The Missing Puzzle Piece in Agentic Financial Analysis: Self-Learning Knowledge Graphs
summary
Claims a working AI financial analyst built on self-learning knowledge graphs that encode individual investment philosophies and learns from user interactions until it mirrors a six-month-trained analyst. Uses LLMs for entity/relation extraction, then a four-step process: SME review, backtests on news flow, iterative editing; targets scaling to roughly 20,000 equities with regeneration every 15–30 days. Product-level work includes an MVP integrating Neo4j tooling and practical graph RAG cost optimization to make continuous updates feasible.
AI-written summary · about
chapters (6)
- 0:00Introduction and background
- 3:18Why knowledge graphs matter
- 7:57Building practical knowledge graphs
- 10:47Scaling self-learning graphs
- 12:36Real-world use case example
- 16:15Q&A and closing
related talks
01h 26mThinking in Graphs: The Cognitive Foundations of Agentic AI
30mAgentic AI for Enterprise Knowledge Graph Management
21mAgentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval
19mWisdom-Driven Knowledge Augmented Generation at Scale
42mMaking OSS AI Real with Knowledge Graphs
12mAgentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval
20mBeyond RAG: Building the AI Corporate Brain with Knowledge Graphs and Virtue Ethics
36mAgentic GraphRAG: AI’s Logical Edge