Dec
09
2020
The Polimi Fintech Series, under the fintech-ho2020.eu and the Cost Fin-AI.eu project, presents
December 9th, 2020 – 17.30 (CET)
Virtual room: Click here to access the Zoom Virtual Room, or insert the Meeting id on your Zoom app: 826 4084 3401
J. D. Turiel (UCL-ICL, Barclays Investment Bank)
with A. Briola and T. Aste
DEEP LEARNING MODELLING OF THE LIMIT ORDER BOOK: A COMPARATIVE PERSPECTIVE
Abstract:
We address 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 modelling 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.
Click here to download the paper
Stay updated with latest news on QFinLab seminars subscribing here: https://bit.ly/2TNtC6e
Information about future seminars: www.qfinlab.polimi.