DeepLOB: Deep Convolutional Neural Networks for Limit Order Books

Abstract

We develop a large-scale deep learning model to predict price movements from limit order book (LOB) data of cash equities. The architecture utilises convolutional filters to capture the spatial structure of the limit order books as well as LSTM modules to capture longer time dependencies. The model is trained using electronic market quotes from the London Stock Exchange. Our model delivers a remarkably stable out-of-sample prediction accuracy for a variety of instruments and outperforms existing methods such as Support Vector Machines, standard Multilayer Perceptrons, as well as other previously proposed convolutional neural network (CNN) architectures. The results obtained lead to good profits in a simple trading simulation, especially when compared with the baseline models. Importantly, our model translates well to instruments which were not part of the training set, indicating the model's ability to extract universal features. In order to better understand these features and to go beyond a "black box" model, we perform a sensitivity analysis to understand the rationale behind the model predictions and reveal the components of LOBs that are most relevant. The ability to extract robust features which translate well to other instruments is an important property of our model which has many other applications.