Smooth Plaid Models: A Dynamic Clustering Algorithm with Application to Electronic Financial Markets

Abstract

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 In fact, the traders themselves have been replaced by algorithms (machines) operating with little or no human oversight.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.