Please use this identifier to cite or link to this item:
Title: Non-fundamental, non-parametric Bitcoin forecasting
Authors: Adcock, R.
Gradojević, Nikola 
Issue Date: 1-Oct-2019
Journal: Physica A: Statistical Mechanics and its Applications
Abstract: © 2019 Elsevier B.V. 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.
ISSN: 03784371
DOI: 10.1016/j.physa.2019.121727
Appears in Collections:FTN Publikacije/Publications

Show full item record


checked on Nov 20, 2023

Page view(s)

Last Week
Last month
checked on Mar 15, 2024

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.