FastAPI: Build a Banking API that has AI/ML Fraud Detection

FastAPI: Build a Banking API that has AI/ML Fraud Detection.
Published 5/2025
Duration: 9h 28m | .MP4 1280×720, 30 fps(r) | AAC, 44100 Hz, 2ch | 6.66 GB

Learn FastAPI, MLFlow, AI/ML, Docker, Celery etc, to build a banking API with transaction fraud protection
What you’ll learn
– You will learn how to integrate Docker with Celery, Redis,RabbitMQ, FlowermMLFlow and FastAPI
– You will learn how to use scikit learn,numpy and pandas for machine learning, to create a transaction analysis and Fraud detection system
– You will learn how to use mlflow to create machine learning training pipelines and lifecycle management
– You will learn how to use Reverse Proxies and load balancing with TRAEFIK
– You will learn how manage multiple Docker containers with Portainer in development and in Production
– You will learn how to use Loguru for comprehensive Logging
– You will learn how to use Redis,RabbitMQ and celery for background machine learning task processing.

Requirements
– This course is NOT for absolute beginners.
– This course is targeted at Python Developers with at least 1 year of web development experience or more
– You should be familiar with the basic concepts surrounding shell scripts, Docker, and FastAPI.
– You should be familiar with concepts surrounding asynchronous python.

Description
Welcome to this comprehensive course on building a banking API with FastAPI with an AI-powered/machine learning transaction analysis and fraud detection system. This course goes beyond basic API development to show you how to architect a complete banking system that’s production-ready, secure, and scalable.
What Makes This Course Unique:

Learn to build a real-world banking system with FastAPI and SQLModel

Implement AI/ML-powered fraud detection using MLflow and scikit-learn

Master containerization with Docker

Master reverse proxying and load balancing with Traefik

Handle high-volume transactions with Celery, Redis, and RabbitMQ
Secure your API with industry-standard authentication practices

You’ll Learn How To:

✓ Design a robust banking API architecture with domain-driven design principles✓ Implement secure user authentication with JWT, OTP verification, and rate limiting✓ Create transaction processing with currency conversions and fraud detection✓ Build a machine learning pipeline for real-time transaction risk analysis✓ Deploy with Docker Compose and manage traffic with Traefik✓ Scale your application using asynchronous Celery workers✓ Monitor your system with comprehensive logging using Loguru✓ Train, evaluate, and deploy ML models with MLflow✓ Work with PostgreSQL using SQLModel and Alembic for migrations
Key Features in This Project:

Core Banking Functionality: Account creation, transfers, deposits, withdrawals, statements

Virtual Card Management: Card creation, activation, blocking, and top-ups

User Management: Profiles, Next of Kin information, KYC implementation

AI/ML-Powered Fraud Detection: ML-based transaction analysis and fraud detection
Background Processing: Email notifications, PDF generation, and ML training

Advanced Deployment: Container orchestration, reverse proxying, and high availability

ML Ops: Model training, evaluation, deployment, and monitoring

This course is perfect For:

• Backend developers with at least 1 year of experience, looking to build secure fintech solutions.• Tech leads planning to architect fintech solutions.

By the end of this course, you’ll have built a production-ready banking system with AI capabilities that you can showcase in your portfolio or implement in real-world projects.

Technologies You’ll Master:

FastAPI & SQLModel: For building high-performance, type-safe APIs

Docker & Traefik: For containerization and intelligent request routing

Celery & RabbitMQ: For distributed task processing

PostgreSQL & Alembic: For robust data storage and schema migrations

Scikit-learn:For machine learning.

MLflow:For managing the machine learning lifecycle

Pydantic V2:For data validation and settings management

JWT & OTP: For secure authentication flows

Cloudinary: For handling image uploads

Rate Limiting: For API protection against abuse

No more basic tutorials – let’s build something real!

Who this course is for:
– Python Developers,curious about building a Fintech API’s
– Intermediate Python Developers with at least 1 year of experience, more is better
– Intermediate Python Develpers curious about machine learning applications in real world projects.
More Info

Please check out others courses in your favourite language and bookmark them
– – – –