Forecasting cryptocurrency price using convolutional neural networks with weighted and attentive memory channels

作者：

Highlights：

• Gated Recurrent Units with attention mechanism learn time-series features efficiently.

• Multi-channel model exploits correlations among the various cryptocurrency prices.

• Convolutional neural networks extract local features effectively.

摘要

•Gated Recurrent Units with attention mechanism learn time-series features efficiently.•Multi-channel model exploits correlations among the various cryptocurrency prices.•Convolutional neural networks extract local features effectively.

论文关键词：Cryptocurrency,Time-series forecasting,Convolutional neural networks,Gated recurrent units,Channel weighting,Attention mechanism

论文评审过程：Received 3 January 2021, Revised 21 May 2021, Accepted 6 June 2021, Available online 18 June 2021, Version of Record 21 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115378