Statistically validated lead-lag networks and inventory prediction in the foreign exchange market

TL;DR

This paper presents a method to infer persistent lead-lag networks among traders in the foreign exchange market, enabling prediction of order flow and price movements at an hourly scale using machine learning.

Contribution

It introduces a statistically validated approach to identify trader lead-lag networks and demonstrates their predictive power for order flow and price direction in FX markets.

Findings

Lead-lag networks are highly persistent over time.

Order flow sign and price direction are strongly predictable for retail traders.

Trader activity is explained by endogenous lead-lag relationships.

Abstract

We introduce a method to infer lead-lag networks of agents' actions in complex systems. These networks open the way to both microscopic and macroscopic states prediction in such systems. We apply this method to trader-resolved data in the foreign exchange market. We show that these networks are remarkably persistent, which explains why and how order flow prediction is possible from trader-resolved data. In addition, if traders' actions depend on past prices, the evolution of the average price paid by traders may also be predictable. Using random forests, we verify that the predictability of both the sign of order flow and the direction of average transaction price is strong for retail investors at an hourly time scale, which is of great relevance to brokers and order matching engines. Finally, we argue that the existence of trader lead-lag networks explains in a self-referential way why a given trader becomes active, which is in line with the fact that most trading activity has an endogenous origin.