Analysis and Modeling of Client Order Flow in Limit Order Markets

Abstract

Orders in major electronic stock markets are executed through centralised limit order books (LOBs). The availability of historical data have led to extensive research modelling LOBs. Better understanding the dynamics of LOBs and building simulators as a framework for controlled experiments, when testing trading algorithms or execution strategies are among the aims in this area. Most work in the literature models the aggregate view of the limit order book, which focuses on the volume of orders at a given price level using a point process. In addition to this aggregate view, brokers and exchanges also have information on the identity of the agents submitting the order to them. This leads to a more complicated representation of limit order book dynamics, which we attempt to model using a heterogeneous model of order flow.

We present a granular representation of the limit order book, that allows to account for the origins of different orders. Using client order flow from a large broker, we analyze the properties of variables in this representation. The heterogeneity of the order flow is modeled by segmenting clients into different clusters, for which we identify representative prototypes. This segmentation appears to be stable both over time, as well as over different stocks. Our findings can be leveraged to build more realistic order flow models that account for the diversity of market participants.

Keywords: Limit order books, order flow, heterogeneous order flow, unsupervised learning, clustering, time series, machine learning