A New Take on SEC Comment Letters: Positive Drift!
Textual Classification of SEC Comment Letters
- James P. Ryans
- A version of the paper can be found here.
- Want a summary of academic papers with alpha? Check out our Academic Research Recap Category.
SEC Comment letters appear to be under-utilized by investors because these largely text-based disclosures are more difficult to access and interpret than other common disclosures. Using a naive Bayesian textual analysis procedure, I classify important SEC comment letters where the signal of importance is significantly negative abnormal returns following comment letter disclosure. Text analysis alone can identify important letters between 10% and 40% better than chance. The text analysis signal provides additional power to identify important comment letters over other signals such as insider sales and the presence of revenue recognition related comments. The incorporation of comment letter information into security prices is more pronounced for comment letters known to have been accessed by investors, using the SEC’s EDGAR download logs, providing evidence of investor inattention to important comment letters.
Should we be paying more attention to SEC Comment Letters? The authors of this paper say “Yes!”
- All SEC comment letters can be found at ftp.sec.gov.
There are a lot of findings in this paper, but Figure 1 was interesting for reasons that have nothing to do with textual analysis. The figure below shows the evolution of CAR, or cumulative abnormal returns, over a disclosure date -10 to +90 day window. We can see that information in comment letters may be slowly incorporate into prices, perhaps due to investor inattention.
- Panel (a) illustrates an unexpected positive drift with delay for all firms. This drift may be explained by the fact that the receipt of an innocuous letter is in effect a certification that the SEC has found no significant financial reporting issues.
- Panel (b) shows a negative drift of firms with greater than 2 requests in the 3 days following disclosure. It indicates that comment letters with bad news appear to be read more frequently.
Perhaps there are ways to identify firms with comment letters that have the most positive drift by eliminating those with multiple comment letter requests? Unfortunately, the author doesn’t share those results…
But he does share results after controlling for insider trading patterns:
Looks like there may be some legs to a strategy that avoids firms with comment letters and insider selling…
We’re new to comment letters, but this paper sparked some ideas.
Anyone worked with comment letters?
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)