Transformers for Limit Order Books

TL;DR

This paper presents a novel deep learning architecture combining causal convolutional networks and masked self-attention to predict price movements from limit order books, outperforming existing models and setting new benchmarks.

Contribution

The authors introduce a new architecture that integrates causal convolutional networks with masked self-attention for improved limit order book prediction.

Findings

Significantly outperforms CNN and LSTM models

Establishes a new state-of-the-art benchmark on FI-2010 dataset

Demonstrates effectiveness of combining causal convolutions with self-attention

Abstract

We introduce a new deep learning architecture for predicting price movements from limit order books. This architecture uses a causal convolutional network for feature extraction in combination with masked self-attention to update features based on relevant contextual information. This architecture is shown to significantly outperform existing architectures such as those using convolutional networks (CNN) and Long-Short Term Memory (LSTM) establishing a new state-of-the-art benchmark for the FI-2010 dataset.