Forecasting of Jump Arrivals in Stock Prices: New Attention-based Network Architecture using Limit Order Book Data

TL;DR

This paper introduces a novel neural network architecture with attention mechanisms for predicting stock return jump arrivals using high-frequency limit order book data, demonstrating improved performance over existing models.

Contribution

A new Convolutional LSTM with Attention architecture is proposed, enhancing short-term jump prediction accuracy by focusing on key features in limit order book data.

Findings

Attention mechanism improves jump prediction performance.

Limit order book data's importance varies across stocks.

Proposed model outperforms existing neural network models.

Abstract

The existing literature provides evidence that limit order book data can be used to predict short-term price movements in stock markets. This paper proposes a new neural network architecture for predicting return jump arrivals in equity markets with high-frequency limit order book data. This new architecture, based on Convolutional Long Short-Term Memory with Attention, is introduced to apply time series representation learning with memory and to focus the prediction attention on the most important features to improve performance. The data set consists of order book data on five liquid U.S. stocks. The use of the attention mechanism makes it possible to analyze the importance of the inclusion limit order book data and other input variables. By using this mechanism, we provide evidence that the use of limit order book data was found to improve the performance of the proposed model in jump prediction, either clearly or marginally, depending on the underlying stock. This suggests that path-dependence in limit order book markets is a stock specific feature. Moreover, we find that the proposed approach with an attention mechanism outperforms the multi-layer perceptron network as well as the convolutional neural network and Long Short-Term memory model.