TY - GEN
T1 - Behavior based learning in identifying High Frequency Trading strategies
AU - Yang, Steve
AU - Paddrik, Mark
AU - Hayes, Roy
AU - Todd, Andrew
AU - Kirilenko, Andrei
AU - Beling, Peter
AU - Scherer, William
PY - 2012
Y1 - 2012
N2 - Electronic markets have emerged as popular venues for the trading of a wide variety of financial assets, and computer based algorithmic trading has also asserted itself as a dominant force in financial markets across the world. Identifying and understanding the impact of algorithmic trading on financial markets has become a critical issue for market operators and regulators. We propose to characterize traders' behavior in terms of the reward functions most likely to have given rise to the observed trading actions. Our approach is to model trading decisions as a Markov Decision Process (MDP), and use observations of an optimal decision policy to find the reward function. This is known as Inverse Reinforcement Learning (IRL), and a variety of approaches for this problem are known. Our IRL-based approach to characterizing trader behavior strikes a balance between two desirable features in that it captures key empirical properties of order book dynamics and yet remains computationally tractable. Using an IRL algorithm based on linear programming, we are able to achieve more than 90% classification accuracy in distinguishing High Frequency Trading from other trading strategies in experiments on a simulated E-Mini S&P 500 futures market. The results of these empirical tests suggest that High Frequency Trading strategies can be accurately identified and profiled based on observations of individual trading actions.
AB - Electronic markets have emerged as popular venues for the trading of a wide variety of financial assets, and computer based algorithmic trading has also asserted itself as a dominant force in financial markets across the world. Identifying and understanding the impact of algorithmic trading on financial markets has become a critical issue for market operators and regulators. We propose to characterize traders' behavior in terms of the reward functions most likely to have given rise to the observed trading actions. Our approach is to model trading decisions as a Markov Decision Process (MDP), and use observations of an optimal decision policy to find the reward function. This is known as Inverse Reinforcement Learning (IRL), and a variety of approaches for this problem are known. Our IRL-based approach to characterizing trader behavior strikes a balance between two desirable features in that it captures key empirical properties of order book dynamics and yet remains computationally tractable. Using an IRL algorithm based on linear programming, we are able to achieve more than 90% classification accuracy in distinguishing High Frequency Trading from other trading strategies in experiments on a simulated E-Mini S&P 500 futures market. The results of these empirical tests suggest that High Frequency Trading strategies can be accurately identified and profiled based on observations of individual trading actions.
KW - Algorithmic trading
KW - High Frequency Trading
KW - Inverse Reinforcement Learning
KW - Limit order book
KW - Markov Decision Process
KW - Price impact
KW - Spoofing
UR - http://www.scopus.com/inward/record.url?scp=84869779430&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84869779430&partnerID=8YFLogxK
U2 - 10.1109/CIFEr.2012.6327783
DO - 10.1109/CIFEr.2012.6327783
M3 - Conference contribution
AN - SCOPUS:84869779430
SN - 9781467318037
T3 - 2012 IEEE Conference on Computational Intelligence for Financial Engineering and Economics, CIFEr 2012 - Proceedings
SP - 133
EP - 140
BT - 2012 IEEE Conference on Computational Intelligence for Financial Engineering and Economics, CIFEr 2012 - Proceedings
T2 - 2012 IEEE Conference on Computational Intelligence for Financial Engineering and Economics, CIFEr 2012
Y2 - 29 March 2012 through 30 March 2012
ER -