@TechReport{iza:izadps:dp19049,
            	author={Gray, Steve and Kemeny, Tom and Nathan, Max and Ozgen, Ceren and Pialli, Guido and Reades, Jon and Rosso, Anna and Seré, Mateo and Siddiqui, Sameera and Valero, Anna},
            	title={GRAPH-EE: Building Employer-Employee Panels from a Knowledge Graph and Company Microdata},
            	year={2026},
	month={Oct},
            	institution={Institute of Labor Economics (IZA)},
            	address={Bonn},
            	type={IZA Discussion Paper},
            	number={19049},
            	url={https://www.iza.org/publications/dp19049},
	abstract={Linked employer-employee datasets are a hugely powerful tool for researchers and policymakers across the social sciences. However, access to such data is typically highly restricted and the quality of data varies substantially across countries. This paper presents GRAPH-EE, a large-scale employer-employee platform for larger companies in the UK. Leveraging a vast knowledge graph of the global public internet linked to UK company microdata and global patents data, GRAPH-EE is a rich complement to administrative data sources. This version of the platform covers over 10,500 companies and 800,000 workers active in the UK during 2007-2023. We show the potential to extend our approach to multiple other countries. A public release version of the data, plus codebase and documentation, is available to researchers and detailed in this paper.},
	keywords={data science;employer-employee data;productivity;innovation;skills},
            }