Adaptive Hidden Markov Model With Anomaly States for Price Manipulation Detection

Y Cao, Yuhua Li, SA Coleman, Ammar Belatreche, TM McGinnity

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Price manipulation refers to the activities of those traders who use carefully designed trading behaviors to manually push up or down the underlying equity prices for making profits. With increasing volumes and frequency of trading, price manipulation can be extremely damaging to the proper functioning and integrity of capital markets. The existing literature focuses on either empirical studies of market abuse cases or analysis of particular manipulation types based on certain assumptions. Effective approaches for analyzing and detecting price manipulation in real time are yet to be developed. This paper proposes a novel approach, called adaptive hidden Markov model with anomaly states (AHMMAS) for modeling and detecting price manipulation activities. Together with wavelet transformations and gradients as the feature extraction methods, the AHMMAS model caters to price manipulation detection and basic manipulation type recognition. The evaluation experiments conducted on seven stock tick data from NASDAQ and the London Stock Exchange and 10 simulated stock prices by stochastic differential equation show that the proposed AHMMAS model can effectively detect price manipulation patterns and outperforms the selected benchmark models.
LanguageEnglish
Pages318-330
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume26
Issue number2
DOIs
Publication statusPublished - Feb 2015

Fingerprint

Hidden Markov models
Feature extraction
Profitability
Differential equations
Experiments

Cite this

Cao, Y ; Li, Yuhua ; Coleman, SA ; Belatreche, Ammar ; McGinnity, TM. / Adaptive Hidden Markov Model With Anomaly States for Price Manipulation Detection. 2015 ; Vol. 26, No. 2. pp. 318-330.
@article{f9f8565fb0ba4d3eb1d5303f9abf9ab9,
title = "Adaptive Hidden Markov Model With Anomaly States for Price Manipulation Detection",
abstract = "Price manipulation refers to the activities of those traders who use carefully designed trading behaviors to manually push up or down the underlying equity prices for making profits. With increasing volumes and frequency of trading, price manipulation can be extremely damaging to the proper functioning and integrity of capital markets. The existing literature focuses on either empirical studies of market abuse cases or analysis of particular manipulation types based on certain assumptions. Effective approaches for analyzing and detecting price manipulation in real time are yet to be developed. This paper proposes a novel approach, called adaptive hidden Markov model with anomaly states (AHMMAS) for modeling and detecting price manipulation activities. Together with wavelet transformations and gradients as the feature extraction methods, the AHMMAS model caters to price manipulation detection and basic manipulation type recognition. The evaluation experiments conducted on seven stock tick data from NASDAQ and the London Stock Exchange and 10 simulated stock prices by stochastic differential equation show that the proposed AHMMAS model can effectively detect price manipulation patterns and outperforms the selected benchmark models.",
author = "Y Cao and Yuhua Li and SA Coleman and Ammar Belatreche and TM McGinnity",
year = "2015",
month = "2",
doi = "10.1109/TNNLS.2014.2315042",
language = "English",
volume = "26",
pages = "318--330",
number = "2",

}

Adaptive Hidden Markov Model With Anomaly States for Price Manipulation Detection. / Cao, Y; Li, Yuhua; Coleman, SA; Belatreche, Ammar; McGinnity, TM.

Vol. 26, No. 2, 02.2015, p. 318-330.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Adaptive Hidden Markov Model With Anomaly States for Price Manipulation Detection

AU - Cao, Y

AU - Li, Yuhua

AU - Coleman, SA

AU - Belatreche, Ammar

AU - McGinnity, TM

PY - 2015/2

Y1 - 2015/2

N2 - Price manipulation refers to the activities of those traders who use carefully designed trading behaviors to manually push up or down the underlying equity prices for making profits. With increasing volumes and frequency of trading, price manipulation can be extremely damaging to the proper functioning and integrity of capital markets. The existing literature focuses on either empirical studies of market abuse cases or analysis of particular manipulation types based on certain assumptions. Effective approaches for analyzing and detecting price manipulation in real time are yet to be developed. This paper proposes a novel approach, called adaptive hidden Markov model with anomaly states (AHMMAS) for modeling and detecting price manipulation activities. Together with wavelet transformations and gradients as the feature extraction methods, the AHMMAS model caters to price manipulation detection and basic manipulation type recognition. The evaluation experiments conducted on seven stock tick data from NASDAQ and the London Stock Exchange and 10 simulated stock prices by stochastic differential equation show that the proposed AHMMAS model can effectively detect price manipulation patterns and outperforms the selected benchmark models.

AB - Price manipulation refers to the activities of those traders who use carefully designed trading behaviors to manually push up or down the underlying equity prices for making profits. With increasing volumes and frequency of trading, price manipulation can be extremely damaging to the proper functioning and integrity of capital markets. The existing literature focuses on either empirical studies of market abuse cases or analysis of particular manipulation types based on certain assumptions. Effective approaches for analyzing and detecting price manipulation in real time are yet to be developed. This paper proposes a novel approach, called adaptive hidden Markov model with anomaly states (AHMMAS) for modeling and detecting price manipulation activities. Together with wavelet transformations and gradients as the feature extraction methods, the AHMMAS model caters to price manipulation detection and basic manipulation type recognition. The evaluation experiments conducted on seven stock tick data from NASDAQ and the London Stock Exchange and 10 simulated stock prices by stochastic differential equation show that the proposed AHMMAS model can effectively detect price manipulation patterns and outperforms the selected benchmark models.

U2 - 10.1109/TNNLS.2014.2315042

DO - 10.1109/TNNLS.2014.2315042

M3 - Article

VL - 26

SP - 318

EP - 330

IS - 2

ER -