CompanyKG: A Large-Scale Heterogeneous Graph for Company Similarity Quantification

• Published in: IEEE transactions on big data 2024-05, p.1-12
• Main Authors: Cao, Lele, von Ehrenheim, Vilhelm, Granroth-Wilding, Mark, Stahl, Richard Anselmo, McCornack, Andrew, Catovic, Armin, Rocha, Dhiana Deva Cavacanti
• Format: Article
• Language: English
• Subjects: Benchmark testing; Companies; company similarity quantification; competitor retrieval; graph dataset; graph neural network; heterogeneous graph; Industries; Investment; Knowledge graph; Knowledge graphs; private equity; similarity prediction; similarity ranking; Soft sensors; Task analysis
• ISSN: 2332-7790; 2332-7790; 2372-2096
• DOI: 10.1109/TBDATA.2024.3407573

In the investment industry, it is often essential to carry out fine-grained company similarity quantification for a range of purposes, including market mapping, competitor analysis, and mergers and acquisitions. We propose and publish a knowledge graph, named CompanyKG, to represent and learn diverse company features and relations. Specifically, 1.17 million companies are represented as nodes enriched with company description embeddings; and 15 different inter-company relations result in 51.06 million weighted edges. To enable a comprehensive assessment of methods for company similarity quantification, we have devised and compiled three evaluation tasks with annotated test sets: similarity prediction, competitor retrieval and similarity ranking. We present extensive benchmarking results for 11 reproducible predictive methods categorized into three groups: node-only, edge-only, and node+edge. To the best of our knowledge, CompanyKG is the first large-scale heterogeneous graph dataset originating from a real-world investment platform, tailored for quantifying inter-company similarity