The dynamics of returns predictability in cryptocurrency markets

【Author】 Bianchi, Daniele; Guidolin, Massimo; Pedio, Manuela

【Source】EUROPEAN JOURNAL OF FINANCE

【影响因子】1.903

【Abstract】In this paper, we take a forecasting perspective and compare the information content of a set of market risk factors, cryptocurrency-specific predictors, and sentiment variables for the returns of cryptocurrencies vs traditional asset classes. To this aim, we rely on a flexible dynamic econometric model that not only features time-varying coefficients, but also allows for the entire forecasting model to change over time to capture the time variation in the exposures of major digital currencies to the predictive variables. Besides, we investigate whether the inclusion of cryptocurrencies in an already diversified portfolio leads to additional economic gains. The main empirical results suggest that cryptocurrencies are not systematically predicted by stock market factors, precious metal commodities or supply factors. On the contrary, they display a time-varying but significant exposure to investors' attention. In addition, also because of a lack of predictability compared to traditional asset classes, cryptocurrencies lead to realized expected utility gains for a power utility investor.

【Keywords】Bitcoin; cryptocurrencies; returns predictability; investments; dynamic model averaging

【发表时间】

【收录时间】2022-06-18

【文献类型】实证性文章

【主题类别】

区块链治理-市场治理-数字货币