DerwenAI/kleptosyn

Synthetic data generation for investigative graphs based on patterns of bad-actor tradecraft.

30
/ 100
Emerging

This project helps financial crime analysts and investigators generate realistic synthetic data to practice identifying complex fraud networks. It takes real-world data about entities and their relationships (like company ownership) and information from known financial crime cases. It then generates new, large datasets of transactions and entities, including both legitimate activity and patterns of bad-actor tradecraft, which can be used to test detection systems or train new analysts.

Use this if you need to create diverse, synthetic datasets that mimic real-world financial fraud scenarios for training, testing, or research without using sensitive actual data.

Not ideal if you are looking for a tool to directly analyze live financial transactions or identify fraud in real-time production systems.

financial-crime-investigation anti-money-laundering fraud-detection risk-management financial-compliance
No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DerwenAI/kleptosyn"

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