Analyzing Speech to Detect Financial Misreporting
Analyzing Speech to Detect Financial Misreporting
- Jessen L. Hobson, William J. Mayew, Mohan Venkatachalam
- A version of the paper can be found here.
“We examine whether vocal markers of cognitive dissonance are useful for detecting financial misreporting. We use speech samples of CEOs during earnings conference calls and generate vocal dissonance markers using automated vocal emotion analysis software. We begin by assessing construct validity for the software-generated dissonance markers by correlating them with four dissonance-from-misreporting proxies obtained in a laboratory setting. We find a positive association between these proxies and vocal dissonance markers generated by the software, suggesting the software’s dissonance markers have construct validity. Applying the software to CEO speech, we find that vocal dissonance markers are positively associated with the likelihood of irregularity restatements. The diagnostic accuracy levels are 11% better than chance and of similar magnitude to models based solely on financial accounting information. Moreover, the association between vocal dissonance markers and irregularity restatements holds even after controlling for financial accounting and linguistic based predictors. Our results provide new evidence on the role of vocal cues in detecting financial misreporting.”
Laboratory Generated Data using Fifty-nine undergraduate volunteers from two large public U.S. universities and 1,572 conference calls available on Thomson Reuters Street Events.
Detecting deceptive financial reporting is important to investors, auditors, analysts and regulators. To developing a framework to predict deceptive financial reporting in a timely manner, this study tests a hypothesis: The probability of financial misreporting is positively associated with the extent of cognitive dissonance markers contained in the CEO’s voice.
At first, the authors generate a sample of truth-telling and misreporting subjects in a laboratory setting and invoke cognitive dissonance in the misreporting subjects. Then thet find the LVA (Layered Voice Analysis) dissonance markers extracted from subject interviews associated with four dissonance-from-misreporting proxies: belief revisions, confessions of misreporting, unexpected reported scores, and a factor score that combines these three individual proxies.
After demonstrating that voice based dissonance markers generated by LVA have validity, they explore the following model:
Pr (Misreporting) = f (Vocal Dissonance Markers, Dissonance Drivers Unrelated to Misreporting, Financial Statement Based Predictors of Misreporting, CEO Characteristics, Monitoring).
In words, the probability of misreporting is associated with a collection of indicators that suggest something doesn’t smell right.
The authors then measure cognitive dissonance using speech samples of CEOs from their interactions with analysts and investors during earnings conference calls. Logistic regressions reveal a positive association between vocal dissonance markers and adverse irregularity restatements. Therefore, cognitive dissonance in CEO speech can predict whether a firm’s quarterly financial reports will be adversely restated at better than random chance levels. The overall evidence suggests vocal cognitive dissonance markers can predict financial misreporting.
- Exam quarterly earnings call to detect fraud risk.
- Buy stocks with no or little fraud risk.
- Short stocks with high fraud risk
- Rebalance quarterly.
- Make money.
This paper provides evidence that elements of voiced speech can help detect financial misreporting. This paper is the first to investigate the predictive ability of vocal cues for actual misreporting in a capital market setting.
This research is informative to investors, analysts, and auditors who attempt to use earnings conference calls as an information source for assessing the risk of misreporting.
Vocal features represent only one class of deception markers and an evaluation of alternative nonverbal markers of deception is a worthwhile endeavor. Future research or investment could consider both verbal and nonverbal markers of deception, not only CEO’s speech but also CFO’s speech as well to detect misreporting and get a better view of all related information.
Go and there and hire you some linguistic PhDs (akin to what RenTec was doing 20 years ago) and try to make some money!
Note: This site provides NO information on our value investing ETFs or our momentum investing ETFs. Please refer to this site.
Join thousands of other readers and subscribe to our blog.
Please remember that past performance is not an indicator of future results. Please read our full disclosures. The views and opinions expressed herein are those of the author and do not necessarily reflect the views of Alpha Architect, its affiliates or its employees. This material has been provided to you solely for information and educational purposes and does not constitute an offer or solicitation of an offer or any advice or recommendation to purchase any securities or other financial instruments and may not be construed as such. The factual information set forth herein has been obtained or derived from sources believed by the author and Alpha Architect to be reliable but it is not necessarily all-inclusive and is not guaranteed as to its accuracy and is not to be regarded as a representation or warranty, express or implied, as to the information’s accuracy or completeness, nor should the attached information serve as the basis of any investment decision. No part of this material may be reproduced in any form, or referred to in any other publication, without express written permission from Alpha Architect.
Definitions of common statistics used in our analysis are available here (towards the bottom)