AmirhosseinHonardoust/Fraud-Detection-SQL-Supervised

Detect and classify fraudulent transactions using SQL and Python. Generate behavioral features with SQLite, train a Logistic Regression model, and evaluate performance with AUC, precision, recall, and ROC analysis. A complete supervised fraud detection workflow.

29
/ 100
Experimental

This project helps financial analysts and fraud prevention teams automatically identify suspicious transactions. It takes your historical transaction data, including which transactions were confirmed fraud, and generates new insights by calculating user spending patterns. The output is a list of transactions ranked by their probability of being fraudulent, along with performance metrics and visualizations to show how well the system works.

Use this if you have past transaction data with known fraud cases and need to build a system to predict future fraudulent activity.

Not ideal if you don't have labeled data indicating which past transactions were fraudulent, as this system requires that information to learn.

fraud-prevention transaction-monitoring risk-management financial-crime
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 13 / 25
Community 3 / 25

How are scores calculated?

Stars

34

Forks

1

Language

Python

License

MIT

Last pushed

Oct 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AmirhosseinHonardoust/Fraud-Detection-SQL-Supervised"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.