Galformer: a transformer with generative decoding and a hybrid loss function for multi-step stock market index prediction

The prediction of stock market fluctuations is crucial for decision-making in various financial fields. Deep learning algorithms have demonstrated outstanding performance in stock market index prediction. Recent research has also highlighted the potential of the Transformer model in enhancing predic...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Scientific reports Ročník 14; číslo 1; s. 23762 - 18
Hlavní autoři:	Ji, Yi, Luo, Yuxuan, Lu, Aixia, Xia, Duanyang, Yang, Lixia, Wee-Chung Liew, Alan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	London Nature Publishing Group UK 10.10.2024 Nature Publishing Group Nature Portfolio
Témata:	639/166 639/705 Accuracy Algorithms Decision making Deep learning Experiments Forecasting Galformer Humanities and Social Sciences multidisciplinary Natural language processing Neural networks Predictions Science Science (multidisciplinary) Securities markets Stock exchanges Stock index prediction Stock market indexes Time series Transformer Trends Deep learning Transformer Stock index prediction Galformer
ISSN:	2045-2322, 2045-2322
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	The prediction of stock market fluctuations is crucial for decision-making in various financial fields. Deep learning algorithms have demonstrated outstanding performance in stock market index prediction. Recent research has also highlighted the potential of the Transformer model in enhancing prediction accuracy. However, the Transformer faces challenges in multi-step stock market forecasting, including limitations in inference speed for long sequence prediction and the inadequacy of traditional loss functions to capture the characteristics of noisy, nonlinear stock history data. To address these issues, we introduce an innovative transformer-based model with generative decoding and a hybrid loss function, named “Galformer,” tailored for the multi-step prediction of stock market indices. Galformer possesses two distinctive characteristics: (1) a novel generative style decoder that predicts long time-series sequences in a single forward operation, significantly boosting the speed of predicting long sequences; (2) a novel loss function that combines quantitative error and trend accuracy of the predicted results, providing feedback and optimizing the transformer-based model. Experimental results on four typical stock market indices, namely the CSI 300 Index, S&P 500 Index, Dow Jones Industrial Average Index (DJI), and Nasdaq Composite Index (IXIC), affirm that Galformer outperforms other classical methods, effectively optimizing the Transformer model for stock market prediction.
AbstractList	The prediction of stock market fluctuations is crucial for decision-making in various financial fields. Deep learning algorithms have demonstrated outstanding performance in stock market index prediction. Recent research has also highlighted the potential of the Transformer model in enhancing prediction accuracy. However, the Transformer faces challenges in multi-step stock market forecasting, including limitations in inference speed for long sequence prediction and the inadequacy of traditional loss functions to capture the characteristics of noisy, nonlinear stock history data. To address these issues, we introduce an innovative transformer-based model with generative decoding and a hybrid loss function, named "Galformer," tailored for the multi-step prediction of stock market indices. Galformer possesses two distinctive characteristics: (1) a novel generative style decoder that predicts long time-series sequences in a single forward operation, significantly boosting the speed of predicting long sequences; (2) a novel loss function that combines quantitative error and trend accuracy of the predicted results, providing feedback and optimizing the transformer-based model. Experimental results on four typical stock market indices, namely the CSI 300 Index, S&P 500 Index, Dow Jones Industrial Average Index (DJI), and Nasdaq Composite Index (IXIC), affirm that Galformer outperforms other classical methods, effectively optimizing the Transformer model for stock market prediction. The prediction of stock market fluctuations is crucial for decision-making in various financial fields. Deep learning algorithms have demonstrated outstanding performance in stock market index prediction. Recent research has also highlighted the potential of the Transformer model in enhancing prediction accuracy. However, the Transformer faces challenges in multi-step stock market forecasting, including limitations in inference speed for long sequence prediction and the inadequacy of traditional loss functions to capture the characteristics of noisy, nonlinear stock history data. To address these issues, we introduce an innovative transformer-based model with generative decoding and a hybrid loss function, named "Galformer," tailored for the multi-step prediction of stock market indices. Galformer possesses two distinctive characteristics: (1) a novel generative style decoder that predicts long time-series sequences in a single forward operation, significantly boosting the speed of predicting long sequences; (2) a novel loss function that combines quantitative error and trend accuracy of the predicted results, providing feedback and optimizing the transformer-based model. Experimental results on four typical stock market indices, namely the CSI 300 Index, S&P 500 Index, Dow Jones Industrial Average Index (DJI), and Nasdaq Composite Index (IXIC), affirm that Galformer outperforms other classical methods, effectively optimizing the Transformer model for stock market prediction.The prediction of stock market fluctuations is crucial for decision-making in various financial fields. Deep learning algorithms have demonstrated outstanding performance in stock market index prediction. Recent research has also highlighted the potential of the Transformer model in enhancing prediction accuracy. However, the Transformer faces challenges in multi-step stock market forecasting, including limitations in inference speed for long sequence prediction and the inadequacy of traditional loss functions to capture the characteristics of noisy, nonlinear stock history data. To address these issues, we introduce an innovative transformer-based model with generative decoding and a hybrid loss function, named "Galformer," tailored for the multi-step prediction of stock market indices. Galformer possesses two distinctive characteristics: (1) a novel generative style decoder that predicts long time-series sequences in a single forward operation, significantly boosting the speed of predicting long sequences; (2) a novel loss function that combines quantitative error and trend accuracy of the predicted results, providing feedback and optimizing the transformer-based model. Experimental results on four typical stock market indices, namely the CSI 300 Index, S&P 500 Index, Dow Jones Industrial Average Index (DJI), and Nasdaq Composite Index (IXIC), affirm that Galformer outperforms other classical methods, effectively optimizing the Transformer model for stock market prediction. Abstract The prediction of stock market fluctuations is crucial for decision-making in various financial fields. Deep learning algorithms have demonstrated outstanding performance in stock market index prediction. Recent research has also highlighted the potential of the Transformer model in enhancing prediction accuracy. However, the Transformer faces challenges in multi-step stock market forecasting, including limitations in inference speed for long sequence prediction and the inadequacy of traditional loss functions to capture the characteristics of noisy, nonlinear stock history data. To address these issues, we introduce an innovative transformer-based model with generative decoding and a hybrid loss function, named “Galformer,” tailored for the multi-step prediction of stock market indices. Galformer possesses two distinctive characteristics: (1) a novel generative style decoder that predicts long time-series sequences in a single forward operation, significantly boosting the speed of predicting long sequences; (2) a novel loss function that combines quantitative error and trend accuracy of the predicted results, providing feedback and optimizing the transformer-based model. Experimental results on four typical stock market indices, namely the CSI 300 Index, S&P 500 Index, Dow Jones Industrial Average Index (DJI), and Nasdaq Composite Index (IXIC), affirm that Galformer outperforms other classical methods, effectively optimizing the Transformer model for stock market prediction.
ArticleNumber	23762
Author	Ji, Yi Xia, Duanyang Yang, Lixia Luo, Yuxuan Lu, Aixia Wee-Chung Liew, Alan
Author_xml	– sequence: 1 givenname: Yi surname: Ji fullname: Ji, Yi organization: School of Electrical Information Engineering, Jiangsu University – sequence: 2 givenname: Yuxuan surname: Luo fullname: Luo, Yuxuan email: 2222107005@stmail.ujs.edu.cn organization: School of Electrical Information Engineering, Jiangsu University – sequence: 3 givenname: Aixia surname: Lu fullname: Lu, Aixia organization: School of Electrical Information Engineering, Jiangsu University – sequence: 4 givenname: Duanyang surname: Xia fullname: Xia, Duanyang organization: School of Electrical Information Engineering, Jiangsu University – sequence: 5 givenname: Lixia surname: Yang fullname: Yang, Lixia organization: School of Electronic Information Engineering, Anhui University – sequence: 6 givenname: Alan surname: Wee-Chung Liew fullname: Wee-Chung Liew, Alan organization: School of Information and Communication Technology, Griffith University
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/39390029$$D View this record in MEDLINE/PubMed
BookMark	eNp9kk1v1DAQhi1UREvpH-CALHHhEvBHnMTcUAWlUiUucLb8Mdl6m7UX2ynsv8dNSkE91D54PHre8XhmXqKjEAMg9JqS95Tw4UNuqZBDQ1jb9Iy0ouHP0MliMM7Y0X_2MTrLeUvqEky2VL5Ax1xySQiTJ-hwoacxph2kj1jjknTI6xX_8uUabyBA0sXfAnZgo_Nhg3VwFb0-mOQdnmLOeJyDLT4GXKV4N0_FN7nAHucS7Q3e6XQDBfvg4DfeJ3B-gV-h56OeMpzdn6fox5fP38-_NlffLi7PP101th1EaSypewBJWjYSMAPhRgPteibF2HFHHJFspNqJTpAeBltdVJiudYMdByIMP0WXa1wX9Vbtk6_5HFTUXi2OmDZKp-LtBKptwRhGGKOat0RKLayRnewdN72hZKyx3q2x9in-nCEXtfPZwjTpAHHOilMqBKE1pYq-fYRu45xC_elCMd6TrqvUm3tqNjtwD-n9bVAF2ArYVCudYHxAKFF3g6DWQVB1ENQyCIpX0fBIZH3Rd0WvDfbT01K-SnN9J2wg_Uv7CdUfzzfGuQ
CitedBy_id	crossref_primary_10_1007_s00521_025_11395_z crossref_primary_10_1016_j_asoc_2025_113783 crossref_primary_10_1007_s13042_025_02740_8 crossref_primary_10_1016_j_iswa_2025_200564 crossref_primary_10_1016_j_eswa_2025_128573 crossref_primary_10_3390_math13172762
Cites_doi	10.1038/s41467-020-19266-y 10.1016/j.physa.2015.12.017 10.1016/j.knosys.2018.10.034 10.1198/jasa.2007.s209 10.1016/j.jclepro.2018.10.128 10.1371/journal.pone.0180944 10.1016/j.eswa.2016.02.006 10.1007/s00607-019-00773-w 10.1016/j.eswa.2021.115537 10.1016/j.dss.2010.08.028 10.1016/j.procs.2019.01.256 10.1109/ACCESS.2021.3056713 10.3115/v1/W14-4012 10.1609/aaai.v33i01.33016706 10.1109/ICACCI.2017.8126078 10.1098/rsta.2020.0209 10.1109/ICMLC56445.2022.9941330 10.1109/SIU53274.2021.9477814
ContentType	Journal Article
Copyright	The Author(s) 2024 2024. The Author(s). The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: The Author(s) 2024 – notice: 2024. The Author(s). – notice: The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	C6C AAYXX CITATION NPM 3V. 7X5 7X7 7XB 88A 88E 88I 8FE 8FH 8FI 8FJ 8FK ABUWG AEUYN AFKRA AZQEC BBNVY BENPR BEZIV BHPHI CCPQU DWQXO FYUFA GHDGH GNUQQ HCIFZ K6~ K9. LK8 M0S M1P M2P M7P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI PRINS Q9U 7X8 DOA
DOI	10.1038/s41598-024-72045-3
DatabaseName	Springer Nature OA Free Journals CrossRef PubMed ProQuest Central (Corporate) Entrepreneurship Database Health & Medical Collection ProQuest Central (purchase pre-March 2016) Biology Database (Alumni Edition) Medical Database (Alumni Edition) Science Database (Alumni Edition) ProQuest SciTech Collection ProQuest Natural Science Collection Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest One Sustainability ProQuest Central UK/Ireland ProQuest Central Essentials - QC Biological Science Collection ProQuest Central Business Premium Collection Natural Science Collection ProQuest One ProQuest Central ProQuest Health & Medical Collection Health Research Premium Collection (Alumni) ProQuest Central Student SciTech Premium Collection ProQuest Business Collection ProQuest Health & Medical Complete (Alumni) ProQuest Biological Science Collection ProQuest Health & Medical Collection Medical Database Science Database Biological Science Database ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic MEDLINE - Academic DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef PubMed Publicly Available Content Database ProQuest Central Student ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest One Health & Nursing ProQuest Natural Science Collection ProQuest Central China ProQuest Biology Journals (Alumni Edition) ProQuest Central ProQuest One Applied & Life Sciences ProQuest One Sustainability ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) Natural Science Collection ProQuest Central Korea Health & Medical Research Collection Biological Science Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest Entrepreneurship Business Premium Collection ProQuest Science Journals (Alumni Edition) ProQuest Biological Science Collection ProQuest Central Basic ProQuest Science Journals ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) Biological Science Database ProQuest SciTech Collection ProQuest Business Collection ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic
DatabaseTitleList	PubMed MEDLINE - Academic Publicly Available Content Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: ProQuest - Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Biology
EISSN	2045-2322
EndPage	18
ExternalDocumentID	oai_doaj_org_article_44ebb20221a34099a5cb9697d3b7b10f 39390029 10_1038_s41598_024_72045_3
Genre	Journal Article
GrantInformation_xml	– fundername: Postgraduate Research & Practice Innovation Program of Jiangsu Province grantid: SJCX23_2088 – fundername: the Collaborative Innovation Program of Universities in Anhui Province grantid: GXXT-2021-028 – fundername: the Natural Science Foundation of Anhui Province grantid: 2008085MF186
GroupedDBID	0R~ 3V. 4.4 53G 5VS 7X7 88A 88E 88I 8FE 8FH 8FI 8FJ AAFWJ AAJSJ AAKDD ABDBF ABUWG ACGFS ACSMW ACUHS ADBBV ADRAZ AENEX AEUYN AFKRA AJTQC ALIPV ALMA_UNASSIGNED_HOLDINGS AOIJS AZQEC BAWUL BBNVY BCNDV BENPR BHPHI BPHCQ BVXVI C6C CCPQU DIK DWQXO EBD EBLON EBS ESX FYUFA GNUQQ GROUPED_DOAJ GX1 HCIFZ HH5 HMCUK HYE KQ8 LK8 M0L M1P M2P M48 M7P M~E NAO OK1 PIMPY PQQKQ PROAC PSQYO RNT RNTTT RPM SNYQT UKHRP AASML AAYXX AFFHD AFPKN CITATION PHGZM PHGZT PJZUB PPXIY PQGLB NPM 7X5 7XB 8FK BEZIV K6~ K9. PKEHL PQEST PQUKI PRINS Q9U 7X8 PUEGO
ID	FETCH-LOGICAL-c485t-c0c0c8e9042f0eb803bae167295f63d0d092f1ad56507e8c3d015b64d8cf805b3
IEDL.DBID	DOA
ISICitedReferencesCount	6
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001337092300049&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2045-2322
IngestDate	Fri Oct 03 12:36:07 EDT 2025 Thu Oct 02 05:11:36 EDT 2025 Tue Oct 07 07:36:34 EDT 2025 Mon Jul 21 05:40:00 EDT 2025 Sat Nov 29 05:24:23 EST 2025 Tue Nov 18 20:58:51 EST 2025 Fri Feb 21 02:38:07 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	1
Keywords	Deep learning Transformer Stock index prediction Galformer
Language	English
License	2024. The Author(s).
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c485t-c0c0c8e9042f0eb803bae167295f63d0d092f1ad56507e8c3d015b64d8cf805b3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
OpenAccessLink	https://doaj.org/article/44ebb20221a34099a5cb9697d3b7b10f
PMID	39390029
PQID	3115237066
PQPubID	2041939
PageCount	18
ParticipantIDs	doaj_primary_oai_doaj_org_article_44ebb20221a34099a5cb9697d3b7b10f proquest_miscellaneous_3115501092 proquest_journals_3115237066 pubmed_primary_39390029 crossref_primary_10_1038_s41598_024_72045_3 crossref_citationtrail_10_1038_s41598_024_72045_3 springer_journals_10_1038_s41598_024_72045_3
PublicationCentury	2000
PublicationDate	2024-10-10
PublicationDateYYYYMMDD	2024-10-10
PublicationDate_xml	– month: 10 year: 2024 text: 2024-10-10 day: 10
PublicationDecade	2020
PublicationPlace	London
PublicationPlace_xml	– name: London – name: England
PublicationTitle	Scientific reports
PublicationTitleAbbrev	Sci Rep
PublicationTitleAlternate	Sci Rep
PublicationYear	2024
Publisher	Nature Publishing Group UK Nature Publishing Group Nature Portfolio
Publisher_xml	– name: Nature Publishing Group UK – name: Nature Publishing Group – name: Nature Portfolio
References	CR19 CR18 Long, Lu, Cui (CR21) 2019; 164 CR17 CR15 CR14 CR13 Jiang (CR10) 2021; 2021 Anagnostidis, Varsakelis, Emmanouilides (CR1) 2016; 447 CR11 Williams, Zipser (CR30) 1989; 1989 Di Persio, Honchar (CR5) 2016; 10 Zhang, Zhong, Dong, Wang, Wang (CR8) 2019; 147 CR2 Li, Ni, Chang (CR9) 2020; 102 Bao, Yue, Rao (CR7) 2017; 12 Huang, Shen, Liu (CR12) 2019; 209 Goodfellow, Bengio, Courville, Bengio (CR24) 2016 CR6 Cavalcante, Brasileiro, Souza, Nobrega, Oliveira (CR4) 2016; 55 Tetko, Karpov, Van Deursen, Godin (CR16) 2020; 11 Tsai, Hsiao (CR3) 2010; 50 CR29 CR28 CR27 CR26 CR25 CR23 CR22 Lund (CR20) 2007; 102 RC Cavalcante (72045_CR4) 2016; 55 R Lund (72045_CR20) 2007; 102 RJ Williams (72045_CR30) 1989; 1989 Y Li (72045_CR9) 2020; 102 72045_CR15 72045_CR17 72045_CR18 72045_CR11 72045_CR13 P Anagnostidis (72045_CR1) 2016; 447 72045_CR14 K Zhang (72045_CR8) 2019; 147 Y Huang (72045_CR12) 2019; 209 C-F Tsai (72045_CR3) 2010; 50 L Di Persio (72045_CR5) 2016; 10 W Bao (72045_CR7) 2017; 12 72045_CR19 I Goodfellow (72045_CR24) 2016 72045_CR26 72045_CR27 72045_CR6 72045_CR28 72045_CR29 72045_CR22 72045_CR23 72045_CR2 W Long (72045_CR21) 2019; 164 W Jiang (72045_CR10) 2021; 2021 IV Tetko (72045_CR16) 2020; 11 72045_CR25
References_xml	– volume: 11 start-page: 1 year: 2020 end-page: 11 ident: CR16 article-title: State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis publication-title: Nat. Commun. doi: 10.1038/s41467-020-19266-y – ident: CR22 – ident: CR18 – ident: CR14 – ident: CR2 – volume: 447 start-page: 116 year: 2016 end-page: 128 ident: CR1 article-title: Has the 2008 financialcrisis affected stock market efficiency? The case of eurozone publication-title: Phys. A doi: 10.1016/j.physa.2015.12.017 – volume: 164 start-page: 163 year: 2019 end-page: 173 ident: CR21 article-title: Deep learning-based feature engineering for stock price movement prediction publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2018.10.034 – volume: 102 start-page: 1079 issue: 479 year: 2007 ident: CR20 article-title: Time series analysis and its applications: With r examples publication-title: J. Am. Stat. Assoc. doi: 10.1198/jasa.2007.s209 – ident: CR6 – ident: CR29 – volume: 209 start-page: 415 year: 2019 end-page: 423 ident: CR12 article-title: Grey relational analysis, principal component analysis and forecasting of carbon emissions based on long short-term memory in China publication-title: J. Clean. Prod. doi: 10.1016/j.jclepro.2018.10.128 – ident: CR25 – ident: CR27 – ident: CR23 – volume: 12 start-page: e0180944 year: 2017 ident: CR7 article-title: A deep learning framework for financial time series using stacked autoencoders and long-short term memory publication-title: PLoS One doi: 10.1371/journal.pone.0180944 – volume: 55 start-page: 194 year: 2016 end-page: 211 ident: CR4 article-title: Computational intelligence and financial markets: A survey and future directions publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2016.02.006 – year: 2016 ident: CR24 publication-title: Deep Learning – ident: CR19 – volume: 102 start-page: 1305 year: 2020 end-page: 1322 ident: CR9 article-title: Application of deep reinforcement learning in stock trading strategies and stock forecasting publication-title: Computing doi: 10.1007/s00607-019-00773-w – volume: 2021 start-page: 115537 year: 2021 ident: CR10 article-title: Applications of deep learning in stock market prediction: Recent progress publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2021.115537 – volume: 50 start-page: 258 year: 2010 end-page: 269 ident: CR3 article-title: Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches publication-title: Decis. Support Syst. doi: 10.1016/j.dss.2010.08.028 – ident: CR15 – volume: 147 start-page: 400 year: 2019 end-page: 406 ident: CR8 article-title: Stock market prediction based on generative adversarial network publication-title: Procedia Comput. Sci. doi: 10.1016/j.procs.2019.01.256 – ident: CR17 – ident: CR13 – ident: CR11 – volume: 1989 start-page: 1270 year: 1989 end-page: 1280 ident: CR30 article-title: A learning algorithm for continually running fully recurrent neural networks publication-title: Neural Comput. – volume: 10 start-page: 403 year: 2016 end-page: 413 ident: CR5 article-title: Artificial neural networks architectures for stock price prediction: Comparisons and applications publication-title: Int. J. Circ. Syst. Signal Process. – ident: CR28 – ident: CR26 – ident: 72045_CR11 – volume: 164 start-page: 163 year: 2019 ident: 72045_CR21 publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2018.10.034 – ident: 72045_CR13 – ident: 72045_CR26 doi: 10.1109/ACCESS.2021.3056713 – ident: 72045_CR28 – volume: 2021 start-page: 115537 year: 2021 ident: 72045_CR10 publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2021.115537 – volume: 10 start-page: 403 year: 2016 ident: 72045_CR5 publication-title: Int. J. Circ. Syst. Signal Process. – ident: 72045_CR19 – ident: 72045_CR27 doi: 10.3115/v1/W14-4012 – ident: 72045_CR15 doi: 10.1609/aaai.v33i01.33016706 – ident: 72045_CR6 doi: 10.1109/ICACCI.2017.8126078 – volume: 12 start-page: e0180944 year: 2017 ident: 72045_CR7 publication-title: PLoS One doi: 10.1371/journal.pone.0180944 – ident: 72045_CR2 – ident: 72045_CR25 doi: 10.1098/rsta.2020.0209 – ident: 72045_CR14 – ident: 72045_CR22 doi: 10.1109/ICMLC56445.2022.9941330 – volume: 50 start-page: 258 year: 2010 ident: 72045_CR3 publication-title: Decis. Support Syst. doi: 10.1016/j.dss.2010.08.028 – ident: 72045_CR29 – volume: 102 start-page: 1079 issue: 479 year: 2007 ident: 72045_CR20 publication-title: J. Am. Stat. Assoc. doi: 10.1198/jasa.2007.s209 – ident: 72045_CR23 – ident: 72045_CR17 doi: 10.1109/SIU53274.2021.9477814 – volume: 147 start-page: 400 year: 2019 ident: 72045_CR8 publication-title: Procedia Comput. Sci. doi: 10.1016/j.procs.2019.01.256 – volume: 11 start-page: 1 year: 2020 ident: 72045_CR16 publication-title: Nat. Commun. doi: 10.1038/s41467-020-19266-y – volume-title: Deep Learning year: 2016 ident: 72045_CR24 – volume: 447 start-page: 116 year: 2016 ident: 72045_CR1 publication-title: Phys. A doi: 10.1016/j.physa.2015.12.017 – volume: 55 start-page: 194 year: 2016 ident: 72045_CR4 publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2016.02.006 – ident: 72045_CR18 – volume: 209 start-page: 415 year: 2019 ident: 72045_CR12 publication-title: J. Clean. Prod. doi: 10.1016/j.jclepro.2018.10.128 – volume: 102 start-page: 1305 year: 2020 ident: 72045_CR9 publication-title: Computing doi: 10.1007/s00607-019-00773-w – volume: 1989 start-page: 1270 year: 1989 ident: 72045_CR30 publication-title: Neural Comput.
SSID	ssj0000529419
Score	2.5049858
Snippet	The prediction of stock market fluctuations is crucial for decision-making in various financial fields. Deep learning algorithms have demonstrated outstanding... Abstract The prediction of stock market fluctuations is crucial for decision-making in various financial fields. Deep learning algorithms have demonstrated...
SourceID	doaj proquest pubmed crossref springer
SourceType	Open Website Aggregation Database Index Database Enrichment Source Publisher
StartPage	23762
SubjectTerms	639/166 639/705 Accuracy Algorithms Decision making Deep learning Experiments Forecasting Galformer Humanities and Social Sciences multidisciplinary Natural language processing Neural networks Predictions Science Science (multidisciplinary) Securities markets Stock exchanges Stock index prediction Stock market indexes Time series Transformer Trends
SummonAdditionalLinks	– databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELagBYkL70egICNxg6hObCc2F0RRCwe0qhCg3iy_UhDL7pLdIu2_Z8ZxUiGgF5RbMo5szdtjf0PIsy6IxsWuLZmTvhROSbCDIpTWW8kbpdUApP35fTubqZMTfZw33Nb5WOVoE5OhDkuPe-T7iApT8xY85KvVjxK7RmF1NbfQuEx2EakM5Hz34HB2_GHaZcE6lqh0vi3DuNpfg8fCW2W1KLE_iyz5bx4pAff_Ldr8o1KaHNDRjf-d-k1yPYee9PUgK7fIpbi4Ta4OzSi3d8j2rZ1jBBv7l9TSzRjQxp7iXi09TfjUaBxpgJQVXR61iwCkX7Z464vOYXEU3SSymsJQmg4rliBGKwohpv9Gv6cr1jQhNNJVjzUiJL5LPh0dfnzzrsyNGUovlNyUnsGjogaF71h0inFnY9VAnC67hgcWmK67ygYIFlkblYdXlXSNCMp3iknH75GdxXIRHxAK6aJ1mqs21lxoXznIr1QITe0jdzq2BalG5hifUcuxecbcpOo5V2ZgqAGGmsRQwwvyfBqzGjA7LqQ-QJ5PlIi3nV4s-1OT1dcIEZ2rId6pLIeMWFvpnW50G7hrXcW6guyNrDfZCKzNOd8L8nT6DOqLNRm7iMuzgUZiebIuyP1B0qaZcM01Vk0L8mIUvfOf_3tBDy-eyyNyrUbpx1M5bI_sbPqz-Jhc8T83X9f9k6xAvwBKMiGV priority: 102 providerName: ProQuest
Title	Galformer: a transformer with generative decoding and a hybrid loss function for multi-step stock market index prediction
URI	https://link.springer.com/article/10.1038/s41598-024-72045-3 https://www.ncbi.nlm.nih.gov/pubmed/39390029 https://www.proquest.com/docview/3115237066 https://www.proquest.com/docview/3115501092 https://doaj.org/article/44ebb20221a34099a5cb9697d3b7b10f
Volume	14
WOSCitedRecordID	wos001337092300049&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: DOA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: M~E dateStart: 20110101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Biological Science Database (ProQuest) customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: M7P dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: 7X7 dateStart: 20110101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest - Publicly Available Content Database customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: PIMPY dateStart: 20110101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: BENPR dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database (ProQuest) customDbUrl: eissn: 2045-2322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000529419 issn: 2045-2322 databaseCode: M2P dateStart: 20110101 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3di9QwEA96p-CL-H3Vc4ngm5ZLm7ZJfPPkTgVvKaKyPoV8VeXW3tLdE_a_dybprid-vUghD-mkJJlJZqaT_IaQx52vGhs6kTNbu7yysoZ9sPK5cabmjVQyAWl_eCOmUzmbqfZCqi88E5bggdPEHVRVsBY89LIwHHwRZWpnVaOE51bYgnW4-zKhLjhTCdW7VFWhxlsyjMuDJWgqvE1WVjnmZalz_pMmioD9v7Myf4mQRsVzfINcHy1G-jz19Ca5FPpb5GrKIbm-TdYvzRwNzzA8o4auNnZoGCj-YqWfIqw07mnUg6eJmoqa3gPp5zVe1qJz6BtF7YYcotCUxjOGOXB_QcEydKf0a7wZTSOwIl0MGNpB4jvk_fHRuxev8jGfQu4qWa9yx-CRQcE67ViwknFrQtGAeV13DffMM1V2hfFg4zERpIOqorZN5aXrJKstv0t2-rM-7BEKXp6xiksRSl4pV1hwi6T3TekCtyqIjBSbudVuBBvHnBdzHYPeXOrEDw380JEfmmfkybbNIkFt_JX6EFm2pUSY7FgBwqNH4dH_Ep6M7G8Yrse1u9SIP1RyAbZYRh5tX8Oqw1CK6cPZeaKpMapYZuReEpRtT7jiCoOdGXm6kZwfH__zgO7_jwE9INdKFHE8csP2yc5qOA8PyRX3bfVlOUzIZTETsZQTsnt4NG3fTuK6gfKkbLEUUO62r0_aj98BrwEY7A
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Jb9QwFLZKAZUL-xIoYCQ4QVTHzmIjIcRWWnUY9VCq3oy3tIhhZshMQfOn-I285yRTIaC3HtDcMi9Rlu89f89vI-Rx7fPShrpKmS1cmltZgB3MfWqcKUQplWwbae8PquFQHhyo3RXys6-FwbTK3iZGQ-0nDvfIN7ArDBcVrJAvp99SnBqF0dV-hEYLi52w-AEu2-zF9lv4vk8433y392Yr7aYKpC6XxTx1DH4yKEBrzYKVTFgTshJIZlGXwjPPFK8z44HpsCpIB4eywpa5l66WrLACrnuOnAcawVlMFdxd7ulg1CzPVFebw4TcmMH6iDVsPE9xGkyRit_Wvzgm4G_c9o-4bFzuNq_8by_qKrncEWv6qtWEa2QljK-Ti-2ozcUNsnhvRsjPQ_OcGjrv6XpoKO5E08PYfRtNP_XgkOOCTs3Yg-jRAmva6AheJkUSgECmcCqNqZgpKMmUAoF2X-jXWEBOY_9JOm0wAobCN8nHM3nuW2R1PBmHO4SCM2ysErIKXOTKZRa8R-l9yV0QVoUqIVkPBu26nuw4GmSkY26AkLoFkAYA6QggLRLydHnOtO1Icqr0a8TYUhK7iccDk-ZQd8ZJ53mwlgOby4wAf1-ZwllVqsoLW9mM1QlZ76GmOxM30yc4S8ij5d9gnDDiZMZhctzKFBh85Qm53SJ7eSdCCYUx4YQ866F-cvF_P9Dd0-_lIVnb2vsw0IPt4c49comj5mH-EVsnq_PmONwnF9z3-edZ8yCqLiWfzloFfgFMnHy-
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Jb9QwFLZKWcSFfQkUMBKcaDSO7SQ2EkJAGahajeYAqDfjLQUxzAyZKWj-Gr-O97JMhYDeekC5JS9RnHxv89sIeVQFWbhYlSlzuU-lUznIQRlS620uCqVV20j7w345GqmDAz3eID_7WhhMq-xlYiOow8zjHvkAu8JwUYKGHFRdWsR4Z_h8_i3FCVIYae3HabQQ2YurH-C-LZ7t7sC_fsz58PW7V2_TbsJA6qXKl6lncKioAbkVi04x4WzMCjA486oQgQWmeZXZAFYPK6PycCrLXSGD8pViuRPw3DPkbIldsTBtkI_X-zsYQZOZ7up0mFCDBehKrGfjMsXJMHkqftOFzciAv9m5f8RoG9U3vPw_f7Qr5FJncNMXLYdcJRtxeo2cb0dwrq6T1Rs7Qbs91k-ppcvejI81xR1qeth05UaVQAM46qjoqZ0GIP20wlo3OoEPS9E4QIBTuJU2KZopMM-cgmHtv9CvTWE5bfpS0nmNkTEkvkHen8q6b5LN6WwabxMKTrJ1WqgyciG1zxx4lSqEgvsonI5lQrIeGMZ3vdpxZMjENDkDQpkWTAbAZBowGZGQJ-t75m2nkhOpXyLe1pTYZbw5MasPTSe0jJTROQ5WXmaFBFfC5t7pQpdBuNJlrErIVg8704m-hTnGXEIeri-D0MJIlJ3G2VFLk2NQlifkVovy9ZsILTTGihOy3cP--OH_XtCdk9_lAbkAyDf7u6O9u-QiRybEtCS2RTaX9VG8R87578vPi_p-w8WUfDxtDvgFIcmFgg
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=Galformer%3A+a+transformer+with+generative+decoding+and+a+hybrid+loss+function+for+multi-step+stock+market+index+prediction&rft.jtitle=Scientific+reports&rft.au=Yi+Ji&rft.au=Yuxuan+Luo&rft.au=Aixia+Lu&rft.au=Duanyang+Xia&rft.date=2024-10-10&rft.pub=Nature+Portfolio&rft.eissn=2045-2322&rft.volume=14&rft.issue=1&rft.spage=1&rft.epage=18&rft_id=info:doi/10.1038%2Fs41598-024-72045-3&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_44ebb20221a34099a5cb9697d3b7b10f
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2045-2322&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2045-2322&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2045-2322&client=summon