English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Bitcoin, one of the major cryptocurrencies, presents great opportunities andchallenges with its tremendous potential returns accompanying high risks. Thehigh volatility of Bitcoin and the complex factors affecting them make thestudy of effective price forecasting methods of great practical importance tofinancial investors and researchers worldwide. In this paper, we propose anovel approach called MRC-LSTM, which combines a Multi-scale ResidualConvolutional neural network (MRC) and a Long Short-Term Memory (LSTM) toimplement Bitcoin closing price prediction. Specifically, the Multi-scaleresidual module is based on one-dimensional convolution, which is not onlycapable of adaptive detecting features of different time scales in multivariatetime series, but also enables the fusion of these features. LSTM has theability to learn long-term dependencies in series, which is widely used infinancial time series forecasting. By mixing these two methods, the model isable to obtain highly expressive features and efficiently learn trends andinteractions of multivariate time series. In the study, the impact of externalfactors such as macroeconomic variables and investor attention on the Bitcoinprice is considered in addition to the trading information of the Bitcoinmarket. We performed experiments to predict the daily closing price of Bitcoin(USD), and the experimental results show that MRC-LSTM significantlyoutperforms a variety of other network structures. Furthermore, we conductadditional experiments on two other cryptocurrencies, Ethereum and Litecoin, tofurther confirm the effectiveness of the MRC-LSTM in short-term forecasting formultivariate time series of cryptocurrencies.

MRC-LSTM: A Hybrid Approach of Multi-scale Residual CNN and LSTM to Predict Bitcoin Price