Convolution on neural networks for high-frequency trend prediction of cryptocurrency exchange rates using technical indicators

作者：

Highlights：

• Highlights

• Short term price trends of some cryptocurrencies can be predicted using deep learning on technical indicators on technical indicators.

• Bitcoin, Ethereum and Litecoin are statistically easier to predict than Dash and Ripple.

• Convolution improves prediction, and LSTM combined with convolutional layers provides the best results.

摘要

Highlights•Short term price trends of some cryptocurrencies can be predicted using deep learning on technical indicators on technical indicators.•Bitcoin, Ethereum and Litecoin are statistically easier to predict than Dash and Ripple.•Convolution improves prediction, and LSTM combined with convolutional layers provides the best results.

论文关键词：Cryptocurrencies,Neural network,Finance,Technical analysis,Deep learning

论文评审过程：Received 11 July 2019, Revised 21 January 2020, Accepted 24 January 2020, Available online 31 January 2020, Version of Record 6 February 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113250