M2 Fraud Detection System

A real-time fraud detection platform for financial transactions

Overview

M2 Fraud Detection is a real-time fraud detection platform for financial transactions. It integrates:

• Node.js API for transaction ingestion
• Kafka for real-time streaming
• Machine Learning (Isolation Forest) for anomaly detection
• Redis for caching and blacklisting
• Decision Engine for automatic actions (APPROVE, FLAG, BLOCK)
• React/Next.js Dashboard for live monitoring

Contact

• Author: Md Mahbubur Rahman
• GitHub: https://github.com/m-a-h-b-u-b
• Website/Portfolio: https://m-a-h-b-u-b.github.io

---

Features

• Modular Architecture Includes modules for API, dashboard, decision engine, ML service, Kafka messaging, and Redis caching.
• Real-Time Fraud Detection Processes transaction streams and applies ML models to identify suspicious activity.
• Docker & Docker-Compose Support Containerized deployment for all services ensures easy setup and scaling.
• Transaction Generator Simulate transactions for testing and ML model training.
• Scalable Messaging System Uses Kafka for real-time transaction streaming and asynchronous processing.

---

Technologies Used

• Backend: Node.js, Express.js
• Frontend: React.js / Dashboard
• Database & Cache: Redis
• Messaging: Apache Kafka
• ML Service: Python (Scikit-learn / TensorFlow / PyTorch)
• Containerization: Docker & Docker-Compose
• Other Tools: Git, ESLint, Prettier

Architecture of M2 Fraud Detection

+----------------+        +----------------+
|  Transaction   | ---->  |     API        | ----> CRUD & Stream
|   Generator    |        +----------------+
+----------------+                |
                                   v
                         +--------------------+
                         |  Decision Engine   | --> Fraud Detection Logic
                         +--------------------+
                                   |
                                   v
                         +--------------------+
                         |  ML Service        | --> Predicts Fraud Probability
                         +--------------------+
                                   |
                                   v
                          +------------------+
                          |   Kafka Broker    | --> Stream Processing
                          +------------------+
                                   |
                                   v
                         +--------------------+
                         |     Dashboard      | --> Real-time Visualization
                         +--------------------+

---

Setup & Installation

Prerequisites

• Docker & Docker-Compose installed
• Node.js & npm installed (for local development)
• Python 3.x (for ML service)
• Kafka & Redis (or via Docker containers)

Clone the Repository

git clone https://github.com/m-a-h-b-u-b/M2-Fraud-Detection.git
cd M2-Fraud-Detection

Running with Docker

docker-compose up --build

This will start all modules:

• API server
• Dashboard
• Decision engine
• ML service
• Kafka broker
• Redis server

Running Locally

1. API Service

cd api
npm install
npm start

2. Dashboard

cd dashboard
npm install
npm start

3. ML Service

cd ml-service
pip install -r requirements.txt
python ml_service.py

---

Usage

• Transaction Simulation: Use generate_transactions.js to simulate transactions:

node generate_transactions.js

• Access Dashboard: Open http://localhost:3000 in your browser to monitor transactions in real-time.

• API Endpoints: The API provides CRUD operations for transactions and fraud analysis. Example:

GET /api/transactions
POST /api/transactions
GET /api/fraud/:transactionId

---

Contributing

Contributions are welcome! Please follow these steps:

1. Fork the repository
2. Create a new branch (git checkout -b feature-name)
3. Make your changes
4. Commit your changes (git commit -m "Add feature")
5. Push to the branch (git push origin feature-name)
6. Create a Pull Request

Please ensure code follows the project’s style and ESLint rules.

---

License

This project is dual-licensed:

• Open-Source / Personal Use: Apache 2.0
• Commercial / Closed-Source Use: Proprietary license required

For commercial licensing inquiries or enterprise use, please contact: mahbub.aaman.app@gmail.com