Case studies & builds

Projects

RAG systems, applied ML tools and product engineering work. Each one names the constraint it was built against.

Tech: Apache Kafka

1 of 18

FraudStream: Score a transaction for fraud in milliseconds, not hours

FraudStream· Data Science· Archived

A production-grade streaming pipeline that scores financial transactions for fraud in milliseconds rather than hours, built on Kafka, Spark Structured Streaming, and a Snowflake medallion warehouse.

ArchivedAug 2025

Score a transaction for fraud in milliseconds, not hours

FraudStream

A production-grade streaming pipeline that scores financial transactions for fraud in milliseconds rather than hours, built on Kafka, Spark Structured Streaming, and a Snowflake medallion warehouse.

Data Science · Open Source

Highlights

Eight distinct fraud patterns detected, including card testing, geographic impossibility, merchant collusion, and bust-out fraud
Sub-second latency from transaction to alert
Schema validation via Avro and a Schema Registry, with quality scoring and trend monitoring

View case study