to certain news items and that this has predictive power to forecast company earnings.
By working with our fundamental analysts we have been able to better understand
which news items are of most interest and relevance. Along this vein, news flow may be
classified as company-specific (such as patent grants) or relate to broader industry trends
(e.g., global freight demand and semiconductor sales). Using statistical techniques that
model the time-series properties of the data we have built models that forecast the
direction of company and industry earnings using passenger numbers for transport
companies, retail vs. wholesale inflation for retailers, and commodity demand and
supply imbalances for materials companies.
With quarterly earnings data for European companies only going back a few years
(post the introduction of IFRS in 2005), the ability to backtest specific news flow and
earnings has been limited. However, the huge changes in market dynamics and behav-
iour in recent years means that such backtests are less of a concern. Indeed, in an
attempt to stay ahead of the competition, many institutional investors subscribe to
direct broker feeds to gain access to fundamental analyst DCF models and proprietary
data sources to stay ahead of consensus.
In conclusion, the analysis of news flow datasets is a complex though exciting area of
research. There are many ways to derive a trading signal using this information either in
isolation or to incorporate it into existing investment processes, providing many oppor-
tunities for future research. We have used news flow datasets to create sector rotation
models, forecast individual companies’ earnings and dividends, and understand price
momentum and short squeezes. Our philosophy to research has been to combine
quantitative techniques with a fundamental insight to stock selection. News flow
datasets enable systematic investors to bridge the gap between the two.
8.8 References
Abarbanell J.S.; Bernard V. (1992) ‘‘Tests of analysts’ overreaction/underreaction to earnings
information as an explanation for anomalous stock price behavior,’’Journal of Finance, 47 ,
1181–1207.
Antweiler W.; Frank M. (2005)The Market Impact of Corporate News Stories, Working Paper,
University of British Columbia.
Bagnoli M.; Levine S.; Watts S.G. (2005a) ‘‘Analyst estimation clusters and corporate events, part
I,’’Annals of Finance, 1 (3), 245–265.
Bagnoli M.; Levine S.; Watts S.G. (2005b) ‘‘Analyst estimation clusters and corporate events, part
II,’’Annals of Finance, 1 (4).
Barber B.M.; Odean T. (2008) ‘‘All that glitters: The effect of attention and news on the buying
behavior of individual and institutional investors,’’Review of Financial Studies, 21.
Barberis N.; Shleifer A.; Vishny R. (1998) ‘‘A model of investor sentiment,’’Journal of Financial
Economics, 49 , 307–343.
Bernard V.; Thomas J. (1989) ‘‘Post earnings announcement drift: Delayed price response or risk
premium,’’Journal of Accounting Research, Suppl. 27, 1–36
Berry T.; Howe K. (1994) ‘‘Public information arrival,’’Journal of Finance, 49 , 1331–1346.
Brar G. (2009)Quantamentals: Momentum Seeking Attention, Macquarie Quantitative Research.
Chan L K.C.; Jegadeesh N.; Lakonishok J. (1996) ‘‘Momentum strategies,’’Journal of Finance, 51 ,
1681–1714.
Chan W.S. (2003) ‘‘Stock price reaction to news and no-news: Drift and reversal after headlines,’’
Journal of Financial Economics, 70 (2), 223–260.
228 News and abnormal returns