We introduce a firm-level exposure to macroeconomic shocks derived from 10K Risk Factors' ability to predict shock-related market surprises and illustrate its application to COVID-19. It has significant explanatory power for returns in- and out-of-sample; contains all relevant information for future real outcomes present in surprises; and can be decomposed into interpretable word groupings that collectively account for real outcomes. These highlight numerous specific channels through which COVID-19 generated negative and positive real effects, and how these are distributed across firms. By reflecting information on trading partners, technology adoption, and business models, text explains how COVID-19 created long-lasting firm heterogeneity.
About the speaker
Stephen Hansen is an Associate Professor of Economics at Imperial College Business School. His current research uses unstructured data to build new measures of economic activity and behavior across a variety of applications, most often related to organisational economics and monetary policy. He maintains a Github page where he shares code and lecture slides related to methodologies for the analysis of unstructured and high-dimensional data. Stephen co-organises the monthly AMLEDS webinar exploring economic applications of machine learning and his research is supported by an ERC Conslidator Grant.
This event will be a HYBRID event. To join this seminar online OR in person, please register on Zoom. You will then receive an email with the dial in details for those attending virtually. Please check your spam/junk folders for joining details.
Please contact email@example.com for more information.