Skip to content
SwankyForge
SwankyForge
All cases

Reference designFraud Detection Pipeline + Monitoring· 5 months

Analysts spent their day on false alarms. The review queue is now a third of the size.

False positive rate · before

4.1%

Static rules at target recall

False positive rate · after

1.6%

Cost-calibrated model, same recall

The problem

A fixed set of rules caught the fraud it already knew about and nothing else. Analysts waded through false alarms all day while genuinely new attack patterns went unnoticed for weeks at a time.

What was built

We built real-time scoring that weighs the actual cost of each kind of mistake, added monitoring that raises a flag when behaviour shifts, and rolled it out gradually alongside the existing rules rather than replacing them overnight.

What changed

Catching the same amount of fraud, false alarms fell from 4.1% to 1.6% — cutting the review queue by nearly two thirds. New patterns now surface within days, and every declined transaction comes with a reason attached.

The system behind itFraud detection with machine learning€7k–€42k · Scoped on discoveryTechnical write-upFraud Detection Pipeline + Monitoring

Tell us about the task.

The first call is free. If this system is not the right answer for your numbers, we say so.

All solutions