Lessons Learned from Building a Real-World Knowledge Graph
summary
Built a temporal knowledge graph for commercial real estate to recover true property ownership and contact info, using public tax, transaction and permit feeds plus corporate registries, NLP address parsing and name typing, and an iterative graph cleaning loop. Production graph runs in BigQuery and Spark with Spark GraphFrames, about 1.5 billion edges and hundreds of millions of nodes, uses a waterfall of half a dozen motifs to resolve owners, and validates by focused sampling on asset types and portfolios.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 1:21Overview
- 3:45Real Estate Data
- 6:23Business Use Case 1
- 11:52Finding the Data
- 14:20Graph Construction
- 17:13Data Extraction
- 19:27Building the Graph
- 26:27Measuring Success
related talks
30mHow Graph Data Science Can Turbocharge Your Knowledge Graph
27mAdaptive Knowledge Graphs for Dynamic RAG Systems
24mEmpowering Lifelong Learning: Transforming Data into Insights With GraphRAG
40mKnowledge graphs --enter- the Hype Cycle
38mKnowledge Graphs : Adding a New Dimension to Vector Search and Generative AI
22mThe Nexus of Innovation: How Knowledge Graphs Fuel AI Scientific Breakthroughs
28mRole of Knowledge Graphs in Mental Health Diagnosis and Cure
26mGraph Databases will change your (freakin') life