16 Pages Posted: 21 Mar 2011 Last revised: 8 Oct 2013
Date Written: March 15, 2011
Not long ago securities were traded by human traders in face-to-face markets. The ecosystem of an open outcry market was well-known, visible to a human eye, and rigidly prescribed. Now trading is increasingly done in anonymous electronic markets where traders do not have designated functions or mandatory roles. In fact, the traders themselves have been replaced by algorithms (machines) operating with little or no human oversight. While the process of electronic trading is not visible to a human eye, machine-learning methods have been developed to recognize persistent patterns in the data. In this study, we develop a dynamic machine-learning method that designates 15,686 traders in the E-mini S&P 500 stock index futures market into five persistent categories. Our method is based on a plaid clustering technique enhanced by a smoothing framework that filters out transient patterns. With the exception of high frequency traders (14 traders), the resulting categories of traders -- market makers (271 traders), opportunistic traders (7126), fundamental traders (254), and small traders (8021) -- play well-known, albeit it non-designated, market functions. High frequency traders, on the other hand, leave a distinctly more profound footprint in an electronic market.
Keywords: Trading Strategies, High Frequency Trading, Machine Learning, Clustering
JEL Classification: G12, G13, G18, G28
Suggested Citation: Suggested Citation
Mankad, Shawn and Michailidis, George and Kirilenko, Andrei A., Discovering the Ecosystem of an Electronic Financial Market with a Dynamic Machine-Learning Method (March 15, 2011). AFA 2012 Chicago Meetings Paper; Algorithmic Finance 2013, 2:2, 151-165. Available at SSRN: https://ssrn.com/abstract=1787577 or http://dx.doi.org/10.2139/ssrn.1787577