An Efficient deep learning model to Predict Stock Price Movement Based on Limit Order Book

TL;DR

This paper introduces a Siamese deep learning architecture with multi-head attention to improve stock price movement prediction from limit order book data, demonstrating significant performance gains on Chinese A-share stocks.

Contribution

The paper proposes a novel Siamese architecture leveraging ask-bid symmetry and integrates multi-head attention with LSTM to enhance prediction accuracy in high-frequency trading models.

Findings

Siamese architecture improves baseline models in over 75% of cases.

Multi-head attention enhances short-term prediction performance.

Raw order book data's ask-bid symmetry is effectively exploited.

Abstract

In high-frequency trading (HFT), leveraging limit order books (LOB) to model stock price movements is crucial for achieving profitable outcomes. However, this task is challenging due to the high-dimensional and volatile nature of the original data. Even recent deep learning models often struggle to capture price movement patterns effectively, particularly without well-designed features. We observed that raw LOB data exhibits inherent symmetry between the ask and bid sides, and the bid-ask differences demonstrate greater stability and lower complexity compared to the original data. Building on this insight, we propose a novel approach in which leverages the Siamese architecture to enhance the performance of existing deep learning models. The core idea involves processing the ask and bid sides separately using the same module with shared parameters. We applied our Siamese-based methods to several widely used strong baselines and validated their effectiveness using data from 14 military industry stocks in the Chinese A-share market. Furthermore, we integrated multi-head attention (MHA) mechanisms with the Long Short-Term Memory (LSTM) module to investigate its role in modeling stock price movements. Our experiments used raw data and widely used Order Flow Imbalance (OFI) features as input with some strong baseline models. The results show that our method improves the performance of strong baselines in over 75$% of cases, excluding the Multi-Layer Perception (MLP) baseline, which performed poorly and is not considered practical. Furthermore, we found that Multi-Head Attention can enhance model performance, particularly over shorter forecasting horizons.