Man vs. Machine Learning: The Term Structure of Earnings Expectations and Conditional Biases

62 Pages Posted: 7 Jul 2020 Last revised: 19 Jan 2023

See all articles by Jules H. van Binsbergen

Jules H. van Binsbergen

University of Pennsylvania - The Wharton School; National Bureau of Economic Research (NBER)

Xiao Han

City University London - Bayes Business School

Alejandro Lopez-Lira

University of Florida - Department of Finance, Insurance and Real Estate

Multiple version iconThere are 2 versions of this paper

Date Written: January 20, 2022

Abstract

We introduce a real-time measure of conditional biases in firms' earnings forecasts. The measure is defined as the difference between analysts' expectations and a statistically optimal unbiased machine-learning benchmark. Analysts' conditional expectations are, on average, biased upwards, a bias that increases in the forecast horizon. These biases are associated with negative cross-sectional return predictability, and the short legs of many anomalies contain firms with excessively optimistic earnings. Further, managers of companies with the greatest upward-biased earnings forecasts are more likely to issue stocks. Commonly used linear earnings models do not work out-of-sample and are inferior to those provided by analysts.

Keywords: Earnings Forecasts, Machine Learning, Investment Strategies

Suggested Citation

van Binsbergen, Jules H. and Han, Xiao and Lopez-Lira, Alejandro, Man vs. Machine Learning: The Term Structure of Earnings Expectations and Conditional Biases (January 20, 2022). Review of Financial Studies, Forthcoming, Jacobs Levy Equity Management Center for Quantitative Financial Research Paper, Available at SSRN: https://ssrn.com/abstract=3625279 or http://dx.doi.org/10.2139/ssrn.3625279

Jules H. Van Binsbergen

University of Pennsylvania - The Wharton School ( email )

3641 Locust Walk
Philadelphia, PA 19104-6365
United States

National Bureau of Economic Research (NBER)

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

HOME PAGE: http://www.nber.org/people/jules_vanbinsbergen

Xiao Han

City University London - Bayes Business School ( email )

United Kingdom

Alejandro Lopez-Lira (Contact Author)

University of Florida - Department of Finance, Insurance and Real Estate ( email )

P.O. Box 117168
Gainesville, FL 32611
United States

HOME PAGE: http://alejandrolopezlira.site/

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
3,166
Abstract Views
9,632
Rank
6,837
PlumX Metrics