Using Financial Knowledge Graphs for Supply Chains, Events, and Factors
Summary
This research overview explains how knowledge graphs represent entities and their relationships, then outlines a construction process: gather data, preprocess it, identify entities and links, reconcile information from different sources, form relationship triples, and store them in a graph or relational database. Text sources may require natural language processing. The article discusses using these networks to map companies to products and supply chains, ownership links, and investment themes.
For investment research, it proposes tracing how company events may affect connected firms, such as earnings warnings propagating through receivables relationships with weaker or delayed effects. It also suggests graph-derived factors based on counterparties, upstream and downstream fundamentals, network importance, and centrality. For industry analysis, graph structure can guide variable selection, dimensionality reduction, and the addition of industry views to quantitative models. These are conceptual applications and examples; the document provides no measured strategy returns or empirical validation of the proposed factors or event effects.
Key ideas
- A financial knowledge graph links entities such as companies, products, suppliers, and shareholders through explicit relationships.
- Graph construction involves sourcing and cleaning data, extracting entities and links, reconciling sources, and storing relationship triples.
- Supply-chain and ownership networks can help map company positions and trace possible event spillovers.
- Network properties and connected firms’ fundamentals can be used to create candidate investment factors.
- The overview describes applications but presents no empirical performance results.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.