Attention-Based Reading, Highlighting, and Forecasting of the Limit Order Book

TL;DR

This paper introduces an advanced sequence-to-sequence model with a novel embedding technique to accurately forecast the entire multi-level limit order book, capturing complex interdependencies in high-frequency trading data.

Contribution

We develop a compound multivariate embedding method that effectively models complex relationships in high-dimensional LOB data, improving forecasting accuracy.

Findings

Outperforms existing multivariate forecasting methods

Achieves lowest forecasting error in experiments

Preserves the ordinal structure of the LOB

Abstract

Managing high-frequency data in a limit order book (LOB) is a complex task that often exceeds the capabilities of conventional time-series forecasting models. Accurately predicting the entire multi-level LOB, beyond just the mid-price, is essential for understanding high-frequency market dynamics. However, this task is challenging due to the complex interdependencies among compound attributes within each dimension, such as order types, features, and levels. In this study, we explore advanced multidimensional sequence-to-sequence models to forecast the entire multi-level LOB, including order prices and volumes. Our main contribution is the development of a compound multivariate embedding method designed to capture the complex relationships between spatiotemporal features. Empirical results show that our method outperforms other multivariate forecasting methods, achieving the lowest forecasting error while preserving the ordinal structure of the LOB.