% WARNING: This file may contain UTF-8 (unicode) characters.
% While non-8-bit characters are officially unsupported in BibTeX, you
% can use them with the biber backend of biblatex
%    usepackage[backend=biber]{biblatex}

@techreport{NBERw27723,
 title = "Data-intensive Innovation and the State: Evidence from AI Firms in China",
 author = "Beraja, Martin and Yang, David Y and Yuchtman, Noam",
 institution = "National Bureau of Economic Research",
 type = "Working Paper",
 series = "Working Paper Series",
 number = "27723",
 year = "2020",
 month = "August",
 doi = {10.3386/w27723},
 URL = "http://www.nber.org/papers/w27723",
 abstract = {Artificial intelligence (AI) innovation is data-intensive. States have historically collected large amounts of data, which is now being used by AI firms. Gathering comprehensive information on firms and government procurement contracts in China’s facial recognition AI industry, we first study how government data shapes AI innovation. We find evidence of a precise mechanism: because data is sharable across uses, economies of scope arise. Firms awarded public security AI contracts providing access to more government data produce more software for both government and commercial purposes. In a directed technical change model incorporating this mechanism, we then study the trade-offs presented by states’ AI procurement and data provision policies. Surveillance states’ demand for AI may incidentally promote growth, but distort innovation, crowd-out resources, and infringe on civil liberties. Government data provision may be justified when economies of scope are strong and citizens’ privacy concerns are limited.},
}