The Wiley Finance Series : Handbook of News Analytics in Finance

(Chris Devlin) #1

To get the most value out of a backtesting system, the news sentiment of a news item
needs to be determined when the news becomes public and before the actual impact of
the news item. Such a backtesting system indicates the ability of the news sentiment
system to predict the impact before the stock movement rather than showing an ability
to measure the sentiment effect after the move took place. The differences are significant
and should not be ignored.


4.18 The value of media sentiment


Media Sentiment^1 has developed a technology that can make a rapid assessment of the
sentiment expressed by management in an earnings news release. The system correlates
that information with estimates from Wall Street analysts and the overbought/oversold
signals of the trading market, which allows profitable trading opportunities to be
discovered. Media Sentiment LimitsTMprovides suggestions for stock price entry points
along with conservative and aggressive stop limits.
What is the value that Media Sentiment brings to traders and investors?
To answer this critical question, one would need to understand how much the Media
Sentiment system improves the accuracy and efficiency of one’s own reading and
determination of the sentiment and impact of an earnings news release. As is the case
with medicine, users’ benefit levels may vary from person to person.
For instance, if one user can increase his/her accuracy by 10% and if the user can
convert that accuracy into dollars that would be the equivalent of a value add of 10 cents
for each dollar invested or traded.
Users’ expectations should be such that Media Sentiment alerts will help to improve
their accuracy and speed in determining the sentiment and impact of a higher number of
earnings news releases.
Even an incremental improvement will allow users to benefit from potential profits
that result from an increased number of opportunities.
The value that Media Sentiment brings to the end-user comes from the following:


a. Its focus on earnings news releases of public companies trading on NASDAQ and
NYSE This is by far one of the most important news releases in the life of a public
company. The earnings news release process is highly regulated; therefore, users are
able to take full advantage of real-time Media Sentiment alerts without questioning
the legitimacy of the news source.
b. Repeatable, unbiased process that finds the stock tickers most likely to move in the
direction of media sentiment Internal data analysis indicated an average of 80% or
more accuracy in media sentiment indicating the direction of movement of the stock
price during the trading day following the news release.
c. Highly accurate real-time sentiment determination and delivery This is achieved
through website updates, email, RSS, a multitude of financial websites via distribu-
tion partners, integration with broker platforms such as TD AMERITRADE and
optionsXpress, and integration with a stock data analysis platform such as
MetaStock (a Reuters product).
d. Backtesting by using Media Sentiment historical data going back to 2002 These
Media Sentiment alerts were delivered before actual stock movement took place


120 Quantifying news: Alternative metrics

Free download pdf