Learning Unfair Trading: A Market Manipulation Analysis from the Reinforcement Learning Perspective

TY - CHAP

T1 - Learning Unfair Trading

T2 - 10th IEEE Conference on Evolving and Adaptive Intelligent Systems, EAIS 2016

AU - Martinez Miranda, Enrique

AU - McBurney, Peter

AU - Howard, Matthew J. W.

PY - 2016/6/30

Y1 - 2016/6/30

N2 - Market manipulation is a strategy used by traders to alter the price of financial assets. One type of manipulation is based on the process of buying or selling assets by using several trading strategies, among them spoofing is a popular strategy and is considered illegal by market regulators. Some promising tools have been developed to detect price manipulation, but cases can still be found in the markets. In this paper we model spoofing and pinging trading from a macroscopic perspective of profit maximisation, two strategies that differ in the legal background but share the same elemental concept of market manipulation. We use a reinforcement learning framework within the full and partial observability of Markov decision processes and analyse the underlying behaviour of the perpetrators by finding the causes of what encourages these traders to perform fraudulent activities. Procedures can be applied to counter the problem as our model predicts the activity of the manipulators.

AB - Market manipulation is a strategy used by traders to alter the price of financial assets. One type of manipulation is based on the process of buying or selling assets by using several trading strategies, among them spoofing is a popular strategy and is considered illegal by market regulators. Some promising tools have been developed to detect price manipulation, but cases can still be found in the markets. In this paper we model spoofing and pinging trading from a macroscopic perspective of profit maximisation, two strategies that differ in the legal background but share the same elemental concept of market manipulation. We use a reinforcement learning framework within the full and partial observability of Markov decision processes and analyse the underlying behaviour of the perpetrators by finding the causes of what encourages these traders to perform fraudulent activities. Procedures can be applied to counter the problem as our model predicts the activity of the manipulators.

KW - Asset price manipulation

KW - Generative model

KW - MDP

KW - Pinging

KW - Spoofing

UR - http://www.scopus.com/inward/record.url?scp=84979870765&partnerID=8YFLogxK

U2 - 10.1109/EAIS.2016.7502499

DO - 10.1109/EAIS.2016.7502499

M3 - Conference paper

AN - SCOPUS:84979870765

SN - 9781509025831

SP - 103

EP - 109

BT - Proceedings of the 2016 IEEE Conference on Evolving and Adaptive Intelligent Systems, EAIS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 23 May 2016 through 25 May 2016

ER -