Deep Learning for Digital Asset Limit Order Books

TL;DR

This paper demonstrates that temporal CNNs can accurately predict bitcoin price movements from limit order book data within seconds, achieving high accuracy and fast training times suitable for real-time trading environments.

Contribution

It introduces a deep learning approach using temporal CNNs for short-term bitcoin price prediction from order book data, with efficient training and deployment potential.

Findings

71% walk-forward accuracy on Coinbase data

Model trains in less than a day on commodity GPUs

Source code and data are publicly available

Abstract

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 at https://github.com/Globe-Research/deep-orderbook.