Using Deep Learning for price prediction by exploiting stationary limit order book features

TL;DR

This paper introduces a new method for creating stationary features from limit order book data, enabling effective deep learning-based price prediction, and proposes a hybrid CNN-LSTM model that outperforms individual models.

Contribution

A novel stationary feature construction method for financial data and a hybrid CNN-LSTM model that improves price movement prediction accuracy.

Findings

Stationary features enhance deep learning model performance.

Hybrid CNN-LSTM outperforms standalone models.

Effective deep learning approach for limit order book analysis.

Abstract

The recent surge in Deep Learning (DL) research of the past decade has successfully provided solutions to many difficult problems. The field of quantitative analysis has been slowly adapting the new methods to its problems, but due to problems such as the non-stationary nature of financial data, significant challenges must be overcome before DL is fully utilized. In this work a new method to construct stationary features, that allows DL models to be applied effectively, is proposed. These features are thoroughly tested on the task of predicting mid price movements of the Limit Order Book. Several DL models are evaluated, such as recurrent Long Short Term Memory (LSTM) networks and Convolutional Neural Networks (CNN). Finally a novel model that combines the ability of CNNs to extract useful features and the ability of LSTMs' to analyze time series, is proposed and evaluated. The combined model is able to outperform the individual LSTM and CNN models in the prediction horizons that are tested.