Machine Learning End-to-End: Credit Card Fraud Detection
Build a real fraud model in Python: EDA, feature engineering, training, tuning & your own FastAPI inference API.
About This Course
Build one complete machine learning project in Python: a credit card fraud detector, from raw data to your own prediction API.
It is written as plain Python scripts, not notebooks, organized the way real projects are. Every model is judged in dollars saved for the bank, not only by accuracy.
What You'll Learn
Technologies You'll Master
Course Resources
Every course comes with companion resources. Follow along step-by-step.
What's Inside
9 sections, and every section adds one piece to the same fraud detection project.
Introduction
What you build, the fraud problem in dollars, and the machine learning workflow the project follows.
Python Environment Setup
Install Miniconda, create the course environment and install the packages.
Synthetic Dataset Generation
Generate 10,000 card transactions with realistic fraud patterns (about 3% fraud).
Model Training and Evaluation
Build the training script step by step (v1 to v7): split, scikit-learn Pipeline, metrics, Net Benefit and saving the model.
Model Serving with an Inference API
Build a FastAPI inference API with input validation, a health check and a web page.
Exploratory Data Analysis
Find the fraud patterns with plots, plus two auto-EDA tools.
Feature Engineering
Create amount_ratio, analyze it and retrain the model.
Hyperparameter Tuning
RandomizedSearchCV, GridSearchCV over class_weight, a YAML handoff and the production model.
Model Serving with the Tuned Inference API
Serve the tuned model and compare it with the baseline on the same input.
One Project, Built the Way Real Projects Are
You do not jump between toy examples. You build one fraud detection project from the first line of data to a running API, and you measure every change in dollars.
Data
Generate 10,000 card transactions and explore the fraud patterns.
Train
Build a scikit-learn Pipeline step by step, from v1 to v7.
Improve
New features and tuning, each one judged by the money it saves.
Serve
Your own FastAPI inference API with a web page.
Every tool is explained the first time we use it, so Python basics are enough to start.
Good to know: the data is synthetic (we generate it ourselves, so every pattern is clear and safe to share), and the API runs on your own machine. Containers and cloud deployment are not part of this course.
Who Is This Course For?
Requirements
What You Need
- Python basics: functions, lists, dictionaries and simple classes (new to Python? take our Python for Absolute Beginners course first)
- A Mac, Windows or Linux computer that can run Miniconda and VS Code
- An internet connection to install the packages
No Prior Experience Needed
- No machine learning experience. Everything is explained as we go
- No cloud account and no paid tools
Your Instructor
Kalyan Reddy Daida
DevOps & Cloud Architect | AWS, Azure & Google Cloud
Architect with 15+ years of experience in cloud infrastructure. Every StackSimplify course focuses on real-world, hands-on implementation with step-by-step instructions and companion GitHub repos. Not just theory, but production-ready skills.
Ready to Build Your First Real ML Project?
Go from raw data to your own fraud detection API, one working script at a time.
30-Day Money-Back Guarantee • Full Lifetime Access • Certificate of Completion
Get DevOps & Cloud insights in your inbox
Weekly DevOps & Cloud insights from a 383K+ Udemy instructor