Description
TL;DR: A period Bitcoin forecasting study that selects an ARIMA(2,1,2) model after ACF, PACF, and first-difference analysis.
About This Document
Nashirah Abu Bakar and Sofian Rosbi examine Bitcoin exchange-rate behavior in a high-volatility environment. The paper reports that the first-differenced series is stationary, gives the selected model an R-squared value of 0.444432, and reports 5.36 percent mean absolute percentage error for its ex-post forecast. Those figures describe the authors' dataset and evaluation, not a standing prediction service.
Why Bitcoin People May Care
The paper is a clean snapshot of conventional time-series machinery being applied to early Bitcoin markets. Its value is methodological: model identification, diagnostics, fit, and forecast error are visible in eight pages. Historical fit does not guarantee future performance, and this document is not investment advice or a trading signal.
What You Receive
Purchase reveals the verified preserved PDF location for this document.
Document Details
- Title: ARIMA Forecasting of Bitcoin Exchange Rates in a High-Volatility Market
- Author / organization: Nashirah Abu Bakar and Sofian Rosbi
- Year: 2017
- Language: English
- Document type: Research paper
- Pages: 8
CacheRat provides researched source-location and document-identification information. CacheRat does not claim ownership of the underlying third-party documentation.
