No Cover Image

Journal article 157 views 13 downloads

Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods

Ahmed Bouteska, Mohammad Abedin, Petr Hajek, Kunpeng Yuan

International Review of Financial Analysis, Volume: 92, Start page: 103055

Swansea University Author: Mohammad Abedin

  • 65393_VoR.pdf

    PDF | Version of Record

    © 2023 The Authors. This is an open access article under the CC BY license.

    Download (2.75MB)

Check full text

DOI (Published version): 10.1016/j.irfa.2023.103055

Abstract

Cryptocurrency price forecasting is attracting considerable interest due to its crucial decision support role in investment strategies. Large fluctuations in non-stationary cryptocurrency prices motivate the urgent need for accurate forecasting models. The lack of seasonal effects and the need to me...

Full description

Published in: International Review of Financial Analysis
ISSN: 1057-5219
Published: Elsevier BV 2024
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa65393
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2024-01-01T22:42:09Z
last_indexed 2024-01-01T22:42:09Z
id cronfa65393
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>65393</id><entry>2024-01-01</entry><title>Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods</title><swanseaauthors><author><sid>4ed8c020eae0c9bec4f5d9495d86d415</sid><ORCID></ORCID><firstname>Mohammad</firstname><surname>Abedin</surname><name>Mohammad Abedin</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-01-01</date><deptcode>CBAE</deptcode><abstract>Cryptocurrency price forecasting is attracting considerable interest due to its crucial decision support role in investment strategies. Large fluctuations in non-stationary cryptocurrency prices motivate the urgent need for accurate forecasting models. The lack of seasonal effects and the need to meet a number of unrealistic requirements make it difficult to make accurate forecasts using traditional statistical methods, leaving machine learning, particularly ensemble and deep learning, as the best technology in the area of cryptocurrency price forecasting. This is the first work to provide a comprehensive comparative analysis of ensemble learning and deep learning forecasting models, examining their relative performance on various cryptocurrencies (Bitcoin, Ethereum, Ripple, and Litecoin) and exploring their potential trading applications. The results of this study reveal that gated recurrent unit, simple recurrent neural network, and LightGBM methods outperform other machine learning methods, as well as the naive buy-and-hold and random walk strategies. This can effectively guide investors in the cryptocurrency markets.</abstract><type>Journal Article</type><journal>International Review of Financial Analysis</journal><volume>92</volume><journalNumber/><paginationStart>103055</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1057-5219</issnPrint><issnElectronic/><keywords>Cryptocurrency; Bitcoin; Forecasting; Ensemble learning; Deep learning; Neural networks</keywords><publishedDay>1</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2024</publishedYear><publishedDate>2024-03-01</publishedDate><doi>10.1016/j.irfa.2023.103055</doi><url/><notes/><college>COLLEGE NANME</college><department>Management School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CBAE</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>This research paper was made possible by a grant from the Czech Sciences Foundation (No. 22-22586S).</funders><projectreference/><lastEdited>2024-05-31T13:09:44.0564066</lastEdited><Created>2024-01-01T22:38:46.3812850</Created><path><level id="1">Faculty of Humanities and Social Sciences</level><level id="2">School of Management - Accounting and Finance</level></path><authors><author><firstname>Ahmed</firstname><surname>Bouteska</surname><order>1</order></author><author><firstname>Mohammad</firstname><surname>Abedin</surname><orcid></orcid><order>2</order></author><author><firstname>Petr</firstname><surname>Hajek</surname><order>3</order></author><author><firstname>Kunpeng</firstname><surname>Yuan</surname><order>4</order></author></authors><documents><document><filename>65393__29793__bfa4a2c2112c46fda194063edfe8798a.pdf</filename><originalFilename>65393_VoR.pdf</originalFilename><uploaded>2024-03-21T16:03:52.9367568</uploaded><type>Output</type><contentLength>2881535</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2023 The Authors. This is an open access article under the CC BY license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 65393 2024-01-01 Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods 4ed8c020eae0c9bec4f5d9495d86d415 Mohammad Abedin Mohammad Abedin true false 2024-01-01 CBAE Cryptocurrency price forecasting is attracting considerable interest due to its crucial decision support role in investment strategies. Large fluctuations in non-stationary cryptocurrency prices motivate the urgent need for accurate forecasting models. The lack of seasonal effects and the need to meet a number of unrealistic requirements make it difficult to make accurate forecasts using traditional statistical methods, leaving machine learning, particularly ensemble and deep learning, as the best technology in the area of cryptocurrency price forecasting. This is the first work to provide a comprehensive comparative analysis of ensemble learning and deep learning forecasting models, examining their relative performance on various cryptocurrencies (Bitcoin, Ethereum, Ripple, and Litecoin) and exploring their potential trading applications. The results of this study reveal that gated recurrent unit, simple recurrent neural network, and LightGBM methods outperform other machine learning methods, as well as the naive buy-and-hold and random walk strategies. This can effectively guide investors in the cryptocurrency markets. Journal Article International Review of Financial Analysis 92 103055 Elsevier BV 1057-5219 Cryptocurrency; Bitcoin; Forecasting; Ensemble learning; Deep learning; Neural networks 1 3 2024 2024-03-01 10.1016/j.irfa.2023.103055 COLLEGE NANME Management School COLLEGE CODE CBAE Swansea University SU Library paid the OA fee (TA Institutional Deal) This research paper was made possible by a grant from the Czech Sciences Foundation (No. 22-22586S). 2024-05-31T13:09:44.0564066 2024-01-01T22:38:46.3812850 Faculty of Humanities and Social Sciences School of Management - Accounting and Finance Ahmed Bouteska 1 Mohammad Abedin 2 Petr Hajek 3 Kunpeng Yuan 4 65393__29793__bfa4a2c2112c46fda194063edfe8798a.pdf 65393_VoR.pdf 2024-03-21T16:03:52.9367568 Output 2881535 application/pdf Version of Record true © 2023 The Authors. This is an open access article under the CC BY license. true eng http://creativecommons.org/licenses/by/4.0/
title Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods
spellingShingle Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods
Mohammad Abedin
title_short Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods
title_full Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods
title_fullStr Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods
title_full_unstemmed Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods
title_sort Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods
author_id_str_mv 4ed8c020eae0c9bec4f5d9495d86d415
author_id_fullname_str_mv 4ed8c020eae0c9bec4f5d9495d86d415_***_Mohammad Abedin
author Mohammad Abedin
author2 Ahmed Bouteska
Mohammad Abedin
Petr Hajek
Kunpeng Yuan
format Journal article
container_title International Review of Financial Analysis
container_volume 92
container_start_page 103055
publishDate 2024
institution Swansea University
issn 1057-5219
doi_str_mv 10.1016/j.irfa.2023.103055
publisher Elsevier BV
college_str Faculty of Humanities and Social Sciences
hierarchytype
hierarchy_top_id facultyofhumanitiesandsocialsciences
hierarchy_top_title Faculty of Humanities and Social Sciences
hierarchy_parent_id facultyofhumanitiesandsocialsciences
hierarchy_parent_title Faculty of Humanities and Social Sciences
department_str School of Management - Accounting and Finance{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}School of Management - Accounting and Finance
document_store_str 1
active_str 0
description Cryptocurrency price forecasting is attracting considerable interest due to its crucial decision support role in investment strategies. Large fluctuations in non-stationary cryptocurrency prices motivate the urgent need for accurate forecasting models. The lack of seasonal effects and the need to meet a number of unrealistic requirements make it difficult to make accurate forecasts using traditional statistical methods, leaving machine learning, particularly ensemble and deep learning, as the best technology in the area of cryptocurrency price forecasting. This is the first work to provide a comprehensive comparative analysis of ensemble learning and deep learning forecasting models, examining their relative performance on various cryptocurrencies (Bitcoin, Ethereum, Ripple, and Litecoin) and exploring their potential trading applications. The results of this study reveal that gated recurrent unit, simple recurrent neural network, and LightGBM methods outperform other machine learning methods, as well as the naive buy-and-hold and random walk strategies. This can effectively guide investors in the cryptocurrency markets.
published_date 2024-03-01T13:09:43Z
_version_ 1800570020471767040
score 11.012678

Similar Items