Enhanced Financial Fraud Detection via SISAE‐METADES: A Supervised Deep Representation and Dynamic Ensemble Approach

Detecting financial reporting fraud is vital for preserving market integrity and protecting investors from substantial losses. Yet, the challenges of high dimensionality and noisy financial data often undermine the effectiveness of existing financial fraud detection systems. To address these issues,...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International journal of intelligent systems Ročník 2025; číslo 1
Hlavní autori: Wang, Chang, Fang, Sheng, Zhao, Fangsu, Mu, Zongmei
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: 01.01.2025
ISSN:0884-8173, 1098-111X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Detecting financial reporting fraud is vital for preserving market integrity and protecting investors from substantial losses. Yet, the challenges of high dimensionality and noisy financial data often undermine the effectiveness of existing financial fraud detection systems. To address these issues, this study proposes SISAE‐METADES, a novel framework that integrates a supervised input‐enhanced stacked autoencoder (SISAE) with a meta‐learning–based dynamic ensemble selection (METADES) strategy. Unlike conventional stacked autoencoders, SISAE concatenates the original input at each encoding stage and incorporates label supervision, thereby learning task‐relevant and class‐discriminative representations. These enriched deep features improve both the diversity and competence of base classifiers and enable METADES to achieve more reliable local competence estimation. We validate the proposed framework using financial statement data from Chinese A‐share listed companies (2005–2023), covering 71 indicators. Experimental results show that SISAE‐METADES significantly outperforms standalone SISAE, traditional METADES, and several state‐of‐the‐art baselines. In particular, it achieves substantial improvements in accuracy, recall, and F1‐score, underscoring the robustness and effectiveness of combining supervised deep representation learning with dynamic ensemble selection for financial fraud detection. These findings highlight the framework’s practical significance in reducing investor losses, strengthening market confidence, and promoting the stability of the financial system.
AbstractList Detecting financial reporting fraud is vital for preserving market integrity and protecting investors from substantial losses. Yet, the challenges of high dimensionality and noisy financial data often undermine the effectiveness of existing financial fraud detection systems. To address these issues, this study proposes SISAE‐METADES, a novel framework that integrates a supervised input‐enhanced stacked autoencoder (SISAE) with a meta‐learning–based dynamic ensemble selection (METADES) strategy. Unlike conventional stacked autoencoders, SISAE concatenates the original input at each encoding stage and incorporates label supervision, thereby learning task‐relevant and class‐discriminative representations. These enriched deep features improve both the diversity and competence of base classifiers and enable METADES to achieve more reliable local competence estimation. We validate the proposed framework using financial statement data from Chinese A‐share listed companies (2005–2023), covering 71 indicators. Experimental results show that SISAE‐METADES significantly outperforms standalone SISAE, traditional METADES, and several state‐of‐the‐art baselines. In particular, it achieves substantial improvements in accuracy, recall, and F1‐score, underscoring the robustness and effectiveness of combining supervised deep representation learning with dynamic ensemble selection for financial fraud detection. These findings highlight the framework’s practical significance in reducing investor losses, strengthening market confidence, and promoting the stability of the financial system.
Author Zhao, Fangsu
Mu, Zongmei
Fang, Sheng
Wang, Chang
Author_xml – sequence: 1
  givenname: Chang
  orcidid: 0000-0003-4933-5349
  surname: Wang
  fullname: Wang, Chang
– sequence: 2
  givenname: Sheng
  orcidid: 0000-0002-5807-426X
  surname: Fang
  fullname: Fang, Sheng
– sequence: 3
  givenname: Fangsu
  orcidid: 0009-0008-7782-2594
  surname: Zhao
  fullname: Zhao, Fangsu
– sequence: 4
  givenname: Zongmei
  orcidid: 0009-0000-2334-7099
  surname: Mu
  fullname: Mu, Zongmei
BookMark eNotkLFOwzAYhC1UJNrCxAt4R6F2bScuW9QmUKkIiWRgixznt2rUOpGdRurGI_CMPAktdLrT6e6Gb4JGrnWA0D0lj5QKMbOun0kZLxLJr9CYkoWMKKUfIzQmUvJI0oTdoEkIn4RQmnAxRkPmtsppaHBu3clYtcO5V4cGr6AH3dvW4cEqXKyLNPv5-n7NynSVFU84xcWhAz_YAOcudPgdOg8BXK_-Vsqd8qNTe6tx5gLs6x3gtOt8q_T2Fl0btQtwd9EpKvOsXL5Em7fn9TLdRHrOSB8lMdENzGuhuakbkDXhc5KwxBjOFVcaJNSaMxYvpADJqBZgFNFEUBMbBmyKHv5vtW9D8GCqztu98seKkupMrDoRqy7E2C-SymKe
Cites_doi 10.1016/j.ijforecast.2020.03.001
10.1126/science.1127647
10.1016/j.patcog.2014.12.003
10.1016/j.jaccpubpol.2010.06.006
10.5539/ijef.v7n7p178
10.1016/j.frl.2023.104304
10.1109/34.58871
10.1002/for.2294
10.1016/j.knosys.2015.08.011
10.1002/int.22581
10.1109/AIKE.2019.00044
10.1111/acfi.13159
10.1111/jori.12359
10.1007/978-3-642-41822-8_15
10.3390/jtaer18040103
10.1016/j.irfa.2024.103405
10.1016/j.patcog.2007.10.015
10.1016/j.asoc.2018.01.021
10.1007/s41060-024-00524-x
10.1016/j.cosrev.2021.100402
10.1016/j.eswa.2006.02.016
10.1287/mnsc.1100.1174
10.1109/tdsc.2022.3187973
10.1016/j.frl.2021.102477
10.1162/neco.2006.18.7.1527
10.1016/j.knosys.2018.05.037
10.1002/widm.1249
10.1016/j.accinf.2024.100693
10.1016/j.eswa.2017.08.030
10.1016/j.cose.2015.09.005
10.1016/j.patrec.2018.07.013
10.1016/j.eswa.2021.116429
10.1109/tim.2022.3194863
10.1007/s00521-021-05933-8
10.1016/j.dss.2010.11.006
10.1080/14697688.2019.1683599
10.1016/j.dss.2024.114231
10.2307/41703508
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.1155/int/8869784
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1098-111X
ExternalDocumentID 10_1155_int_8869784
GroupedDBID -~X
.3N
.4S
.DC
.GA
.Y3
05W
0R~
10A
1L6
1OB
1OC
24P
31~
33P
3SF
3WU
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5GY
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A03
AAESR
AAEVG
AAMMB
AANHP
AAONW
AASGY
AAXRX
AAYXX
AAZKR
ABCQN
ABCUV
ABDPE
ABEML
ABIJN
ABJCF
ABJNI
ABPVW
ABUWG
ACAHQ
ACBWZ
ACCMX
ACCZN
ACGFS
ACIWK
ACPOU
ACRPL
ACSCC
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADMLS
ADNMO
ADOZA
ADXAS
ADZMN
AEFGJ
AEIMD
AENEX
AFBPY
AFFHD
AFGKR
AFKRA
AFZJQ
AGQPQ
AGXDD
AI.
AIDQK
AIDYY
AIQQE
AIURR
AJXKR
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
AMBMR
AMYDB
ARAPS
ARCSS
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZQEC
AZVAB
BAFTC
BDRZF
BENPR
BFHJK
BGLVJ
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CCPQU
CITATION
CMOOK
CS3
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
DWQXO
EBS
EDO
EJD
F00
F01
F04
FEDTE
G-S
G.N
GNP
GNUQQ
GODZA
H.T
H.X
H13
HBH
HCIFZ
HF~
HHY
HVGLF
HZ~
I-F
IX1
J0M
JPC
K7-
KQQ
LATKE
LAW
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
M59
M7S
MK4
MK~
MRFUL
MRSTM
MSFUL
MSSTM
MVM
MXFUL
MXSTM
N04
N05
N9A
NF~
O66
O8X
O9-
OIG
P2P
P2W
P2X
P4D
PALCI
PHGZM
PHGZT
PIMPY
PQGLB
PQQKQ
PTHSS
Q.N
Q11
QB0
QRW
R.K
RIWAO
RJQFR
ROL
RX1
RYL
SAMSI
SUPJJ
TN5
TUS
UB1
V2E
VH1
W8V
W99
WBKPD
WH7
WIH
WIK
WOHZO
WQJ
WXSBR
WYISQ
WZISG
XG1
XPP
XV2
ZY4
ZZTAW
~IA
~WT
ID FETCH-LOGICAL-c230t-760cde2b5c4fbde8b0420737ff44a4ace8ebc4336985e831c5efa0c051f6f3e3
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001595142200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0884-8173
IngestDate Sat Nov 29 07:05:27 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c230t-760cde2b5c4fbde8b0420737ff44a4ace8ebc4336985e831c5efa0c051f6f3e3
ORCID 0009-0000-2334-7099
0000-0003-4933-5349
0000-0002-5807-426X
0009-0008-7782-2594
OpenAccessLink https://doi.org/10.1155/int/8869784
ParticipantIDs crossref_primary_10_1155_int_8869784
PublicationCentury 2000
PublicationDate 2025-01-00
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – month: 01
  year: 2025
  text: 2025-01-00
PublicationDecade 2020
PublicationTitle International journal of intelligent systems
PublicationYear 2025
References e_1_2_10_22_2
e_1_2_10_23_2
e_1_2_10_20_2
e_1_2_10_21_2
Bishop C. M. (e_1_2_10_30_2) 2006
e_1_2_10_19_2
e_1_2_10_1_2
e_1_2_10_3_2
e_1_2_10_17_2
e_1_2_10_2_2
e_1_2_10_18_2
e_1_2_10_39_2
e_1_2_10_5_2
e_1_2_10_15_2
e_1_2_10_38_2
e_1_2_10_4_2
e_1_2_10_16_2
e_1_2_10_37_2
e_1_2_10_7_2
e_1_2_10_13_2
e_1_2_10_36_2
e_1_2_10_6_2
e_1_2_10_14_2
e_1_2_10_35_2
e_1_2_10_9_2
e_1_2_10_11_2
e_1_2_10_34_2
e_1_2_10_8_2
e_1_2_10_12_2
e_1_2_10_33_2
e_1_2_10_32_2
e_1_2_10_10_2
e_1_2_10_31_2
e_1_2_10_28_2
e_1_2_10_29_2
e_1_2_10_26_2
e_1_2_10_27_2
e_1_2_10_24_2
e_1_2_10_25_2
References_xml – ident: e_1_2_10_10_2
  doi: 10.1016/j.ijforecast.2020.03.001
– ident: e_1_2_10_8_2
  doi: 10.1126/science.1127647
– ident: e_1_2_10_15_2
  doi: 10.1016/j.patcog.2014.12.003
– ident: e_1_2_10_3_2
  doi: 10.1016/j.jaccpubpol.2010.06.006
– ident: e_1_2_10_5_2
  doi: 10.5539/ijef.v7n7p178
– ident: e_1_2_10_12_2
  doi: 10.1016/j.frl.2023.104304
– ident: e_1_2_10_28_2
  doi: 10.1109/34.58871
– ident: e_1_2_10_33_2
  doi: 10.1002/for.2294
– ident: e_1_2_10_18_2
  doi: 10.1016/j.knosys.2015.08.011
– volume-title: Pattern Recognition and Machine Learning
  year: 2006
  ident: e_1_2_10_30_2
– ident: e_1_2_10_22_2
  doi: 10.1002/int.22581
– ident: e_1_2_10_7_2
  doi: 10.1109/AIKE.2019.00044
– ident: e_1_2_10_1_2
  doi: 10.1111/acfi.13159
– ident: e_1_2_10_25_2
  doi: 10.1111/jori.12359
– ident: e_1_2_10_9_2
  doi: 10.1007/978-3-642-41822-8_15
– ident: e_1_2_10_26_2
  doi: 10.3390/jtaer18040103
– ident: e_1_2_10_38_2
  doi: 10.1016/j.irfa.2024.103405
– ident: e_1_2_10_14_2
  doi: 10.1016/j.patcog.2007.10.015
– ident: e_1_2_10_35_2
  doi: 10.1016/j.asoc.2018.01.021
– ident: e_1_2_10_27_2
  doi: 10.1007/s41060-024-00524-x
– ident: e_1_2_10_16_2
  doi: 10.1016/j.cosrev.2021.100402
– ident: e_1_2_10_20_2
  doi: 10.1016/j.eswa.2006.02.016
– ident: e_1_2_10_6_2
  doi: 10.1287/mnsc.1100.1174
– ident: e_1_2_10_23_2
  doi: 10.1109/tdsc.2022.3187973
– ident: e_1_2_10_2_2
  doi: 10.1016/j.frl.2021.102477
– ident: e_1_2_10_13_2
  doi: 10.1162/neco.2006.18.7.1527
– ident: e_1_2_10_34_2
  doi: 10.1016/j.knosys.2018.05.037
– ident: e_1_2_10_29_2
  doi: 10.1002/widm.1249
– ident: e_1_2_10_32_2
  doi: 10.1016/j.accinf.2024.100693
– ident: e_1_2_10_21_2
  doi: 10.1016/j.eswa.2017.08.030
– ident: e_1_2_10_17_2
  doi: 10.1016/j.cose.2015.09.005
– ident: e_1_2_10_24_2
  doi: 10.1016/j.patrec.2018.07.013
– ident: e_1_2_10_4_2
  doi: 10.1016/j.eswa.2021.116429
– ident: e_1_2_10_37_2
  doi: 10.1109/tim.2022.3194863
– ident: e_1_2_10_11_2
  doi: 10.1007/s00521-021-05933-8
– ident: e_1_2_10_19_2
  doi: 10.1016/j.dss.2010.11.006
– ident: e_1_2_10_36_2
  doi: 10.1080/14697688.2019.1683599
– ident: e_1_2_10_31_2
  doi: 10.1016/j.dss.2024.114231
– ident: e_1_2_10_39_2
  doi: 10.2307/41703508
SSID ssj0011745
Score 2.3993495
Snippet Detecting financial reporting fraud is vital for preserving market integrity and protecting investors from substantial losses. Yet, the challenges of high...
SourceID crossref
SourceType Index Database
Title Enhanced Financial Fraud Detection via SISAE‐METADES: A Supervised Deep Representation and Dynamic Ensemble Approach
Volume 2025
WOSCitedRecordID wos001595142200001&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: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1098-111X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011745
  issn: 0884-8173
  databaseCode: P5Z
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 1098-111X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011745
  issn: 0884-8173
  databaseCode: K7-
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Engineering Database
  customDbUrl:
  eissn: 1098-111X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011745
  issn: 0884-8173
  databaseCode: M7S
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1098-111X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011745
  issn: 0884-8173
  databaseCode: BENPR
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 1098-111X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011745
  issn: 0884-8173
  databaseCode: PIMPY
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1098-111X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011745
  issn: 0884-8173
  databaseCode: DRFUL
  dateStart: 19960101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
– providerCode: PRVWIB
  databaseName: Wiley Online Library Open Access
  customDbUrl:
  eissn: 1098-111X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011745
  issn: 0884-8173
  databaseCode: 24P
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3NjtMwELbKLgcu_CP-5cPeVmGb2E4cbhWkAmlZIVpExaVKnPG2Eputtmm1Rx6B9-CteBLGseNkC4flwMWq3E4VZT7Nnz3fEHLAJTqhdKgCHYZxwGOpgzTBnEfzxPjfogyLZmrJcXJyImez9ONg8LPthdl-S6pKXl6mq_-qatxDZZvW2X9Qt_9T3MDPqHRcUe24XkvxWbWwp_pjT6aB0enGXDiuwQ4G3y7zw8n7ySjzVx0-ZFNUycT2qU82K2NB1mBkYGWC9K5JyV1etoPsD7NqDWem-WrkuMn7we7VauMOR4XlAa0dlbSP7L-4-nXT9eDB1Ra1F9Btfl3kTZnXfGmnt1jgNMct59XpGSz7JY1I9EoareXjgQztjJNXYC2zIT5Fwzzrm24jvAvSP32CMPQZS0PjMJYyxrSZd86vPfDf8Yn-pmKTIwkxR_G5E75B9qNEpGhC999-Gn8-9odWmNwJm7TYp3ftoCh-hOJHTrwXAPUimeldctulIHRkoXOPDKC6T-604z2os_YPyLZFEvVIog2SqEcSRSTRBkm_vv9wGHpNR7RDEDUIolcRRBFB1CGItgiiLYIekuk4m755F7gxHYHC_LUOknioSogKobguSpAF-gF0HInWnOc8VyChUJyxOJUCJAuVAJ0PFXoDHWsG7BHZq84reEyokKUoI16WjEc8UcM0EjmLQwgZywst2RNy0L66-cqSscz_oqCn1_vZM3KrA99zsldfbOAFuam29XJ98dIp9zchwoDZ
linkProvider Wiley-Blackwell
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=Enhanced+Financial+Fraud+Detection+via+SISAE%E2%80%90METADES%3A+A+Supervised+Deep+Representation+and+Dynamic+Ensemble+Approach&rft.jtitle=International+journal+of+intelligent+systems&rft.au=Wang%2C+Chang&rft.au=Fang%2C+Sheng&rft.au=Zhao%2C+Fangsu&rft.au=Mu%2C+Zongmei&rft.date=2025-01-01&rft.issn=0884-8173&rft.eissn=1098-111X&rft.volume=2025&rft.issue=1&rft_id=info:doi/10.1155%2Fint%2F8869784&rft.externalDBID=n%2Fa&rft.externalDocID=10_1155_int_8869784
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0884-8173&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0884-8173&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0884-8173&client=summon