The information flow and the (semi) automation of the corresponding IS architecture
is set out in Figure 1.8. There are two streams of information which flow simultaneously:
news data and market data. Pre-analysis is applied to news data; it is further filtered and
processed by classifiers to compute relevant metrics. This is consolidated with the
market data of prices and together they constitute the classical datamart which feeds
into whatever relevant model-based applications are sought. A key aspect of these
applications is that they set out to provide technology-enabled support to professional
decision makers and thereby achieve intelligence amplification (Leinweber, 2009).
1.4.2 Trading and fund management
Generally traders and quantitative fund managers seek to identify and exploit asset
mispricings before they are corrected in order to generate alpha. Most simply they may
use (quantified) news data torank stocksand identify which stocks are relatively
attractive (unattractive). They may then buy (sell) the highest (lowest) ranking stocks,
thereby rebalancing a portfolio composed of desired weights on the selected
stocks. Similarly, the news data may be used to identify trading signals for particular
stocks. Alternatively, analysts may usefactor modelsto process new sources of news
data. (Factor models, which are applied to give updated estimates of future asset returns
and volatility, allow us to determine an optimal future portfolio to hold; that is, they tell
us which assets to hold and also in what proportions.) Analysts may also use news data
to identify and exploitbehavioural biasesin investor attitude/reactions which result due
to the market and analyst misreaction to new information. In particular, this can arise
due to delayed information diffusion or due to investor inattention and limited ability to
process all relevant information instantaneously.
Stock picking and ranking
Li (2006) uses a simple ranking procedure to identify stocks with positive and negative
(financial language) sentiment. He examines form 10-K Securities and Exchange Com-
mission (SEC) filings for non-financial firms between 1994 and 2005. He creates a ‘‘risk
sentiment measure’’ which is formed by counting the number of times the words risk,
18 The Handbook of News Analytics in Finance
Figure 1.8.Information flow and computational architecture