HLOB -- Information Persistence and Structure in Limit Order Books

TL;DR

This paper introduces HLOB, a deep learning model that leverages information filtering and homological neural networks to improve mid-price change forecasting in limit order books, revealing complex dependency structures.

Contribution

The paper presents a novel deep learning architecture combining information filtering networks and homological neural networks for limit order book prediction.

Findings

HLOB outperforms 9 state-of-the-art models on NASDAQ datasets.

It uncovers deeper dependency structures among volume levels.

The approach clarifies information distribution and its degradation over time.

Abstract

We introduce a novel large-scale deep learning model for Limit Order Book mid-price changes forecasting, and we name it `HLOB'. This architecture (i) exploits the information encoded by an Information Filtering Network, namely the Triangulated Maximally Filtered Graph, to unveil deeper and non-trivial dependency structures among volume levels; and (ii) guarantees deterministic design choices to handle the complexity of the underlying system by drawing inspiration from the groundbreaking class of Homological Convolutional Neural Networks. We test our model against 9 state-of-the-art deep learning alternatives on 3 real-world Limit Order Book datasets, each including 15 stocks traded on the NASDAQ exchange, and we systematically characterize the scenarios where HLOB outperforms state-of-the-art architectures. Our approach sheds new light on the spatial distribution of information in Limit Order Books and on its degradation over increasing prediction horizons, narrowing the gap between microstructural modeling and deep learning-based forecasting in high-frequency financial markets.