Financial services · Databricks
AME Digital: Combatting the impact of financial fraud
Public case study · not a Metric Oak engagement
- Accuracy in fraud prevention models
- 90%
- More speed while running the model pipeline (vs. on-premises)
- 3.2x
- Reduction in data management costs
- 38%
What happened
The story in brief
A Brazilian digital wallet with tens of millions of customers operates in one of the world's largest fraud markets. It moved its anti-fraud data and model pipelines from on-premises systems to Databricks, improving model accuracy and running the pipeline several times faster at lower data-management cost.
How it compares
- 3.2x more speed while running the model pipeline (vs. on-premises), against a median speed-up of 5x across 8 financial services results.
- 38% reduction in data management costs, against a median reported cost reduction of 60% across 19 financial services results.
Planning something similar?
Cloud data migration
Legacy warehouse to lakehouse, with parallel-run validation. Senior engineers, fixed scope, measured results.
Related case studies
Financial services · Databricks
ABN AMRO10x
Faster time to market: use cases deployed in 2 months
Financial services · Databricks
Addepar5x
Faster pipeline development, accelerating client onboarding
Financial services · Databricks
AXA Japan60%
Reduction in warehouse costs for certain phases of the migration
Related insights
Frequently asked questions
What results did AME Digital report?
AME Digital reported 90% accuracy in fraud prevention models; 3.2x more speed while running the model pipeline (vs. on-premises); 38% reduction in data management costs, according to its customer story published by Databricks.
Which platform and technologies did AME Digital use?
AME Digital used Databricks, including Unity Catalog, Delta Lake, MLflow, Power BI.
How do these results compare with other financial services programs?
3.2x more speed while running the model pipeline (vs. on-premises), against a median speed-up of 5x across 8 financial services results. 38% reduction in data management costs, against a median reported cost reduction of 60% across 19 financial services results.
Source
Customer story published by Databricks: Combatting the impact of financial fraud (opens databricks.com in a new tab) on databricks.com. Figures as published, retrieved 27 October 2026. The summary above is Metric Oak's own. This is not a Metric Oak engagement.
Have 30 minutes? Get a senior architect’s view of your data platform.
No sales deck. You talk to the engineer who would lead the work.
Book an architecture review