Measuring firm-level supply chain risk using a generative large language model

Siyu Fan, Yifei Wu and Ruochen Yang

Finance Research Letters, 2025, vol. 77, issue C

Abstract: Using site visit transcripts from Chinese-listed firms, we propose a generative large language model (LLM)-based approach to quantify firm-level supply chain risks. We validate our measure by showing that it varies intuitively over time and across industries, and it correlates with higher capital costs, greater stock return volatility, and larger inventory reserves. Furthermore, we identify distinct categories of supply chain risks at both the micro and macro levels, finding that supply chain concentration drives micro-level risks, while exposure to overseas markets and macroeconomic conditions drives macro-level risks. Our findings highlight the capability of LLMs to assess supply chain risk.

Keywords: Supply chain risk; Large language models; Generative AI; Site visit (search for similar items in EconPapers)
JEL-codes: G12 G30 G32 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1544612325003745
Full text for ScienceDirect subscribers only

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:eee:finlet:v:77:y:2025:i:c:s1544612325003745

DOI: 10.1016/j.frl.2025.107111

Access Statistics for this article

Finance Research Letters is currently edited by R. Gençay

More articles in Finance Research Letters from Elsevier
Bibliographic data for series maintained by Catherine Liu ().