Wang, YuChen, Runyu2020-01-042020-01-042020-01-07978-0-9981331-3-3http://hdl.handle.net/10125/63875With the rapid development of the Internet, cryptocurrencies have been gaining increasing amounts of attention dramatically. As a digital currency, it is not only used worldwide for online payments, but also traded as an investment tool on the market. Therefore, the ability to predict the price volatility will facilitate future investment and payment decisions. However, there are many uncertainties in the price movement of cryptocurrencies, and the prediction is extremely difficult. To this end, based on the transaction data of three different markets and the number and content of user comments and responses from online forums, this paper constructs a price prediction model of cryptocurrencies using a variety of machine learning and deep learning algorithms. It turns out that the trading price premium rate in different markets will affect the price to be predicted, and adding social media comment features can significantly improve the accuracy of the forecast. This article is conducive to investors who encrypt currencies to make more scientific decisions.9 pagesengAttribution-NonCommercial-NoDerivatives 4.0 InternationalDecision Support for Smart Citiescryptocurrencymultiple marketprice predictiontext miningConference Paper10.24251/HICSS.2020.136