Non-fundamental, non-parametric Bitcoin forecasting

【Author】 Adcock, Robert; Gradojevic, Nikola

【Source】PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS

【影响因子】3.778

【Abstract】Bitcoin is the largest cryptocurrency in the world, but its lack of quantitative qualities makes fundamental analysis of its intrinsic value difficult. As an alternative valuation and forecasting method we propose a non-parametric model based on technical analysis. Using simple technical indicators, we produce point and density forecasts of Bitcoin returns with a feedforward neural network. We run several models over the full period of April 2011-March 2018, and four subsamples, and we find that backpropagation neural networks dominate various competing models in terms of their forecast accuracy. We conclude that the dynamics of Bitcoin returns is characterized by predictive local non-linear trends that reflect the speculative nature of cryptocurrency trading. (C) 2019 Elsevier B.V. All rights reserved.

【Keywords】Bitcoin; Neural networks; Technical analysis; Density forecasting

【发表时间】2019 1-Oct

【收录时间】2022-01-02

【文献类型】

【主题类别】

--