Real-Time Fraud Detection
End-to-end real-time fraud detection pipeline: Flask UI → RabbitMQ → Kafka → Flink → ClickHouse → Grafana.
Architecture
Real-time fraud detection: transactions flow from a UI through a streaming fraud engine into an analytics store and live dashboard.
Integration
Infrastructure
Overview
A real-time fraud detection pipeline that scores transactions as they happen and surfaces results on a live dashboard.
Transactions enter through a Flask UI, are queued via RabbitMQ, streamed through Kafka, processed and scored in Apache Flink, then stored in ClickHouse and visualized in Grafana — a complete streaming architecture from ingestion to insight.
Highlights
- Full streaming path: Flask → RabbitMQ → Kafka → Flink → ClickHouse → Grafana
- Real-time transaction scoring with low-latency processing in Flink
- Live monitoring dashboards in Grafana
Tech stack
More projects
View all →SMILE Platform (UNDP for Kemenkes)
National immunization logistics system in production across all of Indonesia — streaming CDC + batch analytics platform.
LidValid — Unified Data Validation Platform
Full-stack data validation platform with Tiered Validation — cheap aggregate checks across every table, then precise row-level checks only where they fail.
Dataklin — AI-Powered Data Quality & Entity Resolution
Data quality and entity-resolution platform that profiles, validates, deduplicates, and standardizes datasets before handoff — with LLM-generated rules.