Does Text in MD&A Improve Earnings Forecasts?

• In Event: Data Analytics

Abstract

The Management Discussion and Analysis (MD&A) requirements are intended to provide
prospective textual disclosure... with particular emphasis on the registrant's prospects for the
future" (Securities and Exchange Commission, 1989). This paper tests the extent to which
MD&A disclosures improve quantitative forecasts of future prospects. We estimate and com-
pare a set of earnings forecasting models based solely on quantitative factors with expanded
models that include qualitative factors extracted from the MD&A section. To represent text
numerically for use in statistical forecasting models, we employ the bag-of-words (BOW) ap-
proach which identies and counts the words appearing in the MD&A section. Because of
the large number of words used, standard linear regression models cannot be applied, and we
use kernel ridge regressions to overcome the dimensionality problem. We nd that textual
information extracted from the MD&A section dramatically improves earnings forecasting
models that rely solely on quantitative factors. However, in periods of signicant economic
changes or economic downturn, the MD&A section appears to be uninformative, suggesting
that managers do not provide a reliable analysis of the business of the company in those
periods. Our results can be interpreted by the SEC as identifying a problem with MD&A
disclosure, namely the disclosures are least helpful in those periods in which informative
narrative is most needed.

Authors

• Khrystyna Bochkay, Rutgers, The State University of New Jersey, Newark

• Carolyn Levine, Rutgers, The State University of New Jersey