Risk Factors That Matter: Textual Analysis of Risk Disclosures for the Cross-Section of Returns

Alejandro Lopez-Lira, Finance, The Wharton School

Abstract: What are the fundamental risks in the economy? Which risks are systematic? Which risks are priced? Are the risks summarized well by existing models? I use machine learning to identify the risks that firms face based on their annual reports. The risks are described in plain words, and the most discussed risks are Innovation Risk, Demand Risk, Production Risk, International Risk, and Property Risk. I quantify how much each firm is exposed to each risk, design a test to classify them into systematic and idiosyncratic, and construct portfolios proxying for each risk. The portfolios are not spanned by the traditional factors. A factor model formed with the most discussed risks performs at least as good as the traditional ones, while not using any information from past returns.

Read the full working paper here.

Michelle Eckert is Marketing and Communications Coordinator for the Mack Institute, where she works to engage students, researchers, and corporate partners in opportunities for collaboration. Michelle received her B.A. in Art from Valparaiso University in 2007. Her background includes two AmeriCorps terms of service working to teach mathematics, computer literacy, and job readiness skills to out-of-school youth in Philadelphia, focusing particularly on promoting access to post-secondary education.