Trader Lead-Lag Networks and Order Flow Prediction

21 Pages Posted: 18 Sep 2016

See all articles by Damien Challet

Damien Challet

CentraleSupélec; Encelade Capital SA

Rémy Chicheportiche

Ecole Centrale Paris

Mehdi Lallouache

Ecole Centrale Paris

Serge Kassibrakis

Swissquote Bank

Date Written: September 15, 2016

Abstract

Using trader-resolved data, we document lead-lag relationships between groups of investors in the foreign exchange market. Because these relationships are systematic and persistent, order flow is predictable from trader-resolved order flow. We thus propose a generic method to exploit trader lead-lag and predict the sign of the total order imbalance over a given time horizon. It first consists in an unsupervised clustering of investors according to their buy/sell/inactivity synchronization. The collective actions of these groups and their lagged values are given as inputs to machine learning methods. When groups of traders and when their lead-lag relationships are sufficiently persistent, highly successful out-of-sample order flow sign predictions are obtained.

Keywords: order flow, lead-lag, machine learning, prediction, networks

JEL Classification: G02, G11, G23

Suggested Citation

Challet, Damien and Chicheportiche, Rémy and Lallouache, Mehdi and Kassibrakis, Serge, Trader Lead-Lag Networks and Order Flow Prediction (September 15, 2016). Available at SSRN: https://ssrn.com/abstract=2839312 or http://dx.doi.org/10.2139/ssrn.2839312

Damien Challet (Contact Author)

CentraleSupélec ( email )

Labo MICS
3, rue Joliot-Curie
Gif-sur-Yvette, 91192
France

Encelade Capital SA ( email )

Chemin du Bochet 8
Sulpice, 1025
Switzerland

Rémy Chicheportiche

Ecole Centrale Paris ( email )

Paris
France

Mehdi Lallouache

Ecole Centrale Paris ( email )

Paris
France

Serge Kassibrakis

Swissquote Bank ( email )

Ch. de la Crétaux 33
Gland, Vaud 1196
Switzerland

Register to save articles to
your library

Register

Paper statistics

Downloads
109
Abstract Views
553
rank
251,731
PlumX Metrics