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

Alejandro Lopez-Lira, Finance, The Wharton School

Abstract: Using unsupervised machine learning, I introduce interpretable and economically relevant risk factors that characterize the cross-section of returns better than the leading factor models, furthermore, I do not use any information from the past returns to select the risk factors. I exploit natural language processing techniques to identify from the firms’ risk disclosures the types of risks that firms face, quantify how much each firm is exposed to each type of risk, and employ the firms’ exposure to each type of risk to construct a 4-factor model. The risk factors roughly correspond to Technology and Innovation Risk, Demand Risk, Production Risk and International Risk.

Read the full working paper here (PDF).

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.