Combining Third-Party Data, Entity Resolution, and Graph Analytics for ESG Risk Mgmt
summary
Demo builds a working pipeline that combines Dun & Bradstreet climate data, entity resolution via Sensing, Databricks preprocessing and the DataX connector to Neo4j, then runs Graph Data Science and Linkurious alerts. It scores and writes aggregated supply‑chain climate risk (example: Scotmid scores 21), identifies 68 suppliers with 13 flagged as risky and flags supply‑chain components over a 10% risky threshold, and generates investigator cases automatically — the end‑to‑end flow runs and surfaces actionable hits.
AI-written summary · about
chapters (7)
- 0:00Introduction to ESG risks
- 6:42Demo overview and data integration
- 11:16Building the knowledge graph process
- 16:32Graph analytics and risk scoring
- 20:48Automated risk alerts with Linkurious
- 24:40Data processing in Databricks
- 27:35Q&A and closing remarks
related talks
26mDisrupting Supply Chain with Data Science
58mPanel: Data & AI-Driven ESG Reporting
05mWhat's Driving the Shift Towards ESG Investing?
27mConnecting the Dots: Graph Analytics for Economic Sustainability
13mConnecting data sources with AI
23mHybrid RAG–LLM Framework for Supplier Risk Intelligence
23mDemand Sensing Decision Support System
14mSupply Chain Risk Predictions with Neo4j Graph Data Technology