Revolutionizing Bitcoin price forecasts: A comparative study of advanced hybrid deep learning architectures

•Hybrid deep learning model outperforms basic LSTM in Bitcoin forecasting.•NRBO-CNN-BiLSTM-Attention model cuts MAPE by over 50 %.•Significant accuracy in 5-day and 15-day Bitcoin price forecasts.•Model tested across multiple loss functions for robustness.•Suggests dataset restructuring to improve m...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Finance research letters Ročník 69; s. 106136
Hlavní autori: He, Xiangyi, Li, Yiwei, Li, Houjian
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Inc 01.11.2024
Predmet:
ISSN:1544-6123
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract •Hybrid deep learning model outperforms basic LSTM in Bitcoin forecasting.•NRBO-CNN-BiLSTM-Attention model cuts MAPE by over 50 %.•Significant accuracy in 5-day and 15-day Bitcoin price forecasts.•Model tested across multiple loss functions for robustness.•Suggests dataset restructuring to improve model performance. This paper employs a deep learning network with a comprehensive architecture to forecast Bitcoin prices, enhancing accuracy by integrating two meta-heuristic optimization algorithms, INFO and NRBO. Empirical results demonstrate that the hybrid model significantly outperforms the LSTM in both fit and predictive accuracy across in-sample and out-of-sample data. Notably, the NRBO-CNN-BiLSTM-Attention model substantially improves accuracy in 5-day and 15-day forecasts, reducing the MAPE by over 50 % compared to the LSTM model, thereby significantly enhancing overall predictive performance. The robustness of our results is supported by the MCS tests. Furthermore, strategically modifying time steps in data analysis optimizes model performance.
AbstractList •Hybrid deep learning model outperforms basic LSTM in Bitcoin forecasting.•NRBO-CNN-BiLSTM-Attention model cuts MAPE by over 50 %.•Significant accuracy in 5-day and 15-day Bitcoin price forecasts.•Model tested across multiple loss functions for robustness.•Suggests dataset restructuring to improve model performance. This paper employs a deep learning network with a comprehensive architecture to forecast Bitcoin prices, enhancing accuracy by integrating two meta-heuristic optimization algorithms, INFO and NRBO. Empirical results demonstrate that the hybrid model significantly outperforms the LSTM in both fit and predictive accuracy across in-sample and out-of-sample data. Notably, the NRBO-CNN-BiLSTM-Attention model substantially improves accuracy in 5-day and 15-day forecasts, reducing the MAPE by over 50 % compared to the LSTM model, thereby significantly enhancing overall predictive performance. The robustness of our results is supported by the MCS tests. Furthermore, strategically modifying time steps in data analysis optimizes model performance.
ArticleNumber 106136
Author He, Xiangyi
Li, Houjian
Li, Yiwei
Author_xml – sequence: 1
  givenname: Xiangyi
  orcidid: 0009-0009-1658-9845
  surname: He
  fullname: He, Xiangyi
  email: 202103260@stu.sicau.edu.cn
  organization: College of Economics, Sichuan Agricultural University, Wenjiang District, Chengdu 611130, China
– sequence: 2
  givenname: Yiwei
  orcidid: 0000-0003-2386-3055
  surname: Li
  fullname: Li, Yiwei
  email: yiwei.li@essex.ac.uk
  organization: Essex Business School, University of Essex, United Kingdom
– sequence: 3
  givenname: Houjian
  orcidid: 0000-0003-4852-8042
  surname: Li
  fullname: Li, Houjian
  email: 14159@sicau.edu.cn
  organization: College of Economics, Sichuan Agricultural University, Wenjiang District, Chengdu 611130, China
BookMark eNp9kMtOwzAQRb0oEm3hA9j5B1LsPJwEVqXiJVVCQrC2JvaYuqRxZbuRyteTqKxYdDWaxblX98zIpHMdEnLD2YIzLm63C-PbRcrSfPgFz8SETHmR54ngaXZJZiFsGUvLqhRT8v2OvWsP0brO_tjuiz7YqJzt6N5bhdQ4jwpCDHd0SZXb7cFDtD3SEA_6SJ2hoHvoFGq6OTbeaqoR97RF8N2YBl5tbEQVDx7DFbkw0Aa8_rtz8vn0-LF6SdZvz6-r5TpRWZrGpOIFMAaqMakuqrrUtcgbjU2RsQxqXVcMNRSaiaGqbLQxuVDAq6pUBQehdDYn_JSrvAvBo5HDmB34o-RMjobkVg6G5GhIngwNTPmPUTbCqCV6sO1Z8v5E4jCpt-hlUBZHJXZwF6V29gz9C1-giCg
CitedBy_id crossref_primary_10_1063_5_0269566
crossref_primary_10_1051_shsconf_202521802025
Cites_doi 10.1016/j.frl.2019.101386
10.1016/j.resourpol.2020.101666
10.1016/j.engappai.2023.107532
10.1016/j.infoecopol.2017.02.002
10.1016/j.econlet.2018.02.001
10.1016/j.frl.2022.103391
10.1016/j.najef.2021.101379
10.1016/j.techfore.2023.122938
10.1016/j.frl.2017.11.009
10.1007/s12197-020-09526-4
10.1007/s12599-017-0506-0
10.1016/j.energy.2018.03.099
10.1186/s40854-020-00176-3
10.1016/j.eswa.2021.114747
10.1016/j.eswa.2022.116516
10.1080/13504851.2014.916379
10.1016/j.dss.2016.12.001
10.1016/j.inffus.2023.101819
10.1016/j.asoc.2018.11.038
10.1016/j.econmod.2020.05.003
10.1016/j.energy.2011.05.004
10.1016/j.iref.2023.04.013
10.1016/j.geoderma.2017.06.020
10.1016/j.eswa.2022.116804
10.1109/ACCESS.2018.2841987
10.1016/j.frl.2022.103143
10.1016/j.engappai.2024.107991
10.1111/jofi.13119
10.1016/j.frl.2018.09.014
ContentType Journal Article
Copyright 2024 Elsevier Inc.
Copyright_xml – notice: 2024 Elsevier Inc.
DBID AAYXX
CITATION
DOI 10.1016/j.frl.2024.106136
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Business
ExternalDocumentID 10_1016_j_frl_2024_106136
S1544612324011656
GroupedDBID --K
--M
.~1
0R~
1B1
1~.
1~5
4.4
457
4G.
5VS
7-5
71M
8P~
AACTN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAPFB
AAQFI
AAXKI
AAXUO
ABMAC
ABXDB
ACDAQ
ACGFS
ACHQT
ACRLP
ACROA
ADBBV
ADEZE
ADFHU
ADMUD
AEBSH
AEKER
AEYQN
AFJKZ
AFKWA
AFTJW
AGHFR
AGTHC
AGUBO
AGYEJ
AIEXJ
AIIAU
AIKHN
AITUG
AJOXV
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AXJTR
AXLSJ
BKOJK
BLXMC
BZJEE
CS3
DU5
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FIRID
FNPLU
FYGXN
G-Q
GBLVA
HVGLF
HZ~
IHE
J1W
KOM
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
RIG
ROL
RPZ
SDF
SDG
SEB
SES
SEW
SPCBC
SSB
SSF
SSZ
T5K
ZU3
~G-
9DU
AATTM
AAYWO
AAYXX
ABJNI
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFPUW
AIGII
AIIUN
AKBMS
AKYEP
ANKPU
APXCP
CITATION
EFKBS
EFLBG
~HD
ID FETCH-LOGICAL-c322t-815a00acbf2d5897d964bdeb5303a9d980eda5d06dee7bdff46ca1887c51a6cd3
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001320127000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1544-6123
IngestDate Sat Nov 29 01:41:39 EST 2025
Tue Nov 18 21:19:00 EST 2025
Sat Nov 16 15:57:17 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Bitcoin price
Meta-heuristic optimization algorithms
Hybrid models
Price forecast
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c322t-815a00acbf2d5897d964bdeb5303a9d980eda5d06dee7bdff46ca1887c51a6cd3
ORCID 0000-0003-4852-8042
0000-0003-2386-3055
0009-0009-1658-9845
ParticipantIDs crossref_primary_10_1016_j_frl_2024_106136
crossref_citationtrail_10_1016_j_frl_2024_106136
elsevier_sciencedirect_doi_10_1016_j_frl_2024_106136
PublicationCentury 2000
PublicationDate 2024-11-01
PublicationDateYYYYMMDD 2024-11-01
PublicationDate_xml – month: 11
  year: 2024
  text: 2024-11-01
  day: 01
PublicationDecade 2020
PublicationTitle Finance research letters
PublicationYear 2024
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References Sowmya, Premkumar, Jangir (bib0032) 2024; 128
Risius, Spohrer (bib0031) 2017; 59
Ahmadianfar, Heidari, Noshadian, Chen, Gandomi (bib0002) 2022; 195
Ortu, Uras, Conversano, Bartolucci, Destefanis (bib0026) 2022; 198
Cheng, Tiwari, Khaled, Mahendru, Shahzad (bib0012) 2024; 198
Liu, Tsyvinski, Wu (bib0020) 2022; 77
Movagharnejad, Mehdizadeh, Banihashemi, Kordkheili (bib0024) 2011; 36
Phaladisailoed, Numnonda (bib0028) 2018
Baek, Elbeck (bib0005) 2015; 22
Mallqui, Fernandes (bib0022) 2019; 75
Zeng, Yang, Shen (bib0037) 2020; 90
Brauneis, Mestel (bib0007) 2018; 165
Pieters, Vivanco (bib0029) 2017; 39
Buchholz, Delaney, Warren, Parker (bib0008) 2012; 312
Nouir, Hamida (bib0025) 2023; 64
Malladi, Dheeriya (bib0021) 2021; 45
Patel, Kumar, Bouri, Iqbal (bib0027) 2023; 87
Li, Wang (bib0018) 2017; 95
Huang, Wang (bib0016) 2018; 151
Xia, Sang, He, Wang (bib0036) 2023; 52
Chen, Ma, Li, Wang, Li (bib0011) 2023; 97
Hakim das Neves (bib0014) 2020; 6
Hansen, Lunde, Nason (bib0015) 2005
Wang, Shen, Li (bib0034) 2022; 49
McNally, Roche, Caton (bib0023) 2018
Ahmed (bib0003) 2021; 57
Jareño, de la O González, Tolentino, Sierra (bib0017) 2020; 67
Troster, Tiwari, Shahbaz, Macedo (bib0033) 2019; 30
Chen, Pourghasemi, Kornejady, Zhang (bib0010) 2017; 305
Wang, Xie, Wen, Zhao (bib0035) 2019
Pyo, Lee (bib0030) 2020; 37
Aras (bib0004) 2021; 174
Feng, Wang, Zhang (bib0013) 2018; 26
Bâra, Oprea (bib0006) 2024; 133
Ahmad, Basheri, Iqbal, Rahim (bib0001) 2018; 6
Buchholz (10.1016/j.frl.2024.106136_bib0008) 2012; 312
Zeng (10.1016/j.frl.2024.106136_bib0037) 2020; 90
Troster (10.1016/j.frl.2024.106136_bib0033) 2019; 30
Ahmad (10.1016/j.frl.2024.106136_bib0001) 2018; 6
Malladi (10.1016/j.frl.2024.106136_bib0021) 2021; 45
Nouir (10.1016/j.frl.2024.106136_bib0025) 2023; 64
Feng (10.1016/j.frl.2024.106136_bib0013) 2018; 26
Ortu (10.1016/j.frl.2024.106136_bib0026) 2022; 198
Jareño (10.1016/j.frl.2024.106136_bib0017) 2020; 67
Wang (10.1016/j.frl.2024.106136_bib0035) 2019
Ahmed (10.1016/j.frl.2024.106136_bib0003) 2021; 57
Wang (10.1016/j.frl.2024.106136_bib0034) 2022; 49
Cheng (10.1016/j.frl.2024.106136_bib0012) 2024; 198
Risius (10.1016/j.frl.2024.106136_bib0031) 2017; 59
Patel (10.1016/j.frl.2024.106136_bib0027) 2023; 87
Hakim das Neves (10.1016/j.frl.2024.106136_bib0014) 2020; 6
Bâra (10.1016/j.frl.2024.106136_bib0006) 2024; 133
Liu (10.1016/j.frl.2024.106136_bib0020) 2022; 77
Movagharnejad (10.1016/j.frl.2024.106136_bib0024) 2011; 36
Huang (10.1016/j.frl.2024.106136_bib0016) 2018; 151
Pyo (10.1016/j.frl.2024.106136_bib0030) 2020; 37
Chen (10.1016/j.frl.2024.106136_bib0010) 2017; 305
Ahmadianfar (10.1016/j.frl.2024.106136_bib0002) 2022; 195
McNally (10.1016/j.frl.2024.106136_bib0023) 2018
Mallqui (10.1016/j.frl.2024.106136_bib0022) 2019; 75
Li (10.1016/j.frl.2024.106136_bib0018) 2017; 95
Pieters (10.1016/j.frl.2024.106136_bib0029) 2017; 39
Sowmya (10.1016/j.frl.2024.106136_bib0032) 2024; 128
Brauneis (10.1016/j.frl.2024.106136_bib0007) 2018; 165
Xia (10.1016/j.frl.2024.106136_bib0036) 2023; 52
Phaladisailoed (10.1016/j.frl.2024.106136_bib0028) 2018
Baek (10.1016/j.frl.2024.106136_bib0005) 2015; 22
Hansen (10.1016/j.frl.2024.106136_bib0015) 2005
Chen (10.1016/j.frl.2024.106136_bib0011) 2023; 97
Aras (10.1016/j.frl.2024.106136_bib0004) 2021; 174
References_xml – volume: 57
  year: 2021
  ident: bib0003
  article-title: Stock market reactions to upside and downside volatility of Bitcoin: a quantile analysis
  publication-title: N. Am. J. Econ. Finance
– volume: 52
  year: 2023
  ident: bib0036
  article-title: The role of uncertainty index in forecasting volatility of Bitcoin: fresh evidence from GARCH-MIDAS approach
  publication-title: Financ. Res. Lett.
– volume: 97
  year: 2023
  ident: bib0011
  article-title: Long sequence time-series forecasting with deep learning: a survey
  publication-title: Inf. Fusion
– volume: 198
  year: 2022
  ident: bib0026
  article-title: On technical trading and social media indicators for cryptocurrency price classification through deep learning
  publication-title: Expert. Syst. Appl.
– volume: 59
  start-page: 385
  year: 2017
  end-page: 409
  ident: bib0031
  article-title: A blockchain research framework: what we (don't) know, where we go from here, and how we will get there
  publication-title: Bus. Inf. Syst. Eng.
– volume: 87
  start-page: 143
  year: 2023
  end-page: 162
  ident: bib0027
  article-title: Spillovers between green and dirty cryptocurrencies and socially responsible investments around the war in Ukraine
  publication-title: Int. Rev. Econ. Financ.
– volume: 49
  year: 2022
  ident: bib0034
  article-title: Aggregate investor attention and Bitcoin return: the long short-term memory networks perspective
  publication-title: Financ. Res. Lett.
– volume: 128
  year: 2024
  ident: bib0032
  article-title: Newton-Raphson-based optimizer: a new population-based metaheuristic algorithm for continuous optimization problems
  publication-title: Eng. Appl. Artif. Intell.
– volume: 22
  start-page: 30
  year: 2015
  end-page: 34
  ident: bib0005
  article-title: Bitcoins as an investment or speculative vehicle? A first look
  publication-title: Appl. Econ. Lett.
– volume: 312
  start-page: 2
  year: 2012
  end-page: 48
  ident: bib0008
  article-title: Bits and bets, information, price volatility, and demand for Bitcoin
  publication-title: Economics
– volume: 165
  start-page: 58
  year: 2018
  end-page: 61
  ident: bib0007
  article-title: Price discovery of cryptocurrencies: Bitcoin and beyond
  publication-title: Econ. Lett.
– start-page: 506
  year: 2018
  end-page: 511
  ident: bib0028
  article-title: Machine learning models comparison for bitcoin price prediction
  publication-title: 2018 10th International Conference on Information Technology and Electrical Engineering (ICITEE)
– volume: 37
  year: 2020
  ident: bib0030
  article-title: Do FOMC and macroeconomic announcements affect Bitcoin prices?
  publication-title: Financ. Res. Lett.
– volume: 133
  year: 2024
  ident: bib0006
  article-title: An ensemble learning method for Bitcoin price prediction based on volatility indicators and trend
  publication-title: Eng. Appl. Artif. Intell.
– volume: 77
  start-page: 1133
  year: 2022
  end-page: 1177
  ident: bib0020
  article-title: Common risk factors in cryptocurrency
  publication-title: J. Finance
– start-page: 2005
  year: 2005
  end-page: 2007
  ident: bib0015
  publication-title: Model Confidence Sets for Forecasting Models, Federal Reserve Bank of Atlanta. Working paper
– volume: 305
  start-page: 314
  year: 2017
  end-page: 327
  ident: bib0010
  article-title: Landslide spatial modeling: introducing new ensembles of ANN, MaxEnt, and SVM machine learning techniques
  publication-title: Geoderma
– volume: 26
  start-page: 63
  year: 2018
  end-page: 70
  ident: bib0013
  article-title: Informed trading in the Bitcoin market
  publication-title: Financ. Res. Lett.
– volume: 36
  start-page: 3979
  year: 2011
  end-page: 3984
  ident: bib0024
  article-title: Forecasting the differences between various commercial oil prices in the Persian Gulf region by neural network
  publication-title: Energy
– volume: 45
  start-page: 75
  year: 2021
  end-page: 94
  ident: bib0021
  article-title: Time series analysis of cryptocurrency returns and volatilities
  publication-title: J. Econ. Financ.
– volume: 90
  start-page: 209
  year: 2020
  end-page: 220
  ident: bib0037
  article-title: Fancy Bitcoin and conventional financial assets: measuring market integration based on connectedness networks
  publication-title: Econ. Model.
– volume: 151
  start-page: 875
  year: 2018
  end-page: 888
  ident: bib0016
  article-title: Global crude oil price prediction and synchronization based accuracy evaluation using random wavelet neural network
  publication-title: Energy
– volume: 198
  year: 2024
  ident: bib0012
  article-title: Forecasting Bitcoin prices using artificial intelligence: Combination of ML, SARIMA, and Facebook Prophet models
  publication-title: Technol. Forecast. Soc. Change
– start-page: 31
  year: 2019
  ident: bib0035
  article-title: When Bitcoin meets economic policy uncertainty (EPU): measuring risk spillover effect from EPU to Bitcoin
  publication-title: Financ. Res. Lett.
– volume: 39
  start-page: 1
  year: 2017
  end-page: 14
  ident: bib0029
  article-title: Financial regulations and price inconsistencies across Bitcoin markets
  publication-title: Inf. Econ. Pol.
– volume: 174
  year: 2021
  ident: bib0004
  article-title: Stacking hybrid GARCH models for forecasting Bitcoin volatility
  publication-title: Expert. Syst. Appl.
– volume: 195
  year: 2022
  ident: bib0002
  article-title: INFO: an efficient optimization algorithm based on weighted mean of vectors
  publication-title: Expert. Syst. Appl.
– volume: 67
  year: 2020
  ident: bib0017
  article-title: Bitcoin and gold price returns: a quantile regression and NARDL analysis
  publication-title: Resour. Policy.
– volume: 30
  start-page: 187
  year: 2019
  end-page: 193
  ident: bib0033
  article-title: Bitcoin returns and risk: a general GARCH and GAS analysis
  publication-title: Financ. Res. Lett.
– volume: 75
  start-page: 596
  year: 2019
  end-page: 606
  ident: bib0022
  article-title: Predicting the direction, maximum, minimum and closing prices of daily Bitcoin exchange rate using machine learning techniques
  publication-title: Appl. Soft. Comput.
– volume: 6
  start-page: 21
  year: 2020
  ident: bib0014
  article-title: Bitcoin pricing: impact of attractiveness variables
  publication-title: Financ. Innov.
– start-page: 339
  year: 2018
  end-page: 343
  ident: bib0023
  article-title: Predicting the price of bitcoin using machine learning
  publication-title: 2018 26th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)
– volume: 95
  start-page: 49
  year: 2017
  end-page: 60
  ident: bib0018
  article-title: The technology and economic determinants of cryptocurrency exchange rates: The case of Bitcoin
  publication-title: Decis. Support Syst.
– volume: 64
  year: 2023
  ident: bib0025
  article-title: How do economic policy uncertainty and geopolitical risk drive Bitcoin volatility?
  publication-title: Res. Int. Bus. Finance
– volume: 6
  start-page: 33789
  year: 2018
  end-page: 33795
  ident: bib0001
  article-title: Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection
  publication-title: IEEe Access.
– volume: 312
  start-page: 2
  issue: 1
  year: 2012
  ident: 10.1016/j.frl.2024.106136_bib0008
  article-title: Bits and bets, information, price volatility, and demand for Bitcoin
  publication-title: Economics
– volume: 64
  year: 2023
  ident: 10.1016/j.frl.2024.106136_bib0025
  article-title: How do economic policy uncertainty and geopolitical risk drive Bitcoin volatility?
  publication-title: Res. Int. Bus. Finance
– volume: 37
  year: 2020
  ident: 10.1016/j.frl.2024.106136_bib0030
  article-title: Do FOMC and macroeconomic announcements affect Bitcoin prices?
  publication-title: Financ. Res. Lett.
  doi: 10.1016/j.frl.2019.101386
– volume: 67
  year: 2020
  ident: 10.1016/j.frl.2024.106136_bib0017
  article-title: Bitcoin and gold price returns: a quantile regression and NARDL analysis
  publication-title: Resour. Policy.
  doi: 10.1016/j.resourpol.2020.101666
– volume: 128
  year: 2024
  ident: 10.1016/j.frl.2024.106136_bib0032
  article-title: Newton-Raphson-based optimizer: a new population-based metaheuristic algorithm for continuous optimization problems
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2023.107532
– volume: 39
  start-page: 1
  year: 2017
  ident: 10.1016/j.frl.2024.106136_bib0029
  article-title: Financial regulations and price inconsistencies across Bitcoin markets
  publication-title: Inf. Econ. Pol.
  doi: 10.1016/j.infoecopol.2017.02.002
– volume: 165
  start-page: 58
  year: 2018
  ident: 10.1016/j.frl.2024.106136_bib0007
  article-title: Price discovery of cryptocurrencies: Bitcoin and beyond
  publication-title: Econ. Lett.
  doi: 10.1016/j.econlet.2018.02.001
– volume: 52
  year: 2023
  ident: 10.1016/j.frl.2024.106136_bib0036
  article-title: The role of uncertainty index in forecasting volatility of Bitcoin: fresh evidence from GARCH-MIDAS approach
  publication-title: Financ. Res. Lett.
  doi: 10.1016/j.frl.2022.103391
– volume: 57
  year: 2021
  ident: 10.1016/j.frl.2024.106136_bib0003
  article-title: Stock market reactions to upside and downside volatility of Bitcoin: a quantile analysis
  publication-title: N. Am. J. Econ. Finance
  doi: 10.1016/j.najef.2021.101379
– volume: 198
  year: 2024
  ident: 10.1016/j.frl.2024.106136_bib0012
  article-title: Forecasting Bitcoin prices using artificial intelligence: Combination of ML, SARIMA, and Facebook Prophet models
  publication-title: Technol. Forecast. Soc. Change
  doi: 10.1016/j.techfore.2023.122938
– volume: 26
  start-page: 63
  year: 2018
  ident: 10.1016/j.frl.2024.106136_bib0013
  article-title: Informed trading in the Bitcoin market
  publication-title: Financ. Res. Lett.
  doi: 10.1016/j.frl.2017.11.009
– volume: 45
  start-page: 75
  issue: 1
  year: 2021
  ident: 10.1016/j.frl.2024.106136_bib0021
  article-title: Time series analysis of cryptocurrency returns and volatilities
  publication-title: J. Econ. Financ.
  doi: 10.1007/s12197-020-09526-4
– start-page: 31
  year: 2019
  ident: 10.1016/j.frl.2024.106136_bib0035
  article-title: When Bitcoin meets economic policy uncertainty (EPU): measuring risk spillover effect from EPU to Bitcoin
  publication-title: Financ. Res. Lett.
– volume: 59
  start-page: 385
  year: 2017
  ident: 10.1016/j.frl.2024.106136_bib0031
  article-title: A blockchain research framework: what we (don't) know, where we go from here, and how we will get there
  publication-title: Bus. Inf. Syst. Eng.
  doi: 10.1007/s12599-017-0506-0
– volume: 151
  start-page: 875
  year: 2018
  ident: 10.1016/j.frl.2024.106136_bib0016
  article-title: Global crude oil price prediction and synchronization based accuracy evaluation using random wavelet neural network
  publication-title: Energy
  doi: 10.1016/j.energy.2018.03.099
– volume: 6
  start-page: 21
  issue: 1
  year: 2020
  ident: 10.1016/j.frl.2024.106136_bib0014
  article-title: Bitcoin pricing: impact of attractiveness variables
  publication-title: Financ. Innov.
  doi: 10.1186/s40854-020-00176-3
– volume: 174
  year: 2021
  ident: 10.1016/j.frl.2024.106136_bib0004
  article-title: Stacking hybrid GARCH models for forecasting Bitcoin volatility
  publication-title: Expert. Syst. Appl.
  doi: 10.1016/j.eswa.2021.114747
– volume: 195
  year: 2022
  ident: 10.1016/j.frl.2024.106136_bib0002
  article-title: INFO: an efficient optimization algorithm based on weighted mean of vectors
  publication-title: Expert. Syst. Appl.
  doi: 10.1016/j.eswa.2022.116516
– volume: 22
  start-page: 30
  issue: 1
  year: 2015
  ident: 10.1016/j.frl.2024.106136_bib0005
  article-title: Bitcoins as an investment or speculative vehicle? A first look
  publication-title: Appl. Econ. Lett.
  doi: 10.1080/13504851.2014.916379
– volume: 95
  start-page: 49
  year: 2017
  ident: 10.1016/j.frl.2024.106136_bib0018
  article-title: The technology and economic determinants of cryptocurrency exchange rates: The case of Bitcoin
  publication-title: Decis. Support Syst.
  doi: 10.1016/j.dss.2016.12.001
– volume: 97
  year: 2023
  ident: 10.1016/j.frl.2024.106136_bib0011
  article-title: Long sequence time-series forecasting with deep learning: a survey
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2023.101819
– volume: 75
  start-page: 596
  year: 2019
  ident: 10.1016/j.frl.2024.106136_bib0022
  article-title: Predicting the direction, maximum, minimum and closing prices of daily Bitcoin exchange rate using machine learning techniques
  publication-title: Appl. Soft. Comput.
  doi: 10.1016/j.asoc.2018.11.038
– volume: 90
  start-page: 209
  year: 2020
  ident: 10.1016/j.frl.2024.106136_bib0037
  article-title: Fancy Bitcoin and conventional financial assets: measuring market integration based on connectedness networks
  publication-title: Econ. Model.
  doi: 10.1016/j.econmod.2020.05.003
– start-page: 506
  year: 2018
  ident: 10.1016/j.frl.2024.106136_bib0028
  article-title: Machine learning models comparison for bitcoin price prediction
– volume: 36
  start-page: 3979
  issue: 7
  year: 2011
  ident: 10.1016/j.frl.2024.106136_bib0024
  article-title: Forecasting the differences between various commercial oil prices in the Persian Gulf region by neural network
  publication-title: Energy
  doi: 10.1016/j.energy.2011.05.004
– start-page: 2005
  year: 2005
  ident: 10.1016/j.frl.2024.106136_bib0015
– start-page: 339
  year: 2018
  ident: 10.1016/j.frl.2024.106136_bib0023
  article-title: Predicting the price of bitcoin using machine learning
– volume: 87
  start-page: 143
  year: 2023
  ident: 10.1016/j.frl.2024.106136_bib0027
  article-title: Spillovers between green and dirty cryptocurrencies and socially responsible investments around the war in Ukraine
  publication-title: Int. Rev. Econ. Financ.
  doi: 10.1016/j.iref.2023.04.013
– volume: 305
  start-page: 314
  year: 2017
  ident: 10.1016/j.frl.2024.106136_bib0010
  article-title: Landslide spatial modeling: introducing new ensembles of ANN, MaxEnt, and SVM machine learning techniques
  publication-title: Geoderma
  doi: 10.1016/j.geoderma.2017.06.020
– volume: 198
  year: 2022
  ident: 10.1016/j.frl.2024.106136_bib0026
  article-title: On technical trading and social media indicators for cryptocurrency price classification through deep learning
  publication-title: Expert. Syst. Appl.
  doi: 10.1016/j.eswa.2022.116804
– volume: 6
  start-page: 33789
  year: 2018
  ident: 10.1016/j.frl.2024.106136_bib0001
  article-title: Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection
  publication-title: IEEe Access.
  doi: 10.1109/ACCESS.2018.2841987
– volume: 49
  year: 2022
  ident: 10.1016/j.frl.2024.106136_bib0034
  article-title: Aggregate investor attention and Bitcoin return: the long short-term memory networks perspective
  publication-title: Financ. Res. Lett.
  doi: 10.1016/j.frl.2022.103143
– volume: 133
  year: 2024
  ident: 10.1016/j.frl.2024.106136_bib0006
  article-title: An ensemble learning method for Bitcoin price prediction based on volatility indicators and trend
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2024.107991
– volume: 77
  start-page: 1133
  issue: 2
  year: 2022
  ident: 10.1016/j.frl.2024.106136_bib0020
  article-title: Common risk factors in cryptocurrency
  publication-title: J. Finance
  doi: 10.1111/jofi.13119
– volume: 30
  start-page: 187
  year: 2019
  ident: 10.1016/j.frl.2024.106136_bib0033
  article-title: Bitcoin returns and risk: a general GARCH and GAS analysis
  publication-title: Financ. Res. Lett.
  doi: 10.1016/j.frl.2018.09.014
SSID ssj0027876
Score 2.327137
Snippet •Hybrid deep learning model outperforms basic LSTM in Bitcoin forecasting.•NRBO-CNN-BiLSTM-Attention model cuts MAPE by over 50 %.•Significant accuracy in...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 106136
SubjectTerms Bitcoin price
Hybrid models
Meta-heuristic optimization algorithms
Price forecast
Title Revolutionizing Bitcoin price forecasts: A comparative study of advanced hybrid deep learning architectures
URI https://dx.doi.org/10.1016/j.frl.2024.106136
Volume 69
WOSCitedRecordID wos001320127000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 1544-6123
  databaseCode: AIEXJ
  dateStart: 20040301
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0027876
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FFKFeEE_R8tAeOFG5shM_1r0FVBRQVSEoUjhZ9s5u6xA5UeymCb-e2ZfrhocAiYtlrbxra7_x7OzszDeEvASJqpEV4KHmk14IqaK8jQKvSANcH6Sqj6Qp80-S01M2maQfer0TlwuzmiVVxdbrdPFfocY2BFulzv4F3O2g2ID3CDpeEXa8_hHwH8XKjl9-U36A12XD5ypWXNEHqahCwfO6qU1KOu-Qf9eOX7qNC7jYqHyuAxBi4cpLnB90jx7qrm1rSv2qMizWlTLTqUKt0T7WvtMJyuP5pmwDgXQ0wZfySmw1jeeXUye61isxCG16Xusqc-kyN6I5FfOPp_heuurXVGr5QZMbp8L0UC7VAdEgPFR71-EWa7Zehz-pYWNtGhoyoVtkZ5BEKeuTndG748n76w0408UG289wp9w63m_rRT-3Uzq2x9k9ctduGujIgH2f9ET1gNxxOQsPydctzKnFnGrMaYv5ER3RDuJUI07nkjrEqUGcKsSpQ5zeQPwR-fz2-OzN2LNVNDyOyrrxWBDlvp_zQg4gYmmCv2NYgCgiNF7yFFLmC8gj8GMcOilAyjDmeYBrD4-CPOYwfEz61bwSTwiNkxiGSQScMQgDEIyzIgiAgx9KLn1_j_huzjJuKeZVpZNZ5mIJpxlOc6amOTPTvEdetV0Whl_ldw-HDojMGojG8MtQan7dbf_fuj0lu9eS_Yz0m-WleE5u81VT1ssXVra-A4D_jdo
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Revolutionizing+Bitcoin+price+forecasts%3A+A+comparative+study+of+advanced+hybrid+deep+learning+architectures&rft.jtitle=Finance+research+letters&rft.au=He%2C+Xiangyi&rft.au=Li%2C+Yiwei&rft.au=Li%2C+Houjian&rft.date=2024-11-01&rft.pub=Elsevier+Inc&rft.issn=1544-6123&rft.volume=69&rft_id=info:doi/10.1016%2Fj.frl.2024.106136&rft.externalDocID=S1544612324011656
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1544-6123&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1544-6123&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1544-6123&client=summon