Catching Bad Guys using open data and open models for graphs
summary
Claims that GraphRAG can be made accountable by unbundling graph construction and using open models and open data to produce explainable investigative graphs for AML UBO and RMF. Uses KùzuDB and LanceDB plus SpaCy pipelines Liner OpenNRE and entity resolution tooling with PEXTRank and PSL. Cites 177,000 transactions, ~$3B and ~250 open sanctions sources, ~80 languages as concrete signals. Provides a Docker playground and Jupyter notebooks and a PPP loan fraud Las Vegas demo that run end to end.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:53Financial crime graphs
- 6:52Crime investigation model
- 10:50Graph RAG in regulation
- 13:45Entity resolution challenges
- 17:13Constructing graphs from imperfect data
- 19:42Unstructured data linking
- 23:58Open tools and tutorials
- 26:48Community resources
- 27:32Q&A
related talks
35mGraphRag in Action: Revolutionizing Fraud Detection Techniques
25mComposable RAG Pipelines With OPEA Highlighting GraphRAG
42mMaking OSS AI Real with Knowledge Graphs
26mPractical GraphRAG Making LLMs smarter with Knowledge Graphs
24mEmpowering Lifelong Learning: Transforming Data into Insights With GraphRAG
36mGraphRAG Explained 🔥 Building Smarter LLMs
36mGraphRAG for Law: Building Legal Reasoning Agents
53mPractical GraphRAG - Making LLMs smarter with Knowledge Graphs