LOB modeling using Hawkes processes with a state-dependent factor

TL;DR

This paper introduces a novel point process model for limit order book order flows that combines Hawkes processes with a state-dependent factor, improving fit and interpretability of market dynamics.

Contribution

It proposes a new LOB modeling approach integrating state-dependent factors into Hawkes processes, with efficient estimation methods and empirical validation.

Findings

Enhanced model fit to real market data

Effective estimation techniques demonstrated

Improved understanding of order flow dynamics

Abstract

A point process model for order flows in limit order books is proposed, in which the conditional intensity is the product of a Hawkes component and a state-dependent factor. In the LOB context, state observations may include the observed imbalance or the observed spread. Full technical details for the computationally-efficient estimation of such a process are provided, using either direct likelihood maximization or EM-type estimation. Applications include models for bid and ask market orders, or for upwards and downwards price movements. Empirical results on multiple stocks traded in Euronext Paris underline the benefits of state-dependent formulations for LOB modeling, e.g. in terms of goodness-of-fit to financial data.