FIRME improves linking investor knowledge across different sources and times
FIRME: Registry-Anchored Memory Graphs for Evolving, Heterogeneous Investor Knowledge
Artificial IntelligenceComputation and Language
Summary
Financial AI systems that track investor information often struggle to keep track of who or what is being talked about when data uses different names or descriptions. The authors describe FIRME, a system that merges various pieces of investor data into consistent, linked records while keeping track of where and when the data came from. This helps create a clearer picture by connecting conversations and financial signals without losing track of their source. Tests show FIRME matches information more accurately and maintains better evidence chains than previous methods.
What this means in practice
- •For financial technology teams: Create investor knowledge bases that accurately link diverse financial data streams over time, improving analysis quality.
- •For enterprise data engineers: Maintain consistent entity identities in evolving heterogeneous datasets with traceable data origins for complex decision workflows.
- •For business intelligence developers: Build systems that connect spoken investment discussions to portfolio performance data automatically, increasing insight extraction.$Commercial implications: Enables sale of advanced analytics platforms that integrate multiple investor data types with higher accuracy and provenance tracking.
Authors
Yunbai Zhang, Yunyi Gao, Han-Tai Shiao
Abstract
Financial AI workflows that reuse investor knowledge need persistent memory that integrates observations across sources and periods without losing identity or provenance. In a knowledge graph, recurring observations may use different surface forms, fragmenting relationship histories and preventing evidence from accumulating. We introduce Fusion and Identity Registry for Memory Evolution (FIRME), a registry-anchored memory graph that reconciles incoming observations to persistent canonical relationships and retains their source, time, and context. Within periods, rule-based fusion links investor-call discussions to portfolio cash-flow signals, directly or through a fixed product-topic ontology. Across periods, canonical identities and persistent aliases direct recurring observations to the same relationship history; deterministic updates summarize reinforcement, inactivity, and reactivation. We evaluate FIRME on proprietary investor-call and cash-flow records and on S&P 500 earnings-call transcripts. Compared with a historical registry that retains canonical identities and semantic fallback but omits alias memory, FIRME increases final-period Correct Match Rate by 7.8-12.1 percentage points across four dataset-backend settings under a fixed-judge and fallback-review protocol. A blinded human audit of 200 incoming observations per setting finds Correct Match Rate gains of 9.0-16.5 points and reattachment-recall gains of 22.5-29.0 points, with higher observed merge precision in all four samples. A separate audit finds valid evidence paths for 293 of 300 outputs from full within-period fusion in the investor-call setting. Extraction-faithfulness and round-trip diagnostics assess source grounding and preservation of extractor-derived graph content.