemotron-Embed-1B-v2 · Nebius AI Cloud