This paper leverages generative AI to build a network structure over 5,000 product nodes, where directed edges represent input-output relationships in production. We layout a two-step ‘build-prune’ approach using an ensemble of prompt-tuned generative AI classifications. The ’build’ step provides an initial distribution of edge-predictions, the ‘prune’ step then re-evaluates all edges. With our AI-generated Production Network (AIPNET) in toe, we document a host of shifts in the network position of products and countries during the 21st century. Finally, we study production network spillovers using the natural experiment presented by the 2017 blockade of Qatar. We find strong evidence of such spillovers, suggestive of on-shoring of critical production. This descriptive and causal evidence demonstrates some of the many research possibilities opened up by our granular measurement of product linkages, including studies of on-shoring, industrial policy, and other recent shifts in global trade.

About the speaker

Thiemo Fetzer is Professor of Economics at Warwick University and at the University of Bonn. Thiemo is also an Academic Visitor at the Bank of England, an Affiliate at the Center for Economic Policy Research (CEPR) and a Fellow at the British National Institute for Social and Economic Research (NIESR).

His work cross cuts many fields in economics ranging from international trade, economic development, finance, to spatial economics and political economy leveraging frontier techniques from machine learning, artificial intelligence and computer science.