Please use this identifier to cite or link to this item:
Title: Forecasting of Bitcoin Illiquidity Using High-Dimensional and Textual Features
Authors: Sasani, F.,
Moghareh Dehkordi, M.,
Ebrahimi, Z.,
Dustmohammadloo, H.,
Bouzari, P.,
Ebrahimi, P.,
Lencsés, E.,
Fekete-Farkas, M.
Keywords: bitcoin hash rate
illiquidity prediction
IndRNN model
Issue Date: Jan-2024
Publisher: Multidisciplinary Digital Publishing Institute (MDPI)
Citation: Sasani, Faraz & Dehkordi, Mohammad & Ebrahimi, Zahra & Dustmohammadloo, Hakimeh & Bouzari, Parisa & Ebrahimi, Pejman & Lencsés, Enikő & Maria, Fekete Farkas. (2024). Forecasting of Bitcoin Illiquidity Using High-Dimensional and Textual Features. Computers. 13. 20. 10.3390/computers13010020.
Abstract: Liquidity is the ease of converting an asset (physical/digital) into cash or another asset without loss and is shown by the relationship between the time scale and the price scale of an investment. This article examines the illiquidity of Bitcoin (BTC). Bitcoin hash rate information was collected at three different time intervals; parallel to these data, textual information related to these intervals was collected from Twitter for each day. Due to the regression nature of illiquidity prediction, approaches based on recurrent networks were suggested. Seven approaches: ANN, SVM, SANN, LSTM, Simple RNN, GRU, and IndRNN, were tested on these data. To evaluate these approaches, three evaluation methods were used: random split (paper), random split (run) and linear split (run). The research results indicate that the IndRNN approach provided better results.
Description: This article is index by Scopus
ISSN: 2073431X
Appears in Collections:Journal Articles

Files in This Item:
File Description SizeFormat 
Forecasting of Bitcoin Illiquidity Using High-Dimensional and Textual Features.pdf8.65 MBAdobe PDFView/Open

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