ANN‐GA based model for stock market surveillance
| Date | 28 December 2012 |
| DOI | https://doi.org/10.1108/13590791311287355 |
| Pages | 52-66 |
| Published date | 28 December 2012 |
| Author | Murugesan Punniyamoorthy,Jose Joy Thoppan |
| Subject Matter | Accounting & finance |
ANN-GA based model for stock
market surveillance
Murugesan Punniyamoorthy and Jose Joy Thoppan
Department of Management Studies, National Institute of Technology,
Tiruchirappalli, India
Abstract
Purpose – This paper attempts to develop a hybrid model using advanced data mining techniques
for the detection of Stock Price Manipulation. The hybrid model detailed in this article elucidates the
application of a Genetic Algorithm based Artificial Neural Network to classify stocks witnessing
activities that are suggestive of potential manipulation.
Design/methodology/approach – Price,volume and volatilityare usedas the variablesfor this model
to capture the characteristics of stocks. An empirical anal ysis of this model is carried out to evaluate its
abilityto predictstock price manipulationin oneof the largest emergingmarkets – India,which has a large
number of securities and significant trading volumes. Further, the article compares the performance of this
hybrid modelwith a conventionalstandalone model basedon Quadratic DiscreminantFunction (QDF).
Findings – Based on the results obtained, the superiority of the hybrid model over the conventional
model in its ability to predict manipulation in stock prices has been established.
Research limitations/implications – The classification by the proposed model is agnostic of the
type of manipulation – action-based, information-based or trade-based.
Practical implications – The market regulators can use these techniques to ensure that sufficient
deterrents are in place to identify a manipulator in their market. This helps them carry out their
primary function, namely, investor protection. These models will help effective monitoring for
abnormal market activities and detect market manipulation.
Social implications – Implementing this model at a regulator or SRO helps in strengthening the
integrity and safety of the market. This strengthens investor confidence and hence participation, as the
investors are made aware that the regulators implementing market manipulation detection techniques
ensure that the markets they monitor are secure and protects investor interest.
Originality/value – This is the first time a hybrid model has been used to detect market
manipulation.
Keywords Stock markets, Stockprices, Modelling, Market manipulation,Surveillance,
Artificial neuralnetworks, Genetic algorithms
Paper type Research paper
1. Introduction
It is an established fact that share prices are more often than not determined by investor’s
perceptions about the future prospects of the company issuing the shares. This is measured
by the ability of the management in guiding the company on its way to higher growth and
profits and on the current/future market for the company’s goods or services. But these
perceptions can often be manipulated by one or a group of participants and this has from
time to time led to the creation of stock specific or market wide imbalances that have led to
market crashes. These crashes which can be attributed to market manipulations were
almost always characterised by wide swings in the three major variables that determine the
trading activity and interest in particular scrip namely, price, volume and volatility
(Comerton-Forde and Putnins, 2009) among other variables. In the 400 years since
organised trading in shares began, there has been numerous instances of price rigging and
The current issue and full text archive of this journal is available at
www.emeraldinsight.com/1359-0790.htm
JFC
20,1
52
Journal of Financial Crime
Vol. 20 No. 1, 2013
pp. 52-66
qEmerald Group Publishing Limited
1359-0790
DOI 10.1108/13590791311287355
To continue reading
Request your trial