Financial time series forecasting with multi-modality graph neural network

Financial time series analysis plays a central role in hedging market risks and optimizing investment decisions. This is a challenging task as the problems are always accompanied by multi-modality streams and lead-lag effects. For example, the price movements of stock are reflections of complicated...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition Vol. 121; p. 108218
Main Authors: Cheng, Dawei, Yang, Fangzhou, Xiang, Sheng, Liu, Jin
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.01.2022
Subjects:
ISSN:0031-3203, 1873-5142
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Financial time series analysis plays a central role in hedging market risks and optimizing investment decisions. This is a challenging task as the problems are always accompanied by multi-modality streams and lead-lag effects. For example, the price movements of stock are reflections of complicated market states in different diffusion speeds, including historical price series, media news, associated events, etc. Furthermore, the financial industry requires forecasting models to be interpretable and compliant. Therefore, in this paper, we propose a multi-modality graph neural network (MAGNN) to learn from these multimodal inputs for financial time series prediction. The heterogeneous graph network is constructed by the sources as nodes and relations in our financial knowledge graph as edges. To ensure the model interpretability, we leverage a two-phase attention mechanism for joint optimization, allowing end-users to investigate the importance of inner-modality and inter-modality sources. Extensive experiments on real-world datasets demonstrate the superior performance of MAGNN in financial market prediction. Our method provides investors with a profitable as well as interpretable option and enables them to make informed investment decisions.
AbstractList Financial time series analysis plays a central role in hedging market risks and optimizing investment decisions. This is a challenging task as the problems are always accompanied by multi-modality streams and lead-lag effects. For example, the price movements of stock are reflections of complicated market states in different diffusion speeds, including historical price series, media news, associated events, etc. Furthermore, the financial industry requires forecasting models to be interpretable and compliant. Therefore, in this paper, we propose a multi-modality graph neural network (MAGNN) to learn from these multimodal inputs for financial time series prediction. The heterogeneous graph network is constructed by the sources as nodes and relations in our financial knowledge graph as edges. To ensure the model interpretability, we leverage a two-phase attention mechanism for joint optimization, allowing end-users to investigate the importance of inner-modality and inter-modality sources. Extensive experiments on real-world datasets demonstrate the superior performance of MAGNN in financial market prediction. Our method provides investors with a profitable as well as interpretable option and enables them to make informed investment decisions.
ArticleNumber 108218
Author Liu, Jin
Yang, Fangzhou
Cheng, Dawei
Xiang, Sheng
Author_xml – sequence: 1
  givenname: Dawei
  surname: Cheng
  fullname: Cheng, Dawei
  email: dcheng@tongji.edu.cn
  organization: Department of Computer Science and Technology, Tongji University, Shanghai, China
– sequence: 2
  givenname: Fangzhou
  surname: Yang
  fullname: Yang, Fangzhou
  organization: AI Lab, Emoney Inc, Shanghai, China
– sequence: 3
  givenname: Sheng
  surname: Xiang
  fullname: Xiang, Sheng
  organization: Center for Artificial Intelligence, University of Technology Sydney, Sydney, Australia
– sequence: 4
  givenname: Jin
  surname: Liu
  fullname: Liu, Jin
  organization: AI Lab, Emoney Inc, Shanghai, China
BookMark eNqFkM1KAzEUhYNUsK2-gYt5galJpp3MuBCk-EvBja7DbeamvXWalCS19O2dMq5c6OrCOXwH7jdiA-cdMnYt-ERwUd5sJjtIxq8mkkvRRZUU1RkbikoV-UxM5YANOS9EXkheXLBRjBvOheqKIXt9JAfOELRZoi1mEQNhzKwPaCAmcqvsQGmdbfdtonzrG2gpHbNVgN06c7gPHegwHXz4vGTnFtqIVz93zD4eH97nz_ni7ellfr_ITcHLlMsZcN5YMJW0VdEAt9ZUgltRT8vlsu5aVI2yS1VXCkGJaoYoS9WIsgbLSyjG7LbfNcHHGNBqQwkSeZcCUKsF1ycreqN7K_pkRfdWOnj6C94F2kI4_ofd9Rh2j30RBh0NoTPYUCcq6cbT3wPfXJaB3g
CitedBy_id crossref_primary_10_1088_1361_6501_ae014b
crossref_primary_10_1016_j_patcog_2023_109423
crossref_primary_10_1109_TNNLS_2024_3475484
crossref_primary_10_1016_j_compeleceng_2025_110197
crossref_primary_10_1016_j_patcog_2023_110139
crossref_primary_10_1109_JSAC_2022_3221950
crossref_primary_10_1109_TKDE_2025_3543887
crossref_primary_10_1016_j_nlp_2023_100031
crossref_primary_10_3390_ijgi10120835
crossref_primary_10_3233_JCM_247139
crossref_primary_10_1016_j_neunet_2024_106537
crossref_primary_10_1145_3698107
crossref_primary_10_1111_joes_70014
crossref_primary_10_1007_s00521_023_08914_1
crossref_primary_10_1016_j_ipm_2025_104103
crossref_primary_10_3390_math13152402
crossref_primary_10_1016_j_ijforecast_2024_11_004
crossref_primary_10_1016_j_ijepes_2025_110924
crossref_primary_10_1016_j_iswa_2025_200566
crossref_primary_10_3390_jtaer19010016
crossref_primary_10_1016_j_knosys_2024_111638
crossref_primary_10_1186_s40854_025_00768_x
crossref_primary_10_1371_journal_pone_0303977
crossref_primary_10_1016_j_patcog_2024_110264
crossref_primary_10_1007_s13042_025_02756_0
crossref_primary_10_1016_j_future_2024_107677
crossref_primary_10_32604_cmc_2023_036830
crossref_primary_10_1016_j_cosrev_2025_100813
crossref_primary_10_1016_j_patcog_2024_110309
crossref_primary_10_1007_s10614_025_10899_z
crossref_primary_10_3389_fpubh_2025_1540618
crossref_primary_10_1007_s10489_024_05590_z
crossref_primary_10_1016_j_cosrev_2024_100633
crossref_primary_10_1016_j_patcog_2023_109890
crossref_primary_10_1109_TPAMI_2023_3319557
crossref_primary_10_1016_j_ijar_2025_109387
crossref_primary_10_1007_s11704_024_40474_y
crossref_primary_10_1080_13683500_2024_2320851
crossref_primary_10_1016_j_asoc_2024_111754
crossref_primary_10_1016_j_snb_2024_136085
crossref_primary_10_1109_ACCESS_2023_3318478
crossref_primary_10_1016_j_neucom_2025_130168
crossref_primary_10_3389_fenvs_2025_1557665
crossref_primary_10_1016_j_neucom_2025_130049
crossref_primary_10_3390_make6040113
crossref_primary_10_1007_s13042_023_02008_z
crossref_primary_10_1145_3603620
crossref_primary_10_1109_TBDATA_2024_3499338
crossref_primary_10_1016_j_inffus_2025_103228
crossref_primary_10_1016_j_patcog_2023_109920
crossref_primary_10_1016_j_knosys_2023_110997
crossref_primary_10_1016_j_cageo_2023_105435
crossref_primary_10_1016_j_frl_2024_105195
crossref_primary_10_1016_j_patcog_2023_110118
crossref_primary_10_1109_TII_2025_3555981
crossref_primary_10_1016_j_patcog_2024_110912
crossref_primary_10_1016_j_ins_2022_02_015
crossref_primary_10_1007_s10462_024_10989_8
crossref_primary_10_1109_TKDE_2025_3566111
crossref_primary_10_1007_s11424_024_4044_9
crossref_primary_10_1016_j_patcog_2025_111919
crossref_primary_10_1007_s10489_022_04285_7
crossref_primary_10_1016_j_engappai_2023_106077
crossref_primary_10_1016_j_eswa_2023_121654
crossref_primary_10_1016_j_jpdc_2025_105173
crossref_primary_10_1007_s00521_025_11325_z
crossref_primary_10_1049_ccs2_12086
crossref_primary_10_3389_fenvs_2025_1550745
crossref_primary_10_3390_app12126044
crossref_primary_10_1016_j_compag_2024_109439
crossref_primary_10_1016_j_ipm_2024_103758
crossref_primary_10_1007_s11063_022_11001_6
crossref_primary_10_1109_TNNLS_2024_3519169
crossref_primary_10_1109_TKDE_2025_3530467
crossref_primary_10_1016_j_inffus_2024_102461
crossref_primary_10_1016_j_eswa_2023_122072
crossref_primary_10_1016_j_eswa_2025_127964
crossref_primary_10_1016_j_patcog_2023_109872
crossref_primary_10_1016_j_engappai_2023_106754
crossref_primary_10_1016_j_swevo_2024_101693
crossref_primary_10_1038_s41598_025_11622_6
crossref_primary_10_1016_j_inffus_2025_103456
crossref_primary_10_1080_13504851_2022_2141436
crossref_primary_10_1109_TNNLS_2024_3376530
crossref_primary_10_1140_epjs_s11734_024_01368_z
crossref_primary_10_1007_s42979_023_02018_2
crossref_primary_10_1155_2024_5791802
crossref_primary_10_1007_s10791_025_09565_7
crossref_primary_10_1016_j_ins_2024_121286
crossref_primary_10_1038_s41598_025_15907_8
crossref_primary_10_1016_j_jocs_2024_102518
crossref_primary_10_1016_j_procs_2025_04_403
crossref_primary_10_3390_app14198737
crossref_primary_10_1016_j_jempfin_2025_101639
crossref_primary_10_1016_j_patcog_2023_109759
crossref_primary_10_1109_TKDE_2023_3335240
crossref_primary_10_1016_j_iswa_2025_200496
crossref_primary_10_1109_ACCESS_2024_3476159
crossref_primary_10_1016_j_eswa_2025_129462
crossref_primary_10_1109_TKDE_2025_3572216
crossref_primary_10_3390_app14156571
crossref_primary_10_1016_j_inffus_2024_102616
crossref_primary_10_1016_j_eswa_2025_126871
crossref_primary_10_4018_JOEUC_358454
crossref_primary_10_1016_j_neunet_2025_107381
crossref_primary_10_1016_j_patcog_2021_108490
crossref_primary_10_1007_s10489_025_06462_w
crossref_primary_10_1007_s00530_024_01333_9
crossref_primary_10_1016_j_patcog_2023_110211
crossref_primary_10_1016_j_aej_2025_03_037
crossref_primary_10_1016_j_asoc_2022_109809
crossref_primary_10_1016_j_websem_2022_100722
crossref_primary_10_1145_3729531
crossref_primary_10_1016_j_ins_2022_07_105
crossref_primary_10_1007_s12065_025_01078_y
crossref_primary_10_1007_s00500_023_07915_5
crossref_primary_10_1155_2022_7817264
crossref_primary_10_1016_j_asoc_2024_111847
crossref_primary_10_1016_j_asoc_2024_111329
crossref_primary_10_1016_j_procs_2022_11_240
crossref_primary_10_1109_TNNLS_2023_3266243
crossref_primary_10_3389_fenrg_2023_1193662
crossref_primary_10_1016_j_patcog_2025_111412
crossref_primary_10_1016_j_engappai_2023_106854
crossref_primary_10_1016_j_ese_2024_100514
crossref_primary_10_1016_j_aei_2025_103142
crossref_primary_10_1016_j_patcog_2022_108543
crossref_primary_10_1016_j_asoc_2025_113763
crossref_primary_10_1109_ACCESS_2024_3441029
crossref_primary_10_3390_info13100466
crossref_primary_10_1109_ACCESS_2023_3275085
crossref_primary_10_1109_TKDE_2024_3418576
crossref_primary_10_1016_j_eiar_2024_107539
crossref_primary_10_1016_j_eswa_2023_122333
crossref_primary_10_1016_j_asoc_2025_113519
crossref_primary_10_1016_j_ipm_2023_103569
crossref_primary_10_1016_j_inffus_2024_102836
crossref_primary_10_1007_s11063_023_11287_0
crossref_primary_10_1016_j_knosys_2025_113287
crossref_primary_10_3390_forecast5010010
crossref_primary_10_3389_fphy_2025_1585105
crossref_primary_10_4018_IJITSA_384593
crossref_primary_10_1016_j_patcog_2024_110552
crossref_primary_10_1016_j_eswa_2022_119374
crossref_primary_10_1002_eng2_12824
crossref_primary_10_1016_j_eswa_2024_123959
crossref_primary_10_1016_j_jocs_2022_101940
crossref_primary_10_1016_j_eswa_2022_117595
crossref_primary_10_1016_j_neucom_2024_129218
crossref_primary_10_1007_s10844_025_00971_3
crossref_primary_10_3390_info16030196
crossref_primary_10_1088_1361_6501_ad545e
crossref_primary_10_1109_ACCESS_2022_3199008
crossref_primary_10_1109_TSP_2024_3503063
crossref_primary_10_1134_S105466182470144X
crossref_primary_10_32604_cmc_2023_036553
crossref_primary_10_1016_j_neucom_2023_127033
crossref_primary_10_1145_3744918
crossref_primary_10_1016_j_knosys_2025_114441
crossref_primary_10_1007_s00521_024_10418_5
crossref_primary_10_1016_j_patcog_2024_110720
crossref_primary_10_1016_j_engappai_2022_105166
crossref_primary_10_1016_j_patcog_2023_109799
crossref_primary_10_1109_TASE_2023_3335145
crossref_primary_10_1016_j_patcog_2022_109014
crossref_primary_10_1088_1361_6501_adfc8a
crossref_primary_10_1155_2022_5106942
crossref_primary_10_1109_TPAMI_2024_3443253
crossref_primary_10_1016_j_patcog_2025_111716
crossref_primary_10_1016_j_dynatmoce_2023_101388
crossref_primary_10_1109_TAI_2024_3379968
crossref_primary_10_3390_forecast7030036
crossref_primary_10_1007_s13042_024_02402_1
crossref_primary_10_3390_en15134877
crossref_primary_10_3390_info14110598
crossref_primary_10_1109_TETCI_2023_3259434
crossref_primary_10_1080_03081079_2024_2409748
crossref_primary_10_1109_TSP_2023_3282068
crossref_primary_10_1016_j_patcog_2024_111093
crossref_primary_10_1016_j_patcog_2025_111392
crossref_primary_10_3390_math10142437
crossref_primary_10_3390_sym17091372
Cites_doi 10.1016/S0304-405X(03)00146-6
10.1109/TNN.2003.820556
10.1016/j.asoc.2020.106181
10.1016/j.patcog.2018.12.026
10.1086/294743
10.1038/s41598-019-55320-6
10.1111/j.1540-6288.1999.tb00471.x
10.1016/j.jempfin.2008.03.002
10.1080/14697688.2019.1622314
10.1016/j.patcog.2020.107617
10.1016/j.ejor.2017.11.054
10.1007/s10287-017-0280-y
10.2307/1907042
10.1002/jae.3950070512
10.1016/j.patcog.2020.107382
10.1049/iet-ipr.2019.0617
10.1016/j.patcog.2019.107000
ContentType Journal Article
Copyright 2021 Elsevier Ltd
Copyright_xml – notice: 2021 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.patcog.2021.108218
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1873-5142
ExternalDocumentID 10_1016_j_patcog_2021_108218
S003132032100399X
GroupedDBID --K
--M
-D8
-DT
-~X
.DC
.~1
0R~
123
1B1
1RT
1~.
1~5
29O
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABEFU
ABFNM
ABFRF
ABHFT
ABJNI
ABMAC
ABTAH
ABXDB
ABYKQ
ACBEA
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADMXK
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FD6
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
KZ1
LG9
LMP
LY1
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SBC
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TN5
UNMZH
VOH
WUQ
XJE
XPP
ZMT
ZY4
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c306t-25a00dfac82f83da0ffc810f1946bb95a0e7d7fb7987ea7185ee267d169af06a3
ISICitedReferencesCount 232
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000697672400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0031-3203
IngestDate Sat Nov 29 07:30:52 EST 2025
Tue Nov 18 22:11:32 EST 2025
Fri Feb 23 02:43:53 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Quantitative investment
Graph attention
Graph neural network
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-25a00dfac82f83da0ffc810f1946bb95a0e7d7fb7987ea7185ee267d169af06a3
ParticipantIDs crossref_citationtrail_10_1016_j_patcog_2021_108218
crossref_primary_10_1016_j_patcog_2021_108218
elsevier_sciencedirect_doi_10_1016_j_patcog_2021_108218
PublicationCentury 2000
PublicationDate January 2022
2022-01-00
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: January 2022
PublicationDecade 2020
PublicationTitle Pattern recognition
PublicationYear 2022
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Fang, Liu, Xu (bib0045) 2019; 14
O’Connor (bib0003) 1999; 34
Knyazev, Taylor, Amer (bib0037) 2019
Cowles (bib0004) 1933; 1
Cao, Tsay (bib0006) 1992; 7
Zhou, Zheng, Zhu, Li, He (bib0031) 2020
Feng, Xu, Zuo, Chen, Lin, XiaHou (bib0039) 2021
Cheng, Xiang, Shang, Zhang, Yang, Zhang (bib0043) 2020; 34
Sezer, Gudelek, Ozbayoglu (bib0032) 2020; 90
Choi, Bahadori, Song, Stewart, Sun (bib0041) 2017
Sagheer, Kotb (bib0030) 2019; 9
Wu, Zhong, Liu (bib0042) 2020; 107
Tashiro, Matsushima, Izumi, Sakaji (bib0010) 2019; 19
Chan (bib0017) 2003; 70
De Prado (bib0025) 2018
Li, Yang, Zhao, Bian, Qin, Liu (bib0027) 2019
D.P. Kingma, J. Ba, Adam: a method for stochastic optimization
Ledoit, Wolf (bib0024) 2008; 15
Cheng, Niu, Zhang (bib0040) 2020
Taylor (bib0005) 2008
Ganeshapillai, Guttag, Lo (bib0016) 2013
Bharathi, Geetha (bib0011) 2017; 10
Andersen, Davis, Kreiß, Mikosch (bib0026) 2009
Park, Kan, Dong, Zhao, Faloutsos (bib0038) 2019
Fama (bib0002) 1965; 38.1
Xu, Cohen (bib0012) 2018
Deng, Zhang, Zhang, Chen, Pan, Chen (bib0014) 2019
Dehmamy, Barabási, Yu (bib0035) 2019
Worldbank, Market capitalization of listed domestic companies, 2020, Accessed 16-March-2021
Cheng, Tu, Niu, Zhang (bib0008) 2018
Fischer, Krauss (bib0013) 2018; 270
Saha (bib0020) 2018
Hussein, Yang, Cudré-Mauroux (bib0018) 2018
Manessi, Rozza, Manzo (bib0036) 2020; 97
J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: pre-training of deep bidirectional transformers for language understanding, 2018
(2014).
Cheng, Wang, Zhang (bib0044) 2020
Ding, Liao, Liu, Li, Duan (bib0021) 2019
Ye, Dai (bib0033) 2021; 109
.
Velickovic, Casanova, Lio, Cucurull, Romero, Bengio (bib0023) 2018
R.D. Edwards, J. Magee, W.H. Bassetti, Technical Analysis of Stock Trends, 2012.
Hu, Liu, Bian, Liu, Liu (bib0009) 2018
Agapitos, Brabazon, O’Neill (bib0029) 2017; 14
Cheng, Yang, Wang, Zhang, Zhang (bib0015) 2020
Cao, Tay (bib0028) 2003; 14
Wang, Zhang, Wu, Pan, Chen (bib0034) 2019; 89
Cowles (10.1016/j.patcog.2021.108218_bib0004) 1933; 1
Sezer (10.1016/j.patcog.2021.108218_bib0032) 2020; 90
Hu (10.1016/j.patcog.2021.108218_bib0009) 2018
Knyazev (10.1016/j.patcog.2021.108218_bib0037) 2019
Ledoit (10.1016/j.patcog.2021.108218_bib0024) 2008; 15
Fischer (10.1016/j.patcog.2021.108218_bib0013) 2018; 270
Park (10.1016/j.patcog.2021.108218_bib0038) 2019
Choi (10.1016/j.patcog.2021.108218_bib0041) 2017
Andersen (10.1016/j.patcog.2021.108218_bib0026) 2009
Zhou (10.1016/j.patcog.2021.108218_bib0031) 2020
Fama (10.1016/j.patcog.2021.108218_bib0002) 1965; 38.1
Tashiro (10.1016/j.patcog.2021.108218_bib0010) 2019; 19
O’Connor (10.1016/j.patcog.2021.108218_bib0003) 1999; 34
De Prado (10.1016/j.patcog.2021.108218_bib0025) 2018
Cheng (10.1016/j.patcog.2021.108218_bib0015) 2020
Saha (10.1016/j.patcog.2021.108218_bib0020) 2018
Hussein (10.1016/j.patcog.2021.108218_bib0018) 2018
10.1016/j.patcog.2021.108218_bib0019
Cheng (10.1016/j.patcog.2021.108218_bib0040) 2020
Ye (10.1016/j.patcog.2021.108218_bib0033) 2021; 109
Li (10.1016/j.patcog.2021.108218_bib0027) 2019
Dehmamy (10.1016/j.patcog.2021.108218_bib0035) 2019
Fang (10.1016/j.patcog.2021.108218_bib0045) 2019; 14
Ganeshapillai (10.1016/j.patcog.2021.108218_bib0016) 2013
Cheng (10.1016/j.patcog.2021.108218_bib0043) 2020; 34
Wang (10.1016/j.patcog.2021.108218_bib0034) 2019; 89
Taylor (10.1016/j.patcog.2021.108218_bib0005) 2008
Wu (10.1016/j.patcog.2021.108218_bib0042) 2020; 107
Feng (10.1016/j.patcog.2021.108218_bib0039) 2021
Deng (10.1016/j.patcog.2021.108218_bib0014) 2019
10.1016/j.patcog.2021.108218_bib0022
Cao (10.1016/j.patcog.2021.108218_bib0006) 1992; 7
Xu (10.1016/j.patcog.2021.108218_bib0012) 2018
Chan (10.1016/j.patcog.2021.108218_bib0017) 2003; 70
Velickovic (10.1016/j.patcog.2021.108218_bib0023) 2018
Manessi (10.1016/j.patcog.2021.108218_bib0036) 2020; 97
Cheng (10.1016/j.patcog.2021.108218_bib0044) 2020
10.1016/j.patcog.2021.108218_bib0001
Cheng (10.1016/j.patcog.2021.108218_bib0008) 2018
Bharathi (10.1016/j.patcog.2021.108218_bib0011) 2017; 10
10.1016/j.patcog.2021.108218_bib0007
Agapitos (10.1016/j.patcog.2021.108218_bib0029) 2017; 14
Sagheer (10.1016/j.patcog.2021.108218_bib0030) 2019; 9
Ding (10.1016/j.patcog.2021.108218_bib0021) 2019
Cao (10.1016/j.patcog.2021.108218_bib0028) 2003; 14
References_xml – start-page: 4896
  year: 2019
  end-page: 4905
  ident: bib0021
  article-title: Event representation learning enhanced with external commonsense knowledge
  publication-title: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
– volume: 14
  start-page: 1506
  year: 2003
  end-page: 1518
  ident: bib0028
  article-title: Support vector machine with adaptive parameters in financial time series forecasting
  publication-title: IEEE Trans. Neural Netw.
– year: 2009
  ident: bib0026
  article-title: Handbook of Financial Time Series
– volume: 34
  start-page: 95
  year: 1999
  end-page: 117
  ident: bib0003
  article-title: The cross-sectional relationship between trading costs and lead/lag effects in stock & option markets
  publication-title: Financ. Rev.
– reference: (2014).
– start-page: 2230
  year: 2020
  end-page: 2240
  ident: bib0031
  article-title: Domain adaptive multi-modality neural attention network for financial forecasting
  publication-title: Proceedings of The Web Conference 2020
– volume: 107
  start-page: 107382
  year: 2020
  ident: bib0042
  article-title: Dynamic graph convolutional network for multi-video summarization
  publication-title: Pattern Recognit.
– year: 2018
  ident: bib0023
  article-title: Graph attention networks
  publication-title: 6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings
– volume: 14
  start-page: 367
  year: 2017
  end-page: 391
  ident: bib0029
  article-title: Regularised gradient boosting for financial time-series modelling
  publication-title: Comput. Manag. Sci.
– volume: 34
  start-page: 362
  year: 2020
  end-page: 369
  ident: bib0043
  article-title: Spatio-temporal attention-based neural network for credit card fraud detection
  publication-title: Proceedings of the AAAI Conference on Artificial Intelligence
– volume: 38.1
  start-page: 34
  year: 1965
  end-page: 105
  ident: bib0002
  article-title: The behavior of stock-market prices
  publication-title: J. Bus.
– volume: 10
  start-page: 146
  year: 2017
  end-page: 154
  ident: bib0011
  article-title: Sentiment analysis for effective stock market prediction
  publication-title: Int. J. Intell. Eng. Syst.
– start-page: 2715
  year: 2020
  end-page: 2723
  ident: bib0040
  article-title: Contagious chain risk rating for networked-guarantee loans
  publication-title: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
– year: 2008
  ident: bib0005
  article-title: Modelling Financial Time Series[M]
– volume: 7
  start-page: S165
  year: 1992
  end-page: S185
  ident: bib0006
  article-title: Nonlinear time-series analysis of stock volatilities[J]
  publication-title: J. Appl. Econom.
– volume: 1
  start-page: 309
  year: 1933
  end-page: 324
  ident: bib0004
  article-title: Can stock market forecasters forecast?
  publication-title: Econometrica
– start-page: 1970
  year: 2018
  end-page: 1979
  ident: bib0012
  article-title: Stock movement prediction from tweets and historical prices
  publication-title: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
– volume: 15
  start-page: 850
  year: 2008
  end-page: 859
  ident: bib0024
  article-title: Robust performance hypothesis testing with the sharpe ratio
  publication-title: J. Empir. Finance
– volume: 9
  start-page: 1
  year: 2019
  end-page: 16
  ident: bib0030
  article-title: Unsupervised pre-training of a deep LSTM-based stacked autoencoder for multivariate time series forecasting problems
  publication-title: Sci. Rep.
– start-page: 4202
  year: 2019
  end-page: 4212
  ident: bib0037
  article-title: Understanding attention and generalization in graph neural networks
  publication-title: Advances in Neural Information Processing Systems
– volume: 109
  start-page: 107617
  year: 2021
  ident: bib0033
  article-title: Implementing transfer learning across different datasets for time series forecasting
  publication-title: Pattern Recognit.
– volume: 70
  start-page: 223
  year: 2003
  end-page: 260
  ident: bib0017
  article-title: Stock price reaction to news and no-news: drift and reversal after headlines
  publication-title: J. Financ. Econ.
– start-page: 15413
  year: 2019
  end-page: 15423
  ident: bib0035
  article-title: Understanding the representation power of graph neural networks in learning graph topology
  publication-title: Advances in Neural Information Processing Systems
– start-page: 787
  year: 2017
  end-page: 795
  ident: bib0041
  article-title: Gram: graph-based attention model for healthcare representation learning
  publication-title: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
– volume: 14
  start-page: 318
  year: 2019
  end-page: 326
  ident: bib0045
  article-title: Ensemble of deep convolutional neural networks based multi-modality images for Alzheimer’s disease diagnosis
  publication-title: IET Image Proc.
– volume: 19
  start-page: 1499
  year: 2019
  end-page: 1506
  ident: bib0010
  article-title: Encoding of high-frequency order information and prediction of short-term stock price by deep learning
  publication-title: Quant. Finance
– start-page: 109
  year: 2013
  end-page: 117
  ident: bib0016
  article-title: Learning connections in financial time series
  publication-title: International Conference on Machine Learning
– reference: Worldbank, Market capitalization of listed domestic companies, 2020, Accessed 16-March-2021,
– reference: .
– volume: 270
  start-page: 654
  year: 2018
  end-page: 669
  ident: bib0013
  article-title: Deep learning with long short-term memory networks for financial market predictions
  publication-title: Eur. J. Oper. Res.
– start-page: 108
  year: 2021
  end-page: 119
  ident: bib0039
  article-title: Relation-aware dynamic attributed graph attention network for stocks recommendation[J]
  publication-title: Pattern Recognit.
– start-page: 894
  year: 2019
  end-page: 902
  ident: bib0027
  article-title: Individualized indicator for all: stock-wise technical indicator optimization with stock embedding
  publication-title: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
– year: 2020
  ident: bib0044
  article-title: Graph neural network for fraud detection via spatial-temporal attention[J]
  publication-title: IEEE Trans. Knowl. Data Eng.
– start-page: 261
  year: 2018
  end-page: 269
  ident: bib0009
  article-title: Listening to chaotic whispers: a deep learning framework for news-oriented stock trend prediction
  publication-title: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, WSDM ’18
– volume: 89
  start-page: 55
  year: 2019
  end-page: 66
  ident: bib0034
  article-title: Time series feature learning with labeled and unlabeled data
  publication-title: Pattern Recognit.
– year: 2018
  ident: bib0025
  article-title: Advances in Financial Machine Learning
– volume: 90
  start-page: 106181
  year: 2020
  ident: bib0032
  article-title: Financial time series forecasting with deep learning: a systematic literature review: 2005–2019
  publication-title: Appl. Soft Comput.
– volume: 97
  start-page: 107000
  year: 2020
  ident: bib0036
  article-title: Dynamic graph convolutional networks
  publication-title: Pattern Recognit.
– start-page: 596
  year: 2019
  end-page: 606
  ident: bib0038
  article-title: Estimating node importance in knowledge graphs using graph neural networks
  publication-title: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
– reference: J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: pre-training of deep bidirectional transformers for language understanding, 2018
– start-page: 678
  year: 2019
  end-page: 685
  ident: bib0014
  article-title: Knowledge-driven stock trend prediction and explanation via temporal convolutional network
  publication-title: Companion Proceedings of The 2019 World Wide Web Conference
– start-page: 2221
  year: 2020
  end-page: 2230
  ident: bib0015
  article-title: Knowledge graph-based event embedding framework for financial quantitative investments
  publication-title: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
– start-page: 437
  year: 2018
  end-page: 446
  ident: bib0018
  article-title: Are meta-paths necessary? Revisiting heterogeneous graph embeddings
  publication-title: Proceedings of the 27th ACM International Conference on Information and Knowledge Management
– reference: R.D. Edwards, J. Magee, W.H. Bassetti, Technical Analysis of Stock Trends, 2012.
– start-page: 2641
  year: 2018
  end-page: 2645
  ident: bib0008
  article-title: Learning temporal relationships between financial signals
  publication-title: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
– reference: D.P. Kingma, J. Ba, Adam: a method for stochastic optimization,
– start-page: 2288
  year: 2018
  end-page: 2299
  ident: bib0020
  article-title: Open information extraction from conjunctive sentences
  publication-title: Proceedings of the 27th International Conference on Computational Linguistics
– start-page: 2221
  year: 2020
  ident: 10.1016/j.patcog.2021.108218_bib0015
  article-title: Knowledge graph-based event embedding framework for financial quantitative investments
– start-page: 2230
  year: 2020
  ident: 10.1016/j.patcog.2021.108218_bib0031
  article-title: Domain adaptive multi-modality neural attention network for financial forecasting
– year: 2008
  ident: 10.1016/j.patcog.2021.108218_bib0005
– volume: 70
  start-page: 223
  issue: 2
  year: 2003
  ident: 10.1016/j.patcog.2021.108218_bib0017
  article-title: Stock price reaction to news and no-news: drift and reversal after headlines
  publication-title: J. Financ. Econ.
  doi: 10.1016/S0304-405X(03)00146-6
– volume: 14
  start-page: 1506
  issue: 6
  year: 2003
  ident: 10.1016/j.patcog.2021.108218_bib0028
  article-title: Support vector machine with adaptive parameters in financial time series forecasting
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/TNN.2003.820556
– ident: 10.1016/j.patcog.2021.108218_bib0007
– volume: 90
  start-page: 106181
  year: 2020
  ident: 10.1016/j.patcog.2021.108218_bib0032
  article-title: Financial time series forecasting with deep learning: a systematic literature review: 2005–2019
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2020.106181
– start-page: 4896
  year: 2019
  ident: 10.1016/j.patcog.2021.108218_bib0021
  article-title: Event representation learning enhanced with external commonsense knowledge
– volume: 89
  start-page: 55
  year: 2019
  ident: 10.1016/j.patcog.2021.108218_bib0034
  article-title: Time series feature learning with labeled and unlabeled data
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2018.12.026
– start-page: 2715
  year: 2020
  ident: 10.1016/j.patcog.2021.108218_bib0040
  article-title: Contagious chain risk rating for networked-guarantee loans
– start-page: 678
  year: 2019
  ident: 10.1016/j.patcog.2021.108218_bib0014
  article-title: Knowledge-driven stock trend prediction and explanation via temporal convolutional network
– volume: 38.1
  start-page: 34
  year: 1965
  ident: 10.1016/j.patcog.2021.108218_bib0002
  article-title: The behavior of stock-market prices
  publication-title: J. Bus.
  doi: 10.1086/294743
– start-page: 894
  year: 2019
  ident: 10.1016/j.patcog.2021.108218_bib0027
  article-title: Individualized indicator for all: stock-wise technical indicator optimization with stock embedding
– start-page: 108
  year: 2021
  ident: 10.1016/j.patcog.2021.108218_bib0039
  article-title: Relation-aware dynamic attributed graph attention network for stocks recommendation[J]
  publication-title: Pattern Recognit.
– start-page: 261
  year: 2018
  ident: 10.1016/j.patcog.2021.108218_bib0009
  article-title: Listening to chaotic whispers: a deep learning framework for news-oriented stock trend prediction
– ident: 10.1016/j.patcog.2021.108218_bib0022
– ident: 10.1016/j.patcog.2021.108218_bib0019
– volume: 9
  start-page: 1
  issue: 1
  year: 2019
  ident: 10.1016/j.patcog.2021.108218_bib0030
  article-title: Unsupervised pre-training of a deep LSTM-based stacked autoencoder for multivariate time series forecasting problems
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-019-55320-6
– year: 2020
  ident: 10.1016/j.patcog.2021.108218_bib0044
  article-title: Graph neural network for fraud detection via spatial-temporal attention[J]
  publication-title: IEEE Trans. Knowl. Data Eng.
– volume: 34
  start-page: 95
  issue: 4
  year: 1999
  ident: 10.1016/j.patcog.2021.108218_bib0003
  article-title: The cross-sectional relationship between trading costs and lead/lag effects in stock & option markets
  publication-title: Financ. Rev.
  doi: 10.1111/j.1540-6288.1999.tb00471.x
– volume: 15
  start-page: 850
  issue: 5
  year: 2008
  ident: 10.1016/j.patcog.2021.108218_bib0024
  article-title: Robust performance hypothesis testing with the sharpe ratio
  publication-title: J. Empir. Finance
  doi: 10.1016/j.jempfin.2008.03.002
– start-page: 1970
  year: 2018
  ident: 10.1016/j.patcog.2021.108218_bib0012
  article-title: Stock movement prediction from tweets and historical prices
– start-page: 109
  year: 2013
  ident: 10.1016/j.patcog.2021.108218_bib0016
  article-title: Learning connections in financial time series
– start-page: 596
  year: 2019
  ident: 10.1016/j.patcog.2021.108218_bib0038
  article-title: Estimating node importance in knowledge graphs using graph neural networks
– volume: 34
  start-page: 362
  year: 2020
  ident: 10.1016/j.patcog.2021.108218_bib0043
  article-title: Spatio-temporal attention-based neural network for credit card fraud detection
– ident: 10.1016/j.patcog.2021.108218_bib0001
– volume: 19
  start-page: 1499
  issue: 9
  year: 2019
  ident: 10.1016/j.patcog.2021.108218_bib0010
  article-title: Encoding of high-frequency order information and prediction of short-term stock price by deep learning
  publication-title: Quant. Finance
  doi: 10.1080/14697688.2019.1622314
– volume: 109
  start-page: 107617
  year: 2021
  ident: 10.1016/j.patcog.2021.108218_bib0033
  article-title: Implementing transfer learning across different datasets for time series forecasting
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2020.107617
– year: 2009
  ident: 10.1016/j.patcog.2021.108218_bib0026
– volume: 270
  start-page: 654
  issue: 2
  year: 2018
  ident: 10.1016/j.patcog.2021.108218_bib0013
  article-title: Deep learning with long short-term memory networks for financial market predictions
  publication-title: Eur. J. Oper. Res.
  doi: 10.1016/j.ejor.2017.11.054
– volume: 14
  start-page: 367
  issue: 3
  year: 2017
  ident: 10.1016/j.patcog.2021.108218_bib0029
  article-title: Regularised gradient boosting for financial time-series modelling
  publication-title: Comput. Manag. Sci.
  doi: 10.1007/s10287-017-0280-y
– year: 2018
  ident: 10.1016/j.patcog.2021.108218_bib0023
  article-title: Graph attention networks
– year: 2018
  ident: 10.1016/j.patcog.2021.108218_bib0025
– volume: 1
  start-page: 309
  issue: 3
  year: 1933
  ident: 10.1016/j.patcog.2021.108218_bib0004
  article-title: Can stock market forecasters forecast?
  publication-title: Econometrica
  doi: 10.2307/1907042
– volume: 7
  start-page: S165
  issue: S1
  year: 1992
  ident: 10.1016/j.patcog.2021.108218_bib0006
  article-title: Nonlinear time-series analysis of stock volatilities[J]
  publication-title: J. Appl. Econom.
  doi: 10.1002/jae.3950070512
– start-page: 4202
  year: 2019
  ident: 10.1016/j.patcog.2021.108218_bib0037
  article-title: Understanding attention and generalization in graph neural networks
– start-page: 2641
  year: 2018
  ident: 10.1016/j.patcog.2021.108218_bib0008
  article-title: Learning temporal relationships between financial signals
– volume: 107
  start-page: 107382
  year: 2020
  ident: 10.1016/j.patcog.2021.108218_bib0042
  article-title: Dynamic graph convolutional network for multi-video summarization
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2020.107382
– volume: 14
  start-page: 318
  issue: 2
  year: 2019
  ident: 10.1016/j.patcog.2021.108218_bib0045
  article-title: Ensemble of deep convolutional neural networks based multi-modality images for Alzheimer’s disease diagnosis
  publication-title: IET Image Proc.
  doi: 10.1049/iet-ipr.2019.0617
– start-page: 2288
  year: 2018
  ident: 10.1016/j.patcog.2021.108218_bib0020
  article-title: Open information extraction from conjunctive sentences
– volume: 97
  start-page: 107000
  year: 2020
  ident: 10.1016/j.patcog.2021.108218_bib0036
  article-title: Dynamic graph convolutional networks
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2019.107000
– start-page: 15413
  year: 2019
  ident: 10.1016/j.patcog.2021.108218_bib0035
  article-title: Understanding the representation power of graph neural networks in learning graph topology
– start-page: 787
  year: 2017
  ident: 10.1016/j.patcog.2021.108218_bib0041
  article-title: Gram: graph-based attention model for healthcare representation learning
– start-page: 437
  year: 2018
  ident: 10.1016/j.patcog.2021.108218_bib0018
  article-title: Are meta-paths necessary? Revisiting heterogeneous graph embeddings
– volume: 10
  start-page: 146
  issue: 3
  year: 2017
  ident: 10.1016/j.patcog.2021.108218_bib0011
  article-title: Sentiment analysis for effective stock market prediction
  publication-title: Int. J. Intell. Eng. Syst.
SSID ssj0017142
Score 2.715878
Snippet Financial time series analysis plays a central role in hedging market risks and optimizing investment decisions. This is a challenging task as the problems are...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 108218
SubjectTerms Deep learning
Graph attention
Graph neural network
Quantitative investment
Title Financial time series forecasting with multi-modality graph neural network
URI https://dx.doi.org/10.1016/j.patcog.2021.108218
Volume 121
WOSCitedRecordID wos000697672400001&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
  customDbUrl:
  eissn: 1873-5142
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017142
  issn: 0031-3203
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT9wwELZa6KEXSl8qfcmH3pBRbGdj-4goq4IqxIFKe4scP8qiNrtidwHx6zt-JLtbKloOvWQjbzyJMl8m48nMNwh9UpVV0kpPGNMGFijOE0kLT0yjuZamaHxjYrMJcXIiRyN1mqtLZrGdgGhbeXOjpv9V1TAGyg6lsw9Qdy8UBmAflA5bUDts_0nxw55DI_SN3w3ndJF0wRk9m_ex15hJSH5ObHLEI3H1bmC3hIltyg1fdVxPIw9nqH3JCUfLz_cH5y4ZjM_62o17M5ID0UP4vT2fLLrx0biLUIdp3ejX8SLiKfOA5zAEYythiGxaOSWcFXzNtKbq52wcKbgbydjesdsphHCxN4X3z-Q7LNsZ3Vsevk6T_dvrq08q7PLVLuokpQ5S6iTlMdpkYqDA7G3uHx2OjvsPTYKWiVA-X31XXRlTAO9ezZ-9lxWP5GwbbeWlBN5PEHiOHrn2BXrWtenA2Wq_RMc9InBABE6IwCuIwAEReB0ROCICJ0TgjIhX6Nvw8OzgC8ktNIiBteCcsIEuCuu1kcxLbnXhvQnPIlVl1TQK_nXCCt8IJYXT4KcMnGOVsLRS2heV5q_RRjtp3RuEPZW64k3ji5KWFMSUtix1BS6mc9IO-A7i3a2pTeaXD21OftT3KWYHkX7WNPGr_OV40d31OvuIyferAUr3znz7wDO9Q0-XOH-PNuaXC_cBPTFX8_Hs8mPG0S-vtYwj
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=Financial+time+series+forecasting+with+multi-modality+graph+neural+network&rft.jtitle=Pattern+recognition&rft.au=Cheng%2C+Dawei&rft.au=Yang%2C+Fangzhou&rft.au=Xiang%2C+Sheng&rft.au=Liu%2C+Jin&rft.date=2022-01-01&rft.issn=0031-3203&rft.volume=121&rft.spage=108218&rft_id=info:doi/10.1016%2Fj.patcog.2021.108218&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_patcog_2021_108218
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon