Can AI Read the Minds of Corporate Executives?

54 Pages Posted: 7 Jul 2023 Last revised: 9 Apr 2024

See all articles by Nicolas Chapados

Nicolas Chapados

ServiceNow Research

Zhenzhen Fan

Gordon S Lang School of Business and Economics, University of Guelph, Guelph, Canada - Department of Economics and Finance

Ruslan Goyenko

McGill University - Desautels Faculty of Management

Issam Hadj Laradji

ServiceNow Research

Fred Liu

University of Guelph; University of Western Ontario, Department of Economics

Chengyu Zhang

McGill University - Desautels Faculty of Management

Date Written: June 27, 2023

Abstract

It can. Using textual information from a complete history of regular quarterly and annual filings by U.S. corporations, we train classic machine learning algorithms and large language models, LLMs, to predict future earnings surprises. We first find that the length of MD\&A section on its own is negatively associated with future earnings surprises and firm returns in the cross-section. Second, neither sentiment-based nor bag-of-words classic machine learning regression-based approaches are able to ``learn'' from the past managerial discussions to forecast future earnings. Third, only \textit{finance-objective trained} LLMs have the capacity to ``understand'' the contexts of previous 10-Q (10-K) releases to predict both positive and negative earnings surprises, and subsequent future firm returns. We find significant, and often hidden in the complexity of presentations, positive and negative informational content of publicly disclosed corporate filings, and superior (to human and classic NLP approaches) abilities of more recent AI models to identify it.

Suggested Citation

Chapados, Nicolas and Fan, Zhenzhen and Goyenko, Ruslan and Laradji, Issam Hadj and Liu, Fred and Zhang, Chengyu, Can AI Read the Minds of Corporate Executives? (June 27, 2023). Available at SSRN: https://ssrn.com/abstract=4493166 or http://dx.doi.org/10.2139/ssrn.4493166

Nicolas Chapados

ServiceNow Research

Zhenzhen Fan

Gordon S Lang School of Business and Economics, University of Guelph, Guelph, Canada - Department of Economics and Finance ( email )

Canada

Ruslan Goyenko (Contact Author)

McGill University - Desautels Faculty of Management ( email )

1001 Sherbrooke St. West
Montreal, Quebec H3A1G5 H3A 2M1
Canada

Issam Hadj Laradji

ServiceNow Research ( email )

6650 St Urbain Street, Suite 500
Montreal, Quebec H2S3G9
Canada

Fred Liu

University of Guelph ( email )

50 Stone Road East
Guelph, Ontario N1G 2W1
Canada

University of Western Ontario, Department of Economics ( email )

London, Ontario
Canada

Chengyu Zhang

McGill University - Desautels Faculty of Management ( email )

1001 Sherbrooke St. West
Montreal, Quebec H3A1G5 H3A 2M1
Canada

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

Paper statistics

Downloads
716
Abstract Views
2,244
Rank
69,096
PlumX Metrics