Index
Jose Joy Thoppan
(Saintgits Institute of Management, India)
M. Punniyamoorthy
(National Institute of Technology, India)
K. Ganesh
(McKinsey & Company, India)
Sanjay Mohapatra
(Xavier Institute of Management, India)
Developing an Effective Model for Detecting Trade-based Market Manipulation
ISBN: 978-1-80117-397-1, eISBN: 978-1-80117-396-4
Publication date: 5 May 2021
This content is currently only available as a PDF
Citation
Thoppan, J.J., Punniyamoorthy, M., Ganesh, K. and Mohapatra, S. (2021), "Index", Developing an Effective Model for Detecting Trade-based Market Manipulation, Emerald Publishing Limited, Leeds, pp. 101-105. https://doi.org/10.1108/978-1-80117-396-420211021
Publisher
:Emerald Publishing Limited
Copyright © 2021 M. Punniyamoorthy, Jose Joy Thoppan, K. Ganesh, and Sanjay Mohapatra. Published under an exclusive license by Emerald Publishing Limited
INDEX
Action-based manipulation
, 21–22
Advanced detection system (ADS)
, 30
Amsterdam stock markets
, 1
Analytical techniques
, 30
χ2 approximation test
, 62–63
Artificial neural network-genetic algorithm based composite mode (ANN-GA based composite model). See also Support Vector Machines model (SVM model)
, 35–37, 39–40, 53, 83–85
applying weights to neural network
, 71
artificial neural network based model
, 47–49
comparison of results
, 53–54
convergence
, 70–71
for detecting stock price manipulation
, 46–51
determining weights using genetic algorithm
, 68–71
development of model
, 67–71
fitness function
, 70
generating chromosome
, 68
reproduction
, 70
results
, 72–73
weight extraction
, 69–70
Artificial neural networks (ANN)
, 31, 46, 66, 72
ANN based model
, 47–49
computing weights using genetic algorithm
, 49–51
hidden layer nodes
, 47–49
input layer nodes
, 47
output layer nodes
, 49
Autoregressive integrated moving average (ARIMA)
, 17
Behavioural finance
, 3
Bombay stock exchange (BSE)
, 4, 39
index
, 4
Box’s M-test
, 44, 62
C#.NET 2.0
, 53, 83
Capital market
, 4, 10–11
in India
, 3–4
trading behaviour in
, 10
Capital Markets Cooperative Research Centre (CMCRC)
, 2
Chromosome
, 68
Classification
, 30
Classifier equation
, 37
Closing price manipulation
, 25
Co-location facility
, 4–5
Composite model
, 34, 67
Confusion matrix
, 39–40, 72, 81–82
Continuous auction framework
, 20
Convergence
, 70–71
Corporate practices
, 21
Crossover operation
, 47, 49
Currency
derivatives segments
, 4
futures and options
, 4
Day trading
, 8
Department of Company Affairs (DCA)
, 5
Department of Economics Affairs (DEA)
, 5
Depositories
, 11–12
Derivatives Market
, 4
Dhaka Stock Exchange (DSE)
, 17
Direct Market Access (DMA)
, 4–5
Discriminant analysis
, 31, 35, 37, 39–40, 55
Discrimination
, 30
DTREG
, 53, 83
Dual Decision function
, 80
Econometrics and network
, 31
Effective Market Surveillance
, 10
Efficient market
, 16–17
Efficient stock market
, 3
Efficient-Market Hypothesis (EMH)
, 3, 16–17
Equal variance-covariance
, 62–63
test of equal variance-covariance matrices
, 43–44
Equities based derivatives
, 4
Equity based ETFs
, 4
F-approximation
method
, 63
test
, 45
Fitness function
, 70
FIX capabilities
, 4–5
Flash Orders
, 15
Futures & Options segments (F&O segments)
, 37–38
Game theory
, 23
Generalized Squared Distance Function
, 64
Genetic Algorithm (GA)
, 47, 50–51, 66
determining weights using
, 68–71
Global Capital Markets
, 6–7
Gold ETF
, 4
Graph clustering algorithm
, 31
Guinness Four Business Scandal, The
, 6
Hedge Funds
, 27
Helsinki Stock Exchange
, 27
Hyperplane
, 51, 75
maximum margin
, 77
Illegal price manipulation
, 21
Indian Capital Market
, 85
Indian Equity Exchanges
, 71, 81
Indian Equity Market
, 37, 39
Indian Stock Exchange
, 1, 38
Indian Stock Market
, 3, 5, 33
BSE
, 4
identifying research gap
, 33–34
key developments in
, 4–5
limitations of scope
, 35
NSE
, 4
research objectives
, 35–36
scope of research
, 34–35
Information
dissemination
, 16
false
, 23–24
flow
, 17
information-based manipulation
, 21–22, 24
insider
, 23
material
, 3
private
, 25
Information flow dynamics
, 17
Informed trader
, 25
Instruments
, 2
Integrated Market Surveillance System (IMSS)
, 11–12
Integrated Surveillance Department of SEBI
, 11
Intermediaries
, 2
IPOs
, 4–5, 19
Istanbul Stock Exchange
, 31
Karush–Kuhn–Tucker conditions (KKT conditions)
, 79
Kernel function
, 79–80
‘Lead-lag’ linkages
, 17
Linear Classification Function
, 41–42, 56, 59
Linear classifier
, 85
Linear discriminant analysis. See also Quadratic Discriminant analysis
, 83–84
Linear discriminant function (LDF). See also Quadratic Discriminant Function (QDF)
, 35, 39–40, 53, 55, 59, 85
comparison of results
, 53–54
for detecting stock price manipulation
, 41–42
development of model
, 55–56
F-approximation test
, 45, 63
limitation of model
, 58
linear classification function
, 41–42, 56
results
, 56–58
test for multivariate normality
, 42–43
test of equal variance-covariance matrices
, 43–44
test to check data
, 60
test to check for equal variance-covariance
, 62–63
testing assumptions governing
, 42, 45, 59, 63
χ2 approximation test
, 62–63
Linear kernel function
, 79
Linear Soft Margin Classifier
, 52, 75
Linearly Separable Classifier
, 52, 75–76, 79
Liquid market
, 16
Livedoor Scandal, The
, 6
Logistics regression
, 31
Logit, Genetic Algorithm
, 34
Long Dated Options
, 4
Manipulate/manipulation
, 19, 24, 33
in stock market
, 1
of stock prices
, 1
techniques to detect
, 1, 30–31
Manipulators
, 1
Market
data dissemination
, 3
integrity
, 17–18
regulation
, 7
surveillance system
, 7, 11, 13, 15, 18, 29–30, 83
transparency
, 18
Market manipulation
, 5, 9, 13, 19, 29
action-based manipulation
, 22
empirical studies in
, 26–29
information-based manipulation
, 22–24
theoretical foundation to
, 20–26
trade-based manipulation
, 24–26
Market Quality Forum
, 34–35
Market structure
, 2–3
instruments
, 2
market data dissemination
, 3
market participants and intermediaries
, 2
models adopted in present work
, 13
regulator and regulations
, 2
technology
, 2
MATLAB
, 53, 83
Microsoft. Net framework
, 83
Mini Nifty
, 4
Misclassification tables
, 37, 40
Mobile trading
, 4–5
Multi discriminant analysis (MDA)
, 34
Multivariate normality, test for
, 42–43
Mutual Fund Service System
, 4
NASDAQ Stock Market
, 30
Nasdaq-Liffe (futures) stock markets
, 30
National Stock Exchange (NSE)
, 4, 6, 37–39
Neural network model
, 34, 46, 49–50, 68
applying weights to
, 71
Neurons
, 46–47
New York Stock Exchange (NYSE)
, 18
Non-linear classifier
, 52, 75, 79, 81
Online message board database
, 24
Opportunistic individuals
, 23
Over the counter (OTC)
, 30
Penny stocks
, 8
Polynomial kernel function
, 79
Price of stock
, 1, 3
Profit maximization
, 24
Pump-and-dump strategy
, 28
Q-Q plot
, 42, 60–61
Quadratic Classification function
, 64
Quadratic discriminant analysis
, 63–64, 83–84
results
, 64–66
testing assumptions governing Linear Discriminant Function
, 59–63
Quadratic discriminant function (QDF). See also Linear discriminant function
, 35–36, 39–40, 45–46, 53, 63–65, 84–85
comparison of results
, 53–54
QDF based model
, 85
Quadratic Discriminant analysis for detecting stock price manipulation
, 45–46
Radial basis function (RBF)
, 79
kernel function
, 52, 81
Random walk behaviour
, 16
Redistribution method
, 40
Regulations
, 2
Regulator
, 2
Reproduction
, 70
Reserve Bank of India (RBI)
, 5–7
Retail equity investor
, 4–5
Retail Government Securities
, 4
Saddle point
, 78
Securities Exchange Board of India (SEBI)
, 5–7, 10, 12, 19–20, 38–39
IMSS
, 11–12
Securities Exchange Commission
, 23
Securities Observation, News Analysis, and Regulation system (SONAR system)
, 30
Securities regulation
, 18
Self-regulating organizations (SROs)
, 6, 83
SENSEX
, 4
Sequential trade framework
, 20
Share prices
, 20
Sigmoid kernel function
, 79
Sigmoidal activation function
, 71
Small cap stocks
, 8
Smart Order Routing (SOR)
, 4–5
SQL Server 2005
, 83
Stock
, 75–76
Stock market
efficient
, 3
Indian Stock Market
, 3–5
motivation for research
, 12–13
SEBI
, 10–12
stock price manipulation
, 5–9
surveillance
, 9–12
surveillance systems
, 31
Stock price manipulation
, 5, 9, 55
ANN-GA based composite model for detecting stock price manipulation
, 46–51
issues in identifying manipulation
, 7–9
Linear Discriminant Function for detecting
, 41–42
Quadratic Discriminant analysis for detecting
, 45–46
SVM model for detecting
, 51–53
types of manipulation
, 9
Structure–based methods
, 31
Substantiation
, 21
Support vector machine model (SVM model). See also Artificial neural network-genetic algorithm based composite mode (ANN-GA based composite model)
, 31, 34–37, 39–40, 53, 75–77, 81, 84–86
comparison of results
, 53–54
confusion matrix
, 82
development of model
, 75–81
error count estimates for stock
, 82
linearly separable classifier
, 76–79
model for detecting stock price manipulation
, 51–53
non-linear classifier
, 79–81
results
, 81–82
Surveillance system
, 7, 9
stock market
, 9, 12
Technology
, 2
Tehran Stock Exchange (TSE)
, 31
Theory of Efficient Market
, 16
Trade data
, 37–39
Trade-based manipulation
, 21–22, 24, 26
Trade-based market
efficient market
, 16–17
literature review of
, 15
market integrity
, 17–18
market manipulation
, 19–29
market surveillance
, 29–30
techniques to detect manipulation
, 30–31
Trade-based price manipulation
, 20
Trading regulations
, 29
Trading strategy
, 21
Tunisian Stock Market (TSE)
, 17
Variance-covariance matrix
, 34, 59, 83–84
Volatility
, 3, 26
Weight extraction
, 69–70
- Prelims
- 1 Introduction
- 2 Literature Review
- 3 Research Gap, Scope and Objective
- 4 Methodology
- 5 Linear Discriminant Analysis for Detecting Stock Price Manipulation
- 6 Quadratic Discriminant Analysis for Detecting Stock Price Manipulation
- 7 ANN-GA Based Composite Model for Detection of Stock Price Manipulation
- 8 SVM Model for Detecting Stock Price Manipulation
- 9 Summary and Conclusion
- Appendix I Types of Manipulation
- References
- Index