Conditional Asset Pricing with Text-Managed Portfolios

43 Pages Posted: 24 Feb 2025 Last revised: 2 Apr 2025

See all articles by Jian Feng

Jian Feng

HKU Business School, The University of Hong Kong

Jiantao Huang

The University of Hong Kong - Faculty of Business and Economics

Shiyang Huang

The University of Hong Kong - Faculty of Business and Economics

Ran Shi

University of Colorado Boulder - Department of Finance

Date Written: January 26, 2025

Abstract

We construct managed portfolios that exploit information extracted from firms’ earnings call transcripts and examine their asset pricing implications. Returns on these text-managed portfolios correlate with investor sentiment and predict macroeconomic outcomes. Individual stocks’ exposures to the text-managed portfolios explain as much return variation as those to the characteristics-sorted portfolios. Adding earnings call information to firm characteristics increases mean-variance efficiency, though it does not improve stock-level return predictability. Consistent with the insights from Kozak and Nagel (2024) on mean-variance spanning, our results suggest that earnings calls provide information about return covariances beyond what is captured by firm characteristics alone.

Keywords: factor models, mean-variance efficiency, conditioning information, text data

JEL Classification: C11, G11, G12

Suggested Citation

Feng, Jian and Huang, Jiantao and Huang, Shiyang and Shi, Ran, Conditional Asset Pricing with Text-Managed Portfolios (January 26, 2025). HKU Jockey Club Enterprise Sustainability Global Research Institute Paper No. 2025/022, Available at SSRN: https://ssrn.com/abstract=5111794 or http://dx.doi.org/10.2139/ssrn.5111794

Jian Feng

HKU Business School, The University of Hong Kong ( email )

Hong Kong
China

Jiantao Huang (Contact Author)

The University of Hong Kong - Faculty of Business and Economics ( email )

Pokfulam Road
Hong Kong
Hong Kong

Shiyang Huang

The University of Hong Kong - Faculty of Business and Economics ( email )

Pokfulam Road
Hong Kong
China

Ran Shi

University of Colorado Boulder - Department of Finance ( email )

995 Regent Drive
Boulder, CO 80309
United States

HOME PAGE: http://ranshi.one

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
94
Abstract Views
343
Rank
594,309
PlumX Metrics