Case Study Deskcasestudydesk.com
Financial ServicesSourced

Case Study: Neo Financial cuts fraud-stack infrastructure cost 80% with a Materialize online feature store

Neo Financial Case StudySourced & dated by Case Study Desk
Key facts · TL;DR
Company
Neo Financial
Industry
Financial Services
Challenge
High-maintenance fraud feature stack with sub-second latency needs
Headline result
A real-time online feature store on Materialize replaces a high-maintenance fraud stack

Key results

80%
Lower infrastructure spend
Fraud feature stack
<1s
P99 feature lookup latency
Point-of-sale approvals
20x+
Faster feature delivery
Hours instead of days

The challenge

Neo Financial needed a real-time feature store that could serve fraud-detection features with sub-1-second latency while limiting operational complexity and cost. Its prior approaches, including DIY MongoDB, ClickHouse, Flink, and warehouse-only setups, required heavy engineering maintenance.

The solution

Neo built an online feature store on Materialize, streaming MongoDB data and defining aggregates in SQL. Incrementally maintained views serve fresh features, and new features ship through SQL and dbt workflows.

Our fraud losses have substantially decreased, and the infrastructure spend for this system has gone down by about 80 percent.

BR
Brandon Rochon
Head of Data, Neo Financial

The results, in context

Neo reported infrastructure spend for the system down about 80%, sub-1-second P99 feature latency for point-of-sale approvals, and more than 20x faster feature delivery (hours instead of days).

Products used

Materialize Materialize