Paper: arXiv 2304.00323
Authors: Yanci Zhang, Yutong Lu, Haitao Mao, Jiawei Huang, Cien Zhang, Xinyi Li, Rui Dai
Abstract
Financial market participants frequently rely on numerous business relationships to make investment decisions. Investors can learn about potential risks and opportunities associated with other connected entities through these corporate connections. Nonetheless, human annotation of a large corpus to extract such relationships is highly time-consuming, not to mention that it requires a considerable amount of industry expertise and professional training. Meanwhile, we have yet to observe means to generate reliable knowledge graphs of corporate relationships due to the lack of impartial and granular data sources. This study proposes a system to process financial reports and construct the public competitor graph to fill the void. Our method can retrieve more than 83% competition relationship of the S&P 500 index companies. Based on the output from our system, we construct a knowledge graph with more than 700 nodes and 1200 edges. A demo interactive graph interface is available.
Complexity vs Empirical Score
- Math Complexity: 2.0/10
- Empirical Rigor: 5.5/10
- Quadrant: Street Traders — practical and empirical, lighter on theory
Why this score: The paper introduces a practical NLP/information extraction framework for building corporate competition knowledge graphs from 10-K filings. While it lacks mathematical depth and rigorous quantitative backtesting for trading signals, it provides a solid empirical demonstration by constructing a large-scale graph for S&P 500 companies with high recall.
Research Flowchart
flowchart TD
A[Goal: Automate Corporate Competitor Knowledge Graph Construction] --> B[Data Input: S&P 500 Financial Reports]
B --> C[NLP Mining & Information Extraction Pipeline]
C --> D[Extract Business & Competitor Relationships]
D --> E[Outcome: Interactive Knowledge Graph<br/>700+ Nodes, 1200+ Edges]
D --> F[Outcome: High Extraction Recall<br/>>83% S&P 500 Competitors Retrieved]