AmirhosseinHonardoust/Fraud-Detection-SQL-Unsupervised

Detect suspicious financial transactions using SQL and Python. Build user-level behavioral features in SQLite, apply Isolation Forest for anomaly detection, and visualize high-risk patterns. Demonstrates unsupervised fraud analytics and SQL-driven data science workflow.

32
/ 100
Emerging

This project helps financial analysts and risk managers identify unusual bank transactions that could be fraudulent, even without prior examples of fraud. It takes raw transaction data as input and produces a ranked list of suspicious transactions, user-level fraud summaries, and a visualization of anomaly scores as output. This helps financial professionals quickly spot and investigate high-risk activities.

Use this if you need to detect potential fraud or unusual activity in financial transactions and lack labeled examples of past fraud.

Not ideal if you already have a large dataset of known fraudulent and legitimate transactions, as supervised methods might be more suitable.

financial-fraud-detection banking-analytics risk-management transaction-monitoring anomaly-detection
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 13 / 25
Community 6 / 25

How are scores calculated?

Stars

30

Forks

2

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-Unsupervised"

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