Forecasting cryptocurrency prices time series using machine learning approach
Open Access
- 29 May 2019
- journal article
- research article
- Published by EDP Sciences in SHS Web of Conferences
- Vol. 65, 02001
Abstract
This paper describes the construction of the short-term forecasting model of cryptocurrencies’ prices using machine learning approach. The modified model of Binary Auto Regressive Tree (BART) is adapted from the standard models of regression trees and the data of the time series. BART combines the classic algorithm classification and regression trees (C&RT) and autoregressive models ARIMA. Using the BART model, we made a short-term forecast (from 5 to 30 days) for the 3 most capitalized cryptocurrencies: Bitcoin, Ethereum and Ripple. We found that the proposed approach was more accurate than the ARIMA-ARFIMA models in forecasting cryptocurrencies time series both in the periods of slow rising (falling) and in the periods of transition dynamics (change of trend).Keywords
This publication has 17 references indexed in Scilit:
- Can volume predict Bitcoin returns and volatility? A quantiles-based approachEconomic Modelling, 2017
- Predicting Fluctuations in Cryptocurrency Transactions Based on User Comments and RepliesPLOS ONE, 2016
- The economics of BitCoin price formationApplied Economics, 2015
- Speculative bubbles in Bitcoin markets? An empirical investigation into the fundamental value of BitcoinEconomics Letters, 2015
- Bitcoins as an investment or speculative vehicle? A first lookApplied Economics Letters, 2014
- Extended Bayesian information criteria for model selection with large model spacesBiometrika, 2008
- A survey of Knowledge Discovery and Data Mining process modelsThe Knowledge Engineering Review, 2006
- Random ForestsMachine Learning, 2001
- Greedy function approximation: A gradient boosting machine.The Annals of Statistics, 2001
- Bayesian CART Model SearchJournal of the American Statistical Association, 1998