Capital Project Risk Management With Neo4j
summary
Neo4j consolidates siloed risk and P6 schedule data into a graph that links risks, causes, activities and projects for a large public-sector portfolio worth billions, updating risk exposure dates by syncing activity start/finish with risk windows via Cypher scripts, loading transformed rows with Python and Power Query. Visuals size and color nodes by EMV to spotlight escalating risks; queries surface thousands of cascading dependencies and overburdened owners. A Graph RAG agent translates plain language to Cypher, retrieves docs from a vector DB and suggests mitigations sourced from online and internal lessons learned.
AI-written summary · about
chapters (9)
- 0:00Introduction and overview
- 3:00Challenges in project risk management
- 6:36Demonstrating Neo4j with risk data
- 12:48Data transformation and validation
- 16:01Building the risk graph model
- 19:40Visualizing risk insights
- 21:03Future expansion of the graph
- 22:04Graph RAG for risk analysis
- 27:44Closing and next steps
related talks
14mSupply Chain Risk Predictions with Neo4j Graph Data Technology
31mSix Degrees of Infiltration
30mContext Engineering: Connecting the Dots with Graphs
30mInterconnected Capital: Visualizing WAM, PE, RE, and HF Data with Neo4j
24mOur daily graphs written in Ruby and Neo4j
49mWarming up to Graphs
28mInterview with
30mPerformant GraphRAG Improving Neo4j to Drive Autonomous AI ...