Mapping GitHub repositories to NAICS industry codes for repo-scale intelligence

arXiv·low signal

Researchers built a system to classify GitHub repositories into standardized North American Industry Classification System (NAICS) codes, a mapping GitHub itself does not expose, enabling industry-level analysis across hundreds of millions of public repos. For anyone building repo-intelligence or developer-ecosystem agents, it's a reusable classification layer over open-source activity. A small but practical enabler for market- and trend-analysis tooling.