Sequence Classification of the Limit Order Book using Recurrent Neural Networks

TL;DR

This paper demonstrates that recurrent neural networks can effectively predict short-term price flips in high-frequency trading by analyzing limit order book data, outperforming traditional classifiers.

Contribution

It introduces a novel application of RNNs for sequence classification in high-frequency trading, focusing on predicting price flips from order book data.

Findings

RNN captures non-linear relationships in order book data.

RNN outperforms linear Kalman filter in prediction accuracy.

Retraining frequency and latency affect RNN performance.

Abstract

Recurrent neural networks (RNNs) are types of artificial neural networks (ANNs) that are well suited to forecasting and sequence classification. They have been applied extensively to forecasting univariate financial time series, however their application to high frequency trading has not been previously considered. This paper solves a sequence classification problem in which a short sequence of observations of limit order book depths and market orders is used to predict a next event price-flip. The capability to adjust quotes according to this prediction reduces the likelihood of adverse price selection. Our results demonstrate the ability of the RNN to capture the non-linear relationship between the near-term price-flips and a spatio-temporal representation of the limit order book. The RNN compares favorably with other classifiers, including a linear Kalman filter, using S&P500 E-mini futures level II data over the month of August 2016. Further results assess the effect of retraining the RNN daily and the sensitivity of the performance to trade latency.