Deep Learning Modeling of the Limit Order Book: A Comparative Perspective

16 Pages Posted: 15 Dec 2020

See all articles by Antonio Briola

Antonio Briola

University College London

Jeremy Turiel

University College London

Tomaso Aste

University College London

Date Written: October 18, 2020

Abstract

The present work addresses theoretical and practical questions in the domain of Deep Learning for High Frequency Trading. State-of-the-art models such as Random models, Logistic Regressions, LSTMs, LSTMs equipped with an Attention mask, CNN-LSTMs and MLPs are reviewed and compared on the same tasks, feature space, and dataset and clustered according to pairwise similarity and performance metrics. The underlying dimensions of the modeling techniques are hence investigated to understand whether these are intrinsic to the Limit Order Book’s dynamics. We observe that the Multilayer Perceptron performs comparably to or better than state-of-the-art CNN-LSTM architectures indicating that dynamic spatial and temporal dimensions are a good approximation of the LOB’s dynamics, but not necessarily the true underlying dimensions.

Keywords: Artificial Intelligence, Deep Learning, Econophysics, Financial Markets, Market Microstructure

Suggested Citation

Briola, Antonio and Turiel, Jeremy and Aste, Tomaso, Deep Learning Modeling of the Limit Order Book: A Comparative Perspective (October 18, 2020). Available at SSRN: https://ssrn.com/abstract=3714230 or http://dx.doi.org/10.2139/ssrn.3714230

Antonio Briola

University College London ( email )

Gower Street
London, WC1E 6BT
United Kingdom
+39 3334147620 (Phone)

Jeremy Turiel (Contact Author)

University College London ( email )

Gower Street
London, WC1E 6BT
United Kingdom

Tomaso Aste

University College London ( email )

Gower Street
London, WC1E 6BT
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
448
Abstract Views
1,448
rank
92,801
PlumX Metrics