Behavior Based Learning in Identifying High Frequency Trading Strategies

8 Pages Posted: 8 Nov 2011

See all articles by Steve Y. Yang

Steve Y. Yang

Stevens Institute of Technology

Mark E. Paddrik

Government of the United States of America - Office of Financial Research

Roy Hayes

University of Virginia

Andrew Todd

University of Virginia

Andrei A. Kirilenko

Imperial College London - Centre for Global Finance and Technology

Peter Beling

University of Virginia, Dept. of System & Information Engineering

William Scherer

IEEE Intelligent Transportation Systems Society

Date Written: November 7, 2011

Abstract

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). 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.

Keywords: Limit order book, Inverse Reinforcement Learning, Markov Decision Process, Maximum likelihood, Price impact, High Frequency Trading

Suggested Citation

Yang, Steve Y. and Paddrik, Mark Endel and Hayes, Roy Lee and Todd, Andrew and Kirilenko, Andrei A. and Beling, Peter and Scherer, William, Behavior Based Learning in Identifying High Frequency Trading Strategies (November 7, 2011). Available at SSRN: https://ssrn.com/abstract=1955965 or http://dx.doi.org/10.2139/ssrn.1955965

Steve Y. Yang (Contact Author)

Stevens Institute of Technology ( email )

Hoboken, NJ 07030
United States

Mark Endel Paddrik

Government of the United States of America - Office of Financial Research ( email )

717 14th Street, NW
Washington DC, DC 20005
United States

Roy Lee Hayes

University of Virginia ( email )

United States

Andrew Todd

University of Virginia ( email )

1400 University Ave
Charlottesville, VA 22903
United States

Andrei A. Kirilenko

Imperial College London - Centre for Global Finance and Technology ( email )

South Kensington Campus
London, SW7 2AZ
United Kingdom

Peter Beling

University of Virginia, Dept. of System & Information Engineering ( email )

1400 University Ave
Charlottesville, VA 22903
United States

William Scherer

IEEE Intelligent Transportation Systems Society

United States

Register to save articles to
your library

Register

Paper statistics

Downloads
1,642
Abstract Views
7,231
rank
9,837
PlumX Metrics