KNODE: A Knowledge Graph Approach to Risk-Driven Compliance and UBO Discovery

Session Track: AI Engineering

Session Time: 11:30 pm - 12:00 am November 7

Session description

Compliance teams today face a flood of structured and unstructured data—from KYC onboarding files to sanction lists and transaction records. In this session, Arthur will introduce KNODE, a semantic knowledge graph built in Neo4j that combines rule-based risk scoring, UBO tracing, and jurisdictional risk profiling. By connecting real-world concepts like ownership layers, PEP classification, transaction behaviors, and legal entity forms across multiple jurisdictions, KNODE helps compliance teams make better, faster decisions. The session will include practical Cypher examples, visual walkthroughs, and integration of standards like FIBO and OWL, offering a robust blueprint for next-generation AML and compliance tooling.

Speaker

Arthur Namias de Crasto

Compliance Officer, University of Amsterdam

Arthur Namias de Crasto is an economist from the University of Amsterdam with more than 25 years of experience in various roles within the financial sector in Curaçao. He is a Neo4j Certified Developer and a returning speaker at NODES. Arthur combines deep domain expertise in compliance, risk management, and financial crime prevention with a passion for connected data. In his work, he explores how graph technology can bring clarity to complex networks—ranging from Ultimate Beneficial Ownership (UBO) structures to transaction monitoring and jurisdictional risk assessments. Arthur actively develops the KNODE compliance knowledge graph framework, integrating semantic standards (FIBO, RDF/OWL) with Neo4j’s powerful query and inference capabilities.