A complete empirical ensemble mode decomposition and support vector machine-based approach to predict Bitcoin prices

被引：43

作者：

Aggarwal, Divya ^{[1
]}

Chandrasekaran, Shabana ^{[2
]}

Annamalai, Balamurugan ^{[3
]}

机构：

[1] XLRI Xavier Sch Management, Jamshedpur 831001, Jharkhand, India

[2] Xavier Univ, Xavier Inst Management, Bhubaneswar 751013, Odisha, India

[3] Indian Inst Management Sambalpur, Sambalpur 768019, Odisha, India

来源：

JOURNAL OF BEHAVIORAL AND EXPERIMENTAL FINANCE | 2020年 / 27卷

关键词：

Bitcoin; Complete empirical ensemble mode with adaptive noise decomposition (CEEMDAN); Cryptocurrency; Support vector machine; Empirical mode decomposition (EMD); Ensemble empirical mode decomposition (EEMD); VOLATILITY; STOCK; CRYPTOCURRENCIES; INEFFICIENCY; MARKETS; GOLD; CURRENCIES; DEPENDENCE; SPECTRUM;

D O I：

10.1016/j.jbef.2020.100335

中图分类号：

F8 [财政、金融];

学科分类号：

0202 ;

摘要：

Bitcoin as an asset class has received phenomenal investor attention and is considered to have similar characteristics like gold. This study aims to analyze the price behavior of bitcoin and apply machine learning algorithm for its prediction. Understanding the nature of Bitcoin price series is a multi-scale problem, and it can be best examined by analyzing its compositional characteristics. This study uses complete empirical ensemble mode decomposition (CEEMD) to analyze the nature of Bitcoin price series. Daily Bitcoin prices from 2012 to 2018 are used to perform CEEMD to identify the short term, medium term, and long-term trend in the Bitcoin price series. The study uses support vector machine (SVM) learning algorithm to find whether it can predict Bitcoin prices and finds that SVM predicts five steps ahead Bitcoin prices for the short term, medium term, long term, and overall Bitcoin price level. (C) 2020 Published by Elsevier B.V.

引用

页数：12

共 69 条

[41] Minute-ahead stock price forecasting based on singular spectrum analysis and support vector regression [J].

Lahmiri, Salim .

APPLIED MATHEMATICS AND COMPUTATION, 2018, 320 :444-451

[42] Comparing Variational and Empirical Mode Decomposition in Forecasting Day-Ahead Energy Prices [J].

Lahmiri, Salim .

IEEE SYSTEMS JOURNAL, 2017, 11 (03) :1907-1910

[43] A variational mode decompoisition approach for analysis and forecasting of economic and financial time series [J].

Lahmiri, Salim .

EXPERT SYSTEMS WITH APPLICATIONS, 2016, 55 :268-273

[44] Intraday stock price forecasting based on variational mode decomposition [J].

Lahmiri, Salim .

JOURNAL OF COMPUTATIONAL SCIENCE, 2016, 12 :23-27

[45] Long memory in international financial markets trends and short movements during 2008 financial crisis based on variational mode decomposition and detrended fluctuation analysis [J].

Lahmiri, Salim .

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2015, 437 :130-138

[46] Wavelet low- and high-frequency components as features for predicting stock prices with backpropagation neural networks [J].

Lahmiri, Salim .

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2014, 26 (02) :218-227

[47] Automated detection of circinate exudates in retina digital images using empirical mode decomposition and the entropy and uniformity of the intrinsic mode functions [J].

Lahmiri, Salim ;

Boukadoum, Mounir .

BIOMEDICAL ENGINEERING-BIOMEDIZINISCHE TECHNIK, 2014, 59 (04) :357-366

[48] Multi-fluctuation nonlinear patterns of European financial markets based on adaptive filtering with application to family business, green, Islamic, common stocks, and comparison with Bitcoin, NASDAQ, and VIX [J].

Lahmri, Salim ;

Bekiros, Stelios ;

Bezzina, Frank .

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2020, 538

[49] Predicting the direction, maximum, minimum and closing prices of daily Bitcoin exchange rate using machine learning techniques [J].

Mallqui, Dennys C. A. ;

Fernandes, Ricardo A. S. .

APPLIED SOFT COMPUTING, 2019, 75 :596-606

[50] Predicting the Price of Bitcoin Using Machine Learning [J].

McNally, Sean ;

Roche, Jason ;

Caton, Simon .

2018 26TH EUROMICRO INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED, AND NETWORK-BASED PROCESSING (PDP 2018), 2018, :339-343

← 1 2 3 4 5 6 7 →