Mapping the Geography of Products: Generative AI as a New Methodological Frontier

Milad Abbasiharofteh and Hamid Bekamiri

No 2616, Papers in Evolutionary Economic Geography (PEEG) from Utrecht University, Department of Human Geography and Spatial Planning, Group Economic Geography

Abstract: This paper argues that generative artificial intelligence (GenAI) represents a methodological turning point in economic geography and regional studies and provides a proof of concept for this transition. Building on successive waves of data collection methods, from surveys and standardized secondary data to web-based data, we show how GenAI can complement existing methods by approximating firms’ product portfolios from unstructured information and linking them to standardized classifications. Moving beyond product mapping, we conclude by discussing a research agenda that addresses broader data and methodological challenges and outlines how GenAI can contribute to a new methodological frontier.

Keywords: economic geography, regional studies; generative artificial intelligence; geography of products; web data (search for similar items in EconPapers)
JEL-codes: C55 L26 O33 R12 (search for similar items in EconPapers)
Date: 2026-08, Revised 2026-08
New Economics Papers: this item is included in nep-geo and nep-tid
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://econ.geo.uu.nl/peeg/peeg2616.pdf Version August 2026 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:egu:wpaper:2616

Access Statistics for this paper

More papers in Papers in Evolutionary Economic Geography (PEEG) from Utrecht University, Department of Human Geography and Spatial Planning, Group Economic Geography Contact information at EDIRC.
Bibliographic data for series maintained by ( this e-mail address is bad, please contact ).