jivajbrar.com

Overview

FraudSense is a containerized, real-time fraud detection system that scores transactions through a production-style API, enriches them with behavioral features, and returns actionable decisions (approve / review / decline).

The system combines online feature aggregation, rule-based decisioning, and a trained ML model to simulate a modern fraud scoring architecture.

FraudSense processes each transaction through the following pipeline:

1. Incoming transaction hits FastAPI endpoint

2. Behavioral features computed in real time using Redis

3. Feature vector scored by trained fraud classifier

4. Rule-based policy applied to determine final decision

5. Transaction, prediction, and decision persisted in PostgreSQL

The system is fully containerized using Docker.

Architecture

Backend: FastAPI

Data Store: PostgreSQL

Online Feature Store: Redis

Model Layer: Scikit-learn classifier

Containerization: Docker

Key system components:

REST API for transaction scoring

Redis-based rolling window velocity features

Device and merchant behavioral aggregation

Threshold-calibrated ML scoring

Rule-based override logic

Persisted audit logging for retraining

Model Training

The fraud classifier was trained on Kaggle's 250K-row credit card fraud dataset.

Key metrics:

ROC-AUC: 0.941

Calibrated threshold tuning under severe class imbalance

Imbalance awareness was critical due to the ~0.17% fraud rate in the dataset.

Thresholds were tuned to balance precision and recall appropriately for fraud detection environments.

Benchmarks

The live API was load-tested using a transaction replay pipeline.

Results:

10,000 simulated transactions processed

Sustained throughput: 233 requests per second

Median latency (p50): 3.73 ms

95th percentile latency (p95): 6.33 ms

This validated system stability and low-latency scoring under high-volume conditions.