Listen Closely: Using Vocal Cues to Predict Future Earnings

48 Pages Posted: 28 Dec 2022 Last revised: 13 Aug 2023

See all articles by Jonas Ewertz

Jonas Ewertz

Ruhr University of Bochum - Department of Finance and Banking

Charlotte Knickrehm

Ruhr University of Bochum - Department of Industrial Sales and Service Engineering

Martin Nienhaus

Ruhr University of Bochum

Doron Reichmann

Ruhr University of Bochum - Department of Finance and Banking

Date Written: August 12, 2023

Abstract

We analyze the information content of managerial vocal cues using machine learning. We develop a new approach using visualizations of managerial vocal cues (mel spectrograms) as inputs to a convolutional neural network (CNN). In examining the model's out-of-sample predictive power for future earnings changes, we find that the CNN significantly outperforms models based on numerical financial data and text. Moreover, the model estimates can be used to construct profitable stock portfolios and provide incremental information to analyst forecasts. Our results imply that managerial vocal cues are important information signals for future earnings that investment practitioners currently overlook.

Keywords: Earnings Prediction, Voice Analysis, Big Data

JEL Classification: G17, G41, C45, M41

Suggested Citation

Ewertz, Jonas and Knickrehm, Charlotte and Nienhaus, Martin and Reichmann, Doron, Listen Closely: Using Vocal Cues to Predict Future Earnings (August 12, 2023). Available at SSRN: https://ssrn.com/abstract=4307178 or http://dx.doi.org/10.2139/ssrn.4307178

Jonas Ewertz

Ruhr University of Bochum - Department of Finance and Banking ( email )

Germany
+49-(0)234-3223429 (Phone)

Charlotte Knickrehm

Ruhr University of Bochum - Department of Industrial Sales and Service Engineering ( email )

Universitätsstraße 150
Bochum, NRW 44780
Germany

Martin Nienhaus

Ruhr University of Bochum ( email )

Universitätsstraße 150
Bochum, 44801
Germany

Doron Reichmann (Contact Author)

Ruhr University of Bochum - Department of Finance and Banking ( email )

Germany

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

Paper statistics

Downloads
777
Abstract Views
2,606
Rank
61,117
PlumX Metrics