A Ternary-Frequency Cryptocurrency Price Prediction Scheme by Ensemble of Clustering and Reconstructing Intrinsic Mode Functions based on CEEMDAN

doi:10.1016/j.eswa.2023.121008

機構典藏 > College of Business and Management > Graduate Institute & Department of Business Administration > Journal Article > Item 987654321/124325

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/124325

Title:	A Ternary-Frequency Cryptocurrency Price Prediction Scheme by Ensemble of Clustering and Reconstructing Intrinsic Mode Functions based on CEEMDAN
Authors:	Ting-Jen Chang;Tian-Shyug Lee;Chih-Te Yang;Chi-Jie Lu
Keywords:	Cryptocurrency;Bitcoin prices;CEEMDAN;Time series clustering;Ensemble;Multivariate adaptive regression splines
Date:	2023-07-22
Issue Date:	2023-08-02 12:05:16 (UTC+8)
Publisher:	PERGAMON-ELSEVIER SCIENCE LTD
Abstract:	Cryptocurrency, particularly Bitcoin, is a significant financial asset for investors, but predicting its price is challenging due to its volatile and erratic nature. In this study, we suggest a novel ternary-frequency (TF) prediction scheme for Bitcoin prices, which combines complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), a time series clustering method, and the reconstruction of intrinsic mode functions (IMFs). In the proposed scheme, CEEMDAN was utilized to decompose Bitcoin’s daily price into IMFs, then prototypes of time series clustering were used to construct robust ensemble clusters. The IMFs in the ensemble clusters were reconstructed into ensemble time series and then identified as three different frequencies, which were respectively used in a prediction model to generate different predicted values, and then aggregated to produce the final prediction results. To generate three different TF Bitcoin price prediction schemes, this study employed three prominent prediction algorithms: autoregressive integrated moving average with exogenous variables (ARIMAX), multivariate adaptive regression splines (MARS), and extreme gradient boosting (XGB); these resulted in three distinct models, named TF-ARIMAX, TF-MARS, and TF-XGB. Empirical results from the two daily Bitcoin and one daily Ethereum closing price datasets showed that the proposed TF prediction scheme outperformed other benchmark approaches. Moreover, among the three TF models, TF-MARS produced superior prediction accuracy compared to both TF-ARIMAX and TF-XGB models, and proved to be an effective alternative for cryptocurrency price prediction.
Relation:	Expert Systems with Applications 233,　121008
DOI:	10.1016/j.eswa.2023.121008
Appears in Collections:	[Graduate Institute & Department of Business Administration] Journal Article

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	103	View/Open

Loading...