YingtongDou/CARE-GNN

Code for CIKM 2020 paper Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

48
/ 100
Emerging

This project helps fraud analysts and risk managers improve their ability to detect subtle, 'camouflaged' fraud within complex transaction networks. It takes your existing data, structured as a multi-relation graph (like connections between users, merchants, and items), along with node labels and features, and produces a more accurate fraud detection model. This tool is designed for professionals who need to identify fraudulent accounts or activities that deliberately mimic legitimate behavior.

306 stars. No commits in the last 6 months.

Use this if you need to detect sophisticated fraud where fraudsters try to blend in with normal users, making them hard to spot with traditional methods.

Not ideal if your fraud detection needs are basic, or if your data isn't structured as a multi-relation graph.

fraud-detection risk-management financial-crime network-analysis anomaly-detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

306

Forks

62

Language

Python

License

Apache-2.0

Last pushed

Oct 11, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YingtongDou/CARE-GNN"

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