Recent Advances of Exception Mining in Stock Market - Evolving Application Domains of Data Warehousing and Mining - page 227

future reSeArch toPIcS there are a variety of definitions of insider trad-

ing from different exchanges, and there are also
different regulations for market manipulations
in different exchanges. In addition, the emerg-
ing markets have different performance with the
mature markets, such as NYSK. There are two
kinds of markets: one is floor stock markets, like
NYSK; another kind of markets is electric markets
where the trades occur automatically by comput-
ers. Therefore, there are no general models which
fit everywhere. The produced models should be
based on specific environments.
The market microstructure theory provides
some measures of stock markets including re-
turn, abnormal return, volume, volatility, spread
(Gopikrishnan & Stanley 2005). These measures
play important roles in stock market surveil-
lance.

Although there are a couple of existing techniques
on exception mining in stock market, there are
still many open issues on this research, and there
are also some possible research topics which have
potential to stock market surveillance. This section
will present future research topics in this area.

Application of Market
Microstructure theory

Market Microstructure is a branch of finance con-
cerned with the details of how exchange occurs
in markets (Frino & Segara 2008, Harris 2003).
While the theory of market microstructure applies
to the exchange of real or financial assets, more
evidence is available on the microstructure of
financial markets due to the availability of transac-
tion data from financial markets. The major thrust
of market microstructure research examines the
ways in which the working process of a market
affects determinants of transaction costs, prices,
quotes, volume, and trading behavior.
O'Hara (1997) defined market microstructure
as “the study of the process and outcomes of ex-
changing assets under a specific set of rules. While
much of economics abstracts from the mechan-
ics of trading, microstructure theory focuses on
how specific trading mechanisms affect the price
formation process.” The market microstructure
theory is one of the most important theories in
finance. It is a rapid growing specialization of fi-
nancial economics. It can help us understand stock
markets and the elements in stock markets. The
key elements in stock market include the trading
protocol, participants, information, regulations,
technologies and instruments. Market microstruc-
ture also provides the measures of market quality
and efficiency, such as the liquidity, transparency,
volatility and transaction cost and risk.
In order to utilize microstructure efficiently in
stock market surveillance, we need to consider all
the elements and their relationships. For instance,

• Return refers to the gain or loss for a single

security or portfolio over a specific pe-
riod. It is usually quoted as a percentage.
The popular equation to calculate return
is VOMM price eturn

k

_ , where R t is the return
over the period from time t to time t-1 , P t
is the trading price at time t , and P t-1 is the
trading price at time t-1 .
Abnormal return is the difference between •

the actual return of a single security or
portfolio and the expected return over a
specific period. The expected return is the
estimated return based on an asset pricing
model, using a long run historical average
or multiple valuations. Brown and Warner
(1985) gave the following formula to mea-
sure the abnormal return: AR jt = R jt - (α j
+ β j R mt ), where AR jt is the abnormal return
for the security j at time t , R jt is the ob-
served return for the security j at time t, R mt
is the observed return for the market index
at time t, and α j , β j are the estimated param-
eters using previous return observations.
Volatility is a statistical measure of the •