Deep Learning for Digital Asset Limit Order Books
University of Cambridge
arXiv:2010.01241 [q-fin.ST], (3 Oct 2020)
@misc{jha2020deep,
title={Deep Learning for Digital Asset Limit Order Books},
author={Rakshit Jha and Mattijs De Paepe and Samuel Holt and James West and Shaun Ng},
year={2020},
eprint={2010.01241},
archivePrefix={arXiv},
primaryClass={q-fin.ST}
}
This paper shows that temporal CNNs accurately predict bitcoin spot price movements from limit order book data. On a 2 second prediction time horizon we achieve 71% walk-forward accuracy on the popular cryptocurrency exchange coinbase. Our model can be trained in less than a day on commodity GPUs which could be installed into colocation centers allowing for model sync with existing faster orderbook prediction models. We provide source code and data.
October 11, 2020 by hgpu
