Machine learning shows that the Covid-19 pandemic is impacting U.S. public companies unequally by changing risk structures

Likun Cao and Jie Ren

PLOS ONE, 2022, vol. 17, issue 6, 1-18

Abstract: Covid-19 has impacted the U.S. economy and business organizations in multiple ways, yet its influence on company fundamentals and risk structures have not been fully elucidated. In this paper, we apply LDA, a mainstream topic model, to analyze the risk factor section from SEC filings (10-K and 10-Q), and describe risk structure change over the past two years. The results show that Covid-19 has transformed the risk structures U.S. companies face in the short run, exerting excessive stress on international interactions, operations, and supply chains. However, this shock has been waning since the second quarter of 2020. Our model shows that risk structure change (measured by topic distribution) from Covid-19 is a significant predictor of lower performance, but smaller companies tend to be stricken harder.

Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0269582 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 69582&type=printable (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:plo:pone00:0269582

DOI: 10.1371/journal.pone.0269582

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().