Deep learning for credit scoring: Do or don’t?

•Deep learning techniques are compared to both conventional methods and ensemble methods for credit scoring.•This comparison is executed over a significant number of credit scoring data sets stemming from a real-life environment.•The models are evaluated and compared over a number of performance mea...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:European journal of operational research Ročník 295; číslo 1; s. 292 - 305
Hlavní autoři: Gunnarsson, Björn Rafn, vanden Broucke, Seppe, Baesens, Bart, Óskarsdóttir, María, Lemahieu, Wilfried
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 16.11.2021
Témata:
ISSN:0377-2217, 1872-6860
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract •Deep learning techniques are compared to both conventional methods and ensemble methods for credit scoring.•This comparison is executed over a significant number of credit scoring data sets stemming from a real-life environment.•The models are evaluated and compared over a number of performance measures.•Bayesian hypothesis testing is considered and compared to an advanced non-parametric statistical testing procedure. Developing accurate analytical credit scoring models has become a major focus for financial institutions. For this purpose, numerous classification algorithms have been proposed for credit scoring. However, the application of deep learning algorithms for classification has been largely ignored in the credit scoring literature. The main motivation for this research is to consider the appropriateness of deep learning algorithms for credit scoring. To this end two deep learning architectures are constructed, namely a multilayer perceptron network and a deep belief network, and their performance compared to that of two conventional methods and two ensemble methods for credit scoring. The models are then evaluated using a range of credit scoring data sets and performance measures. Furthermore, Bayesian statistical testing procedures are introduced in the context of credit scoring and compared to frequentist non-parametric testing procedures which have traditionally been considered best practice in credit scoring. This comparison will highlight the benefits of Bayesian statistical procedures and secure empirical findings. Two main conclusions emerge from comparing the different classification algorithms for credit scoring. Firstly, the ensemble method, XGBoost, is the best performing method for credit scoring of all the methods considered here. Secondly, deep neural networks do not outperform their shallower counterparts and are considerably more computationally expensive to construct. Therefore, deep learning algorithms do not seem to be appropriate models for credit scoring based on this comparison and XGBoost should be preferred over the other credit scoring methods considered here when classification performance is the main objective of credit scoring activities.
AbstractList •Deep learning techniques are compared to both conventional methods and ensemble methods for credit scoring.•This comparison is executed over a significant number of credit scoring data sets stemming from a real-life environment.•The models are evaluated and compared over a number of performance measures.•Bayesian hypothesis testing is considered and compared to an advanced non-parametric statistical testing procedure. Developing accurate analytical credit scoring models has become a major focus for financial institutions. For this purpose, numerous classification algorithms have been proposed for credit scoring. However, the application of deep learning algorithms for classification has been largely ignored in the credit scoring literature. The main motivation for this research is to consider the appropriateness of deep learning algorithms for credit scoring. To this end two deep learning architectures are constructed, namely a multilayer perceptron network and a deep belief network, and their performance compared to that of two conventional methods and two ensemble methods for credit scoring. The models are then evaluated using a range of credit scoring data sets and performance measures. Furthermore, Bayesian statistical testing procedures are introduced in the context of credit scoring and compared to frequentist non-parametric testing procedures which have traditionally been considered best practice in credit scoring. This comparison will highlight the benefits of Bayesian statistical procedures and secure empirical findings. Two main conclusions emerge from comparing the different classification algorithms for credit scoring. Firstly, the ensemble method, XGBoost, is the best performing method for credit scoring of all the methods considered here. Secondly, deep neural networks do not outperform their shallower counterparts and are considerably more computationally expensive to construct. Therefore, deep learning algorithms do not seem to be appropriate models for credit scoring based on this comparison and XGBoost should be preferred over the other credit scoring methods considered here when classification performance is the main objective of credit scoring activities.
Author vanden Broucke, Seppe
Lemahieu, Wilfried
Gunnarsson, Björn Rafn
Óskarsdóttir, María
Baesens, Bart
Author_xml – sequence: 1
  givenname: Björn Rafn
  orcidid: 0000-0002-5062-5354
  surname: Gunnarsson
  fullname: Gunnarsson, Björn Rafn
  email: bjornrafn.gunnarsson@kuleuven.be
  organization: Research Center for Information Systems Engineering (LIRIS), KU Leuven, Naamsestraat 69, Leuven 3000, Belgium
– sequence: 2
  givenname: Seppe
  surname: vanden Broucke
  fullname: vanden Broucke, Seppe
  email: seppe.vandenbroucke@kuleuven.be
  organization: Research Center for Information Systems Engineering (LIRIS), KU Leuven, Naamsestraat 69, Leuven 3000, Belgium
– sequence: 3
  givenname: Bart
  surname: Baesens
  fullname: Baesens, Bart
  email: bart.baesens@kuleuven.be
  organization: Research Center for Information Systems Engineering (LIRIS), KU Leuven, Naamsestraat 69, Leuven 3000, Belgium
– sequence: 4
  givenname: María
  surname: Óskarsdóttir
  fullname: Óskarsdóttir, María
  email: mariaoskars@ru.is
  organization: Department of Computer Science, Reykjavík University, Menntavegi 1, Reykjavík 101, Iceland
– sequence: 5
  givenname: Wilfried
  surname: Lemahieu
  fullname: Lemahieu, Wilfried
  email: wilfried.lemahieu@kuleuven.be
  organization: Research Center for Information Systems Engineering (LIRIS), KU Leuven, Naamsestraat 69, Leuven 3000, Belgium
BookMark eNp9kM1KAzEURoNUsK2-gKt5gRlvEpOZEUGk9Q8KbnQd0js3kqFOShIEd76Gr-eTOKWuXHR14cD54NwZmwxhIMbOOVQcuL7oK-pDrAQIXoGsAPQRm_KmFqVuNEzYFGRdl0Lw-oTNUuoBgCuupgyWRNtiQzYOfngrXIgFRup8LhKGOKKrYhmKkXZh-Pn6zjen7NjZTaKzvztnr_d3L4vHcvX88LS4XZUotcqlBudAY8fJ6g4vlXOoqGub1gmFsnZ6razTFhDF2rbYNErSCCRy2dp6reScNftdjCGlSM6gzzb7MORo_cZwMLty05tdudmVG5BmLB9V8U_dRv9u4-dh6Xov0Rj14SmahJ4GHH8RCbPpgj-k_wJUbHVz
CitedBy_id crossref_primary_10_1016_j_eswa_2025_126448
crossref_primary_10_1016_j_ejor_2024_12_014
crossref_primary_10_1007_s10115_023_01943_1
crossref_primary_10_1016_j_bar_2023_101241
crossref_primary_10_3390_jrfm15120597
crossref_primary_10_1080_00207543_2023_2257807
crossref_primary_10_1016_j_eswa_2022_118143
crossref_primary_10_1016_j_eswa_2023_119599
crossref_primary_10_1111_jori_12452
crossref_primary_10_3390_sci6040074
crossref_primary_10_1007_s10479_025_06528_5
crossref_primary_10_1016_j_ejor_2025_06_027
crossref_primary_10_1111_exsy_13259
crossref_primary_10_1186_s40537_022_00665_5
crossref_primary_10_1145_3728366
crossref_primary_10_1002_for_2891
crossref_primary_10_1007_s10462_023_10697_9
crossref_primary_10_1016_j_ejor_2021_06_023
crossref_primary_10_1016_j_ejor_2023_08_027
crossref_primary_10_3390_axioms12040402
crossref_primary_10_1080_03081079_2025_2515980
crossref_primary_10_1016_j_jsmc_2021_05_004
crossref_primary_10_1016_j_ejor_2025_01_040
crossref_primary_10_1016_j_eswa_2025_127893
crossref_primary_10_1002_ijfe_3097
crossref_primary_10_1016_j_datak_2025_102490
crossref_primary_10_1016_j_elerap_2023_101292
crossref_primary_10_3846_tede_2022_17045
crossref_primary_10_1016_j_ejor_2023_08_040
crossref_primary_10_1186_s40854_024_00689_1
crossref_primary_10_1016_j_ejor_2022_06_035
crossref_primary_10_1016_j_ejor_2025_04_020
crossref_primary_10_1016_j_aei_2023_102227
crossref_primary_10_1016_j_eswa_2023_119882
crossref_primary_10_1016_j_ejor_2023_08_039
crossref_primary_10_4018_JGIM_308806
crossref_primary_10_1093_jcde_qwad039
crossref_primary_10_1016_j_techfore_2024_123491
crossref_primary_10_3390_math11051137
crossref_primary_10_1007_s10479_023_05209_5
crossref_primary_10_1080_14765284_2022_2162246
crossref_primary_10_1016_j_ejor_2025_01_022
crossref_primary_10_1016_j_ijforecast_2024_07_005
crossref_primary_10_3390_electronics11193181
crossref_primary_10_1007_s10618_023_00985_x
crossref_primary_10_1016_j_techfore_2023_123008
crossref_primary_10_1007_s10479_025_06754_x
crossref_primary_10_1177_14738716231180803
crossref_primary_10_3390_jrfm16040221
crossref_primary_10_1007_s10479_024_06385_8
crossref_primary_10_1109_TKDE_2025_3544284
crossref_primary_10_1016_j_engappai_2025_110009
crossref_primary_10_1016_j_ejor_2023_09_009
crossref_primary_10_1016_j_pacfin_2024_102612
crossref_primary_10_1155_2024_5585575
crossref_primary_10_1016_j_ejor_2024_09_025
crossref_primary_10_1007_s10479_025_06621_9
crossref_primary_10_3846_tede_2025_23060
crossref_primary_10_1007_s10479_023_05259_9
crossref_primary_10_1016_j_heliyon_2024_e39286
crossref_primary_10_1080_01605682_2024_2418882
crossref_primary_10_1080_01605682_2024_2339510
crossref_primary_10_25300_MISQ_2024_18340
crossref_primary_10_1007_s43069_022_00177_1
crossref_primary_10_1103_PhysRevResearch_5_043117
crossref_primary_10_1016_j_jhydrol_2024_131767
crossref_primary_10_1016_j_ejor_2023_11_022
crossref_primary_10_1016_j_ejor_2021_12_024
crossref_primary_10_1016_j_jbusres_2025_115349
crossref_primary_10_1080_01605682_2024_2416908
crossref_primary_10_1016_j_jjimei_2025_100323
crossref_primary_10_1016_j_ejor_2025_01_001
crossref_primary_10_1109_TNNLS_2024_3398559
crossref_primary_10_1016_j_ejor_2024_10_046
crossref_primary_10_1016_j_heliyon_2024_e39770
crossref_primary_10_1111_itor_13467
crossref_primary_10_1016_j_eswa_2022_117013
crossref_primary_10_1016_j_ejor_2025_05_029
crossref_primary_10_1007_s00291_024_00787_7
crossref_primary_10_1016_j_ejor_2023_11_013
crossref_primary_10_1016_j_asoc_2021_108160
crossref_primary_10_1016_j_engappai_2023_106056
crossref_primary_10_1016_j_ejco_2025_100115
crossref_primary_10_1016_j_ejor_2023_03_012
crossref_primary_10_1016_j_ejor_2023_09_026
crossref_primary_10_1109_ACCESS_2023_3286018
crossref_primary_10_1016_j_irfa_2021_101971
crossref_primary_10_1016_j_ribaf_2024_102722
crossref_primary_10_1080_01605682_2025_2485263
crossref_primary_10_1111_jori_12427
crossref_primary_10_3390_systems12070254
crossref_primary_10_3390_info16050397
crossref_primary_10_1016_j_elerap_2022_101155
crossref_primary_10_1016_j_eswa_2022_117363
crossref_primary_10_1016_j_ribaf_2023_102186
crossref_primary_10_1108_JEFAS_09_2021_0193
crossref_primary_10_3233_JCM_247181
crossref_primary_10_2139_ssrn_4496106
crossref_primary_10_1111_obes_12592
crossref_primary_10_1080_00036846_2022_2140769
crossref_primary_10_1016_j_patcog_2022_108701
crossref_primary_10_1016_j_ribaf_2022_101869
crossref_primary_10_1016_j_eswa_2023_121484
crossref_primary_10_3389_fams_2022_1076083
crossref_primary_10_3390_ai5040101
crossref_primary_10_1016_j_ribaf_2024_102397
crossref_primary_10_1016_j_tre_2025_103969
crossref_primary_10_1186_s40854_022_00390_1
crossref_primary_10_3233_JIFS_233141
crossref_primary_10_1016_j_eswa_2024_125327
crossref_primary_10_1016_j_tre_2025_104020
crossref_primary_10_1016_j_ejor_2023_06_036
crossref_primary_10_1016_j_jfds_2022_07_002
crossref_primary_10_1016_j_ejor_2022_04_027
crossref_primary_10_1016_j_ejor_2023_12_028
crossref_primary_10_1007_s11518_025_5663_y
crossref_primary_10_1016_j_asoc_2025_112771
crossref_primary_10_1016_j_ejor_2025_05_039
crossref_primary_10_1016_j_eswa_2024_124072
crossref_primary_10_1016_j_frl_2024_105937
crossref_primary_10_1002_for_70004
crossref_primary_10_1002_ijfe_70012
Cites_doi 10.1016/j.neucom.2013.05.020
10.1002/isaf.1437
10.1016/j.ejor.2012.04.009
10.1023/A:1010933404324
10.3758/s13423-016-1221-4
10.1080/00031305.2016.1154108
10.1016/j.ejor.2014.01.044
10.1016/j.ejor.2014.04.001
10.14569/SpecialIssue.2014.040203
10.1016/j.knosys.2020.105758
10.1016/j.eswa.2018.01.012
10.1007/BF02478259
10.1109/ACCESS.2018.2870052
10.3390/risks6020038
10.1016/j.dss.2017.10.007
10.1109/ACCESS.2018.2887138
10.1016/j.engappai.2016.12.002
10.1016/j.ins.2009.12.010
10.1016/j.eswa.2007.12.020
10.1016/j.eswa.2009.05.024
10.1038/nature14539
10.3390/jrfm11010012
10.1007/s10654-016-0149-3
10.1057/palgrave.jors.2601545
10.1016/j.dss.2019.01.002
10.21314/JCR.2005.025
10.1016/j.neunet.2014.09.003
10.1177/1094428112457829
10.1007/s11518-006-5023-5
10.1016/j.ejor.2015.05.030
10.1016/j.ejor.2019.01.072
10.1016/j.ejor.2019.09.018
10.1016/j.asoc.2018.10.004
10.1016/j.ejor.2021.03.008
10.1016/S0169-7439(97)00061-0
10.1126/science.1127647
10.1109/TASL.2011.2109382
10.1038/506150a
10.1007/s10994-017-5641-9
10.1016/j.eswa.2012.03.033
10.1016/S0031-3203(96)00142-2
10.5120/14249-2444
10.1016/j.eswa.2011.06.023
10.1016/j.dss.2005.10.001
10.1016/j.eswa.2017.02.017
ContentType Journal Article
Copyright 2021 Elsevier B.V.
Copyright_xml – notice: 2021 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.ejor.2021.03.006
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
Business
EISSN 1872-6860
EndPage 305
ExternalDocumentID 10_1016_j_ejor_2021_03_006
S037722172100196X
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1RT
1~.
1~5
4.4
457
4G.
5GY
5VS
6OB
7-5
71M
8P~
9JN
9JO
AAAKF
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARIN
AAXUO
AAYFN
ABAOU
ABBOA
ABFNM
ABFRF
ABJNI
ABMAC
ABUCO
ABYKQ
ACAZW
ACDAQ
ACGFO
ACGFS
ACIWK
ACNCT
ACRLP
ACZNC
ADBBV
ADEZE
ADGUI
AEBSH
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIGVJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
APLSM
ARUGR
AXJTR
BKOJK
BKOMP
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HAMUX
IHE
J1W
KOM
LY1
M41
MHUIS
MO0
MS~
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
ROL
RPZ
RXW
SCC
SDF
SDG
SDP
SDS
SES
SPC
SPCBC
SSB
SSD
SSV
SSW
SSZ
T5K
TAE
TN5
U5U
XPP
ZMT
~02
~G-
1OL
29G
41~
9DU
AAAKG
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADIYS
ADJOM
ADMUD
ADNMO
ADXHL
AEIPS
AEUPX
AFFNX
AFJKZ
AFPUW
AGQPQ
AI.
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
HVGLF
HZ~
R2-
SEW
VH1
WUQ
~HD
ID FETCH-LOGICAL-c365t-60ff06cd1ea6dc45ffc5ed989f25c37f6b5af6a0cc2ba9c8853eaf63c139a7b53
ISICitedReferencesCount 134
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000661773000019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0377-2217
IngestDate Sat Nov 29 07:24:18 EST 2025
Tue Nov 18 22:41:08 EST 2025
Fri Feb 23 02:41:48 EST 2024
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords Decision support systems
Deep learning
Bayesian statistical testing
Risk analysis
Credit scoring
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c365t-60ff06cd1ea6dc45ffc5ed989f25c37f6b5af6a0cc2ba9c8853eaf63c139a7b53
ORCID 0000-0002-5062-5354
PageCount 14
ParticipantIDs crossref_citationtrail_10_1016_j_ejor_2021_03_006
crossref_primary_10_1016_j_ejor_2021_03_006
elsevier_sciencedirect_doi_10_1016_j_ejor_2021_03_006
PublicationCentury 2000
PublicationDate 2021-11-16
PublicationDateYYYYMMDD 2021-11-16
PublicationDate_xml – month: 11
  year: 2021
  text: 2021-11-16
  day: 16
PublicationDecade 2020
PublicationTitle European journal of operational research
PublicationYear 2021
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Thomas, Edelman, Crook (bib0063) 2002
Saberi, Mirtalaie, Hussain, Azadeh, Hussain, Ashjari (bib0056) 2013; 122
Hollander, Wolfe, Chicken (bib0027) 2014; 751
McCulloch, Pitts (bib0047) 1943; 5
Wasserstein, Lazar (bib0072) 2016; 70
Xia, Liu, Li, Liu (bib0073) 2017; 78
Marqués, García, Sánchez (bib0046) 2012; 39
Nuzzo (bib0052) 2014; 506
Kraus, Feuerriegel, Oztekin (bib0034) 2020; 281
Benavoli, Corani, Mangili, Zaffalon, Ruggeri (bib0008) 2014
Wang, Han, Liu, Luo (bib0070) 2018; 7
Huang, Hung, Jiau (bib0031) 2006; 7
Dua, D., & Graff, C. (2017). UCI machine learning repository.
Demšar (bib0015) 2006; 7
Greenland, Senn, Rothman, Carlin, Poole, Goodman, Altman (bib0021) 2016; 31
Xiao, Zhao, Fei (bib0074) 2006; 15
Mancisidor, R. A., Kampffmeyer, M., Aas, K., & Jenssen, R. (2019). Deep generative models for reject inference in credit scoring. arXiv preprint arXiv
Jiang, Wang, Zhao (bib0033) 2019; 277
Van Gestel, Baesens, Van Dijcke, Suykens, Garcia, Alderweireld (bib0066) 2005; 1
Spanoudes, P., & Nguyen, T. (2017). Deep learning in customer churn prediction: Unsupervised feature learning on abstract company independent feature vectors. arXiv preprint arXiv
Vinyals, Ravuri (bib0069) 2011
.
Hosmer, Lemeshow, Sturdivant (bib0028) 2013; 398
Baesens, Van Gestel, Viaene, Stepanova, Suykens, Vanthienen (bib0006) 2003; 54
Hua, Guo, Zhao (bib0030) 2015
Addo, Guegan, Hassani (bib0002) 2018; 6
Akkoç (bib0003) 2012; 222
Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv
Hamori, Kawai, Kume, Murakami, Watanabe (bib0022) 2018; 11
Kruschke, Liddell (bib0037) 2018; 25
Sun, Vasarhelyi (bib0061) 2018; 25
Wang, Yu, Ji (bib0071) 2018
Lopes, Ribeiro (bib0041) 2015
Hssina, Merbouha, Ezzikouri, Erritali (bib0029) 2014; 4
LeCun, Bengio, Hinton (bib0038) 2015; 521
Mohamed, Dahl, Hinton (bib0049) 2012; 20
García, Fernández, Luengo, Herrera (bib0019) 2010; 180
Chen, Guo, Zhao (bib0012) 2020
Verbraken, Bravo, Weber, Baesens (bib0068) 2014; 238
Chen, Guestrin (bib0013) 2016
Hinton, Salakhutdinov (bib0026) 2006; 313
Kruschke, Aguinis, Joo (bib0036) 2012; 15
Benavoli, Corani, Demšar, Zaffalon (bib0007) 2017; 18
Yu, Yao, Wang, Lai (bib0076) 2011; 38
Breiman (bib0011) 2001; 45
Bradley (bib0010) 1997; 30
Van-Sang, Ha-Nam (bib0067) 2016; 54
Corani, Benavoli, Demšar, Mangili, Zaffalon (bib0014) 2017; 106
Maldonado, Bravo, López, Pérez (bib0044) 2017; 104
Munkhdalai, Wang, Park, Ryu (bib0051) 2019
Adadi, Berrada (bib0001) 2018; 6
Kruschke (bib0035) 2011
Van Gestel, Baesens, Van Dijcke, Garcia, Suykens, Vanthienen (bib0065) 2006; 42
Zhou, Lai, Yu (bib0078) 2010; 37
Haykin (bib0023) 1994; 2
Lessmann, Baesens, Seow, Thomas (bib0040) 2015; 247
Board of Governors of the Federal Reserve System (2019). Federal reserve statistical release.
[Online; accessed 28-February-2019].
Goodfellow, Bengio, Courville (bib0020) 2016
Baesens (bib0004) 2014
Lesaffre, Lawson (bib0039) 2012
Luo, Wu, Wu (bib0043) 2017; 65
Svozil, Kvasnicka, Pospichal (bib0062) 1997; 39
Mohamed, Sainath, Dahl, Ramabhadran, Hinton, Picheny (bib0050) 2011
Óskarsdóttir, Bravo, Sarraute, Vanthienen, Baesens (bib0053) 2019; 74
Sharma, Agrawal, Sharma (bib0058) 2013; 82
Mohamed, Dahl, Hinton (bib0048) 2009
Hinton (bib0025) 2012
Zhang, Gao, Shi (bib0077) 2014; 237
Schmidhuber (bib0057) 2015; 61
Lundberg, Lee (bib0042) 2017
Tieleman, Hinton (bib0064) 2012; 4
Papouskova, Hajek (bib0054) 2019; 118
Baesens, Roesch, Scheule (bib0005) 2016
Zhu, Yang, Wang, Yuan (bib0079) 2018
Stevenson, M., Mues, C., & Bravo, C. (2020). The value of text for small business default prediction: A deep learning approach. arXiv preprint arXiv
Deng (bib0016) 2014; 3
Durand (bib0018) 1941
Yeh, Lien (bib0075) 2009; 36
He, Zhang, Zhang (bib0024) 2018; 98
Ribeiro, Singh, Guestrin (bib0055) 2016
Hinton (10.1016/j.ejor.2021.03.006_bib0026) 2006; 313
Wasserstein (10.1016/j.ejor.2021.03.006_bib0072) 2016; 70
Yu (10.1016/j.ejor.2021.03.006_bib0076) 2011; 38
Sharma (10.1016/j.ejor.2021.03.006_bib0058) 2013; 82
10.1016/j.ejor.2021.03.006_bib0009
He (10.1016/j.ejor.2021.03.006_bib0024) 2018; 98
Kruschke (10.1016/j.ejor.2021.03.006_bib0037) 2018; 25
Lopes (10.1016/j.ejor.2021.03.006_bib0041) 2015
Schmidhuber (10.1016/j.ejor.2021.03.006_bib0057) 2015; 61
García (10.1016/j.ejor.2021.03.006_bib0019) 2010; 180
10.1016/j.ejor.2021.03.006_bib0045
Hinton (10.1016/j.ejor.2021.03.006_bib0025) 2012
Thomas (10.1016/j.ejor.2021.03.006_bib0063) 2002
Van Gestel (10.1016/j.ejor.2021.03.006_bib0066) 2005; 1
Baesens (10.1016/j.ejor.2021.03.006_bib0004) 2014
Chen (10.1016/j.ejor.2021.03.006_bib0013) 2016
Mohamed (10.1016/j.ejor.2021.03.006_sbref0048) 2009
Zhang (10.1016/j.ejor.2021.03.006_bib0077) 2014; 237
10.1016/j.ejor.2021.03.006_bib0017
Xia (10.1016/j.ejor.2021.03.006_bib0073) 2017; 78
Bradley (10.1016/j.ejor.2021.03.006_bib0010) 1997; 30
Baesens (10.1016/j.ejor.2021.03.006_bib0005) 2016
Saberi (10.1016/j.ejor.2021.03.006_bib0056) 2013; 122
Kruschke (10.1016/j.ejor.2021.03.006_bib0036) 2012; 15
Goodfellow (10.1016/j.ejor.2021.03.006_bib0020) 2016
Greenland (10.1016/j.ejor.2021.03.006_bib0021) 2016; 31
Munkhdalai (10.1016/j.ejor.2021.03.006_bib0051) 2019
Chen (10.1016/j.ejor.2021.03.006_bib0012) 2020
Hamori (10.1016/j.ejor.2021.03.006_bib0022) 2018; 11
LeCun (10.1016/j.ejor.2021.03.006_bib0038) 2015; 521
10.1016/j.ejor.2021.03.006_bib0059
Xiao (10.1016/j.ejor.2021.03.006_bib0074) 2006; 15
Benavoli (10.1016/j.ejor.2021.03.006_bib0007) 2017; 18
Lesaffre (10.1016/j.ejor.2021.03.006_bib0039) 2012
Svozil (10.1016/j.ejor.2021.03.006_bib0062) 1997; 39
Demšar (10.1016/j.ejor.2021.03.006_bib0015) 2006; 7
Yeh (10.1016/j.ejor.2021.03.006_bib0075) 2009; 36
Kruschke (10.1016/j.ejor.2021.03.006_bib0035) 2011
Addo (10.1016/j.ejor.2021.03.006_bib0002) 2018; 6
Durand (10.1016/j.ejor.2021.03.006_bib0018) 1941
Kraus (10.1016/j.ejor.2021.03.006_bib0034) 2020; 281
Ribeiro (10.1016/j.ejor.2021.03.006_bib0055) 2016
Zhu (10.1016/j.ejor.2021.03.006_bib0079) 2018
Hollander (10.1016/j.ejor.2021.03.006_bib0027) 2014; 751
Maldonado (10.1016/j.ejor.2021.03.006_bib0044) 2017; 104
Zhou (10.1016/j.ejor.2021.03.006_bib0078) 2010; 37
Van-Sang (10.1016/j.ejor.2021.03.006_bib0067) 2016; 54
Huang (10.1016/j.ejor.2021.03.006_bib0031) 2006; 7
Adadi (10.1016/j.ejor.2021.03.006_bib0001) 2018; 6
Marqués (10.1016/j.ejor.2021.03.006_bib0046) 2012; 39
Tieleman (10.1016/j.ejor.2021.03.006_bib0064) 2012; 4
Lessmann (10.1016/j.ejor.2021.03.006_bib0040) 2015; 247
Deng (10.1016/j.ejor.2021.03.006_bib0016) 2014; 3
Papouskova (10.1016/j.ejor.2021.03.006_bib0054) 2019; 118
10.1016/j.ejor.2021.03.006_bib0060
Verbraken (10.1016/j.ejor.2021.03.006_bib0068) 2014; 238
Haykin (10.1016/j.ejor.2021.03.006_bib0023) 1994; 2
McCulloch (10.1016/j.ejor.2021.03.006_bib0047) 1943; 5
Van Gestel (10.1016/j.ejor.2021.03.006_bib0065) 2006; 42
Mohamed (10.1016/j.ejor.2021.03.006_bib0049) 2012; 20
Mohamed (10.1016/j.ejor.2021.03.006_bib0050) 2011
Hua (10.1016/j.ejor.2021.03.006_bib0030) 2015
Akkoç (10.1016/j.ejor.2021.03.006_bib0003) 2012; 222
Hssina (10.1016/j.ejor.2021.03.006_bib0029) 2014; 4
Lundberg (10.1016/j.ejor.2021.03.006_bib0042) 2017
Hosmer (10.1016/j.ejor.2021.03.006_bib0028) 2013; 398
Óskarsdóttir (10.1016/j.ejor.2021.03.006_bib0053) 2019; 74
10.1016/j.ejor.2021.03.006_bib0032
Nuzzo (10.1016/j.ejor.2021.03.006_bib0052) 2014; 506
Corani (10.1016/j.ejor.2021.03.006_bib0014) 2017; 106
Luo (10.1016/j.ejor.2021.03.006_bib0043) 2017; 65
Baesens (10.1016/j.ejor.2021.03.006_bib0006) 2003; 54
Sun (10.1016/j.ejor.2021.03.006_bib0061) 2018; 25
Wang (10.1016/j.ejor.2021.03.006_bib0071) 2018
Wang (10.1016/j.ejor.2021.03.006_bib0070) 2018; 7
Benavoli (10.1016/j.ejor.2021.03.006_bib0008) 2014
Vinyals (10.1016/j.ejor.2021.03.006_bib0069) 2011
Breiman (10.1016/j.ejor.2021.03.006_bib0011) 2001; 45
Jiang (10.1016/j.ejor.2021.03.006_bib0033) 2019; 277
References_xml – volume: 2
  year: 1994
  ident: bib0023
  article-title: Neural networks
– reference: Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:
– start-page: 1135
  year: 2016
  end-page: 1144
  ident: bib0055
  article-title: “Why should I trust you?” Explaining the predictions of any classifier
  publication-title: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining
– volume: 6
  start-page: 52138
  year: 2018
  end-page: 52160
  ident: bib0001
  article-title: Peeking inside the black-box: A survey on explainable artificial intelligence (XAI)
  publication-title: IEEE Access
– reference: Stevenson, M., Mues, C., & Bravo, C. (2020). The value of text for small business default prediction: A deep learning approach. arXiv preprint arXiv:
– start-page: 4596
  year: 2011
  end-page: 4599
  ident: bib0069
  article-title: Comparing multilayer perceptron to deep belief network tandem features for robust ASR
  publication-title: Proceedings of the 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP)
– start-page: 785
  year: 2016
  end-page: 794
  ident: bib0013
  article-title: XGBoost: A scalable tree boosting system
  publication-title: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining
– start-page: 5060
  year: 2011
  end-page: 5063
  ident: bib0050
  article-title: Deep belief networks using discriminative features for phone recognition.
  publication-title: Proceedings of the ICASSP
– volume: 3
  year: 2014
  ident: bib0016
  article-title: A tutorial survey of architectures, algorithms, and applications for deep learning
  publication-title: APSIPA Transactions on Signal and Information Processing
– volume: 237
  start-page: 335
  year: 2014
  end-page: 348
  ident: bib0077
  article-title: Credit risk evaluation using multi-criteria optimization classifier with kernel, fuzzification and penalty factors
  publication-title: European Journal of Operational Research
– volume: 39
  start-page: 10916
  year: 2012
  end-page: 10922
  ident: bib0046
  article-title: Two-level classifier ensembles for credit risk assessment
  publication-title: Expert Systems with Applications
– start-page: 205
  year: 2018
  end-page: 208
  ident: bib0079
  article-title: A hybrid deep learning model for consumer credit scoring
  publication-title: Proceedings of the 2018 international conference on artificial intelligence and big data (ICAIBD)
– volume: 45
  start-page: 5
  year: 2001
  end-page: 32
  ident: bib0011
  article-title: Random forests
  publication-title: Machine Learning
– volume: 30
  start-page: 1145
  year: 1997
  end-page: 1159
  ident: bib0010
  article-title: The use of the area under the ROC curve in the evaluation of machine learning algorithms
  publication-title: Pattern Recognition
– start-page: 599
  year: 2012
  end-page: 619
  ident: bib0025
  article-title: A practical guide to training restricted Boltzmann machines
  publication-title: Neural networks: Tricks of the trade
– volume: 4
  year: 2014
  ident: bib0029
  article-title: A comparative study of decision tree ID3 and C4.5
  publication-title: International Journal of Advanced Computer Science and Applications
– year: 2020
  ident: bib0012
  article-title: Predicting mortgage early delinquency with machine learning methods
  publication-title: European Journal of Operational Research
– start-page: 407
  year: 2019
  end-page: 419
  ident: bib0051
  article-title: Advanced neural network approach, its explanation with lime for credit scoring application
  publication-title: Proceedings of the Asian conference on intelligent information and database systems
– volume: 7
  start-page: 2161
  year: 2018
  end-page: 2168
  ident: bib0070
  article-title: A deep learning approach for credit scoring of peer-to-peer lending using attention mechanism LSTM
  publication-title: IEEE Access
– volume: 222
  start-page: 168
  year: 2012
  end-page: 178
  ident: bib0003
  article-title: An empirical comparison of conventional techniques, neural networks and the three stage hybrid adaptive neuro fuzzy inference system (ANFIS) model for credit scoring analysis: The case of turkish credit card data
  publication-title: European Journal of Operational Research
– start-page: 39
  year: 2009
  ident: bib0048
  article-title: Deep belief networks for phone recognition
  publication-title: Proceedings of the NIPS workshop on deep learning for speech recognition and related applications
– reference: Dua, D., & Graff, C. (2017). UCI machine learning repository.
– volume: 65
  start-page: 465
  year: 2017
  end-page: 470
  ident: bib0043
  article-title: A deep learning approach for credit scoring using credit default swaps
  publication-title: Engineering Applications of Artificial Intelligence
– volume: 122
  start-page: 100
  year: 2013
  end-page: 115
  ident: bib0056
  article-title: A granular computing-based approach to credit scoring modeling
  publication-title: Neurocomputing
– volume: 751
  year: 2014
  ident: bib0027
  article-title: Nonparametric statistical methods
– reference: Mancisidor, R. A., Kampffmeyer, M., Aas, K., & Jenssen, R. (2019). Deep generative models for reject inference in credit scoring. arXiv preprint arXiv:
– reference: . [Online; accessed 28-February-2019].
– volume: 15
  start-page: 419
  year: 2006
  end-page: 435
  ident: bib0074
  article-title: A comparative study of data mining methods in consumer loans credit scoring management
  publication-title: Journal of Systems Science and Systems Engineering
– volume: 15
  start-page: 722
  year: 2012
  end-page: 752
  ident: bib0036
  article-title: The time has come: Bayesian methods for data analysis in the organizational sciences
  publication-title: Organizational Research Methods
– reference: Spanoudes, P., & Nguyen, T. (2017). Deep learning in customer churn prediction: Unsupervised feature learning on abstract company independent feature vectors. arXiv preprint arXiv:
– volume: 74
  start-page: 26
  year: 2019
  end-page: 39
  ident: bib0053
  article-title: The value of big data for credit scoring: Enhancing financial inclusion using mobile phone data and social network analytics
  publication-title: Applied Soft Computing
– year: 2016
  ident: bib0005
  article-title: Credit risk analytics: Measurement techniques, applications, and examples in SAS
– volume: 82
  year: 2013
  ident: bib0058
  article-title: Classification through machine learning technique: C4.5 algorithm based on various entropies
  publication-title: International Journal of Computer Applications
– volume: 11
  start-page: 12
  year: 2018
  ident: bib0022
  article-title: Ensemble learning or deep learning? Application to default risk analysis
  publication-title: Journal of Risk and Financial Management
– year: 2014
  ident: bib0004
  article-title: Analytics in a big data world: The essential guide to data science and its applications
– reference: Board of Governors of the Federal Reserve System (2019). Federal reserve statistical release.
– volume: 31
  start-page: 337
  year: 2016
  end-page: 350
  ident: bib0021
  article-title: Statistical tests,
  publication-title: European Journal of Epidemiology
– volume: 281
  start-page: 628
  year: 2020
  end-page: 641
  ident: bib0034
  article-title: Deep learning in business analytics and operations research: Models, applications and managerial implications
  publication-title: European Journal of Operational Research
– start-page: 1
  year: 2015
  end-page: 4
  ident: bib0030
  article-title: Deep belief networks and deep learning
  publication-title: Proceedings of the 2014 international conference on intelligent computing and internet of things (ICIT)
– year: 2002
  ident: bib0063
  article-title: Credit scoring and its applications
– volume: 104
  start-page: 113
  year: 2017
  end-page: 121
  ident: bib0044
  article-title: Integrated framework for profit-based feature selection and SVM classification in credit scoring
  publication-title: Decision Support Systems
– year: 2012
  ident: bib0039
  article-title: Bayesian biostatistics
– volume: 54
  year: 2016
  ident: bib0067
  article-title: Credit scoring with a feature selection approach based deep learning
  publication-title: Proceedings of the MATEC web of conferences
– start-page: 1026
  year: 2014
  end-page: 1034
  ident: bib0008
  article-title: A Bayesian Wilcoxon signed-rank test based on the Dirichlet process
  publication-title: Proceedings of the international conference on machine learning
– volume: 180
  start-page: 2044
  year: 2010
  end-page: 2064
  ident: bib0019
  article-title: Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: Experimental analysis of power
  publication-title: Information Sciences
– volume: 313
  start-page: 504
  year: 2006
  end-page: 507
  ident: bib0026
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
– volume: 6
  start-page: 38
  year: 2018
  ident: bib0002
  article-title: Credit risk analysis using machine and deep learning models
  publication-title: Risks
– volume: 398
  year: 2013
  ident: bib0028
  article-title: Applied logistic regression
– volume: 4
  start-page: 26
  year: 2012
  end-page: 31
  ident: bib0064
  article-title: Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude
  publication-title: COURSERA: Neural Networks for Machine Learning
– volume: 70
  start-page: 129
  year: 2016
  end-page: 133
  ident: bib0072
  article-title: The ASA’s statement on
  publication-title: The American Statistician
– volume: 36
  start-page: 2473
  year: 2009
  end-page: 2480
  ident: bib0075
  article-title: The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients
  publication-title: Expert Systems with Applications
– volume: 1
  year: 2005
  ident: bib0066
  article-title: Linear and nonlinear credit scoring by combining logistic regression and support vector machines
  publication-title: Journal of Credit Risk
– volume: 238
  start-page: 505
  year: 2014
  end-page: 513
  ident: bib0068
  article-title: Development and application of consumer credit scoring models using profit-based classification measures
  publication-title: European Journal of Operational Research
– volume: 106
  start-page: 1817
  year: 2017
  end-page: 1837
  ident: bib0014
  article-title: Statistical comparison of classifiers through Bayesian hierarchical modelling
  publication-title: Machine Learning
– volume: 20
  start-page: 14
  year: 2012
  end-page: 22
  ident: bib0049
  article-title: Acoustic modeling using deep belief networks
  publication-title: IEEE Transactions on Audio, Speech, and Language Processing
– volume: 54
  start-page: 627
  year: 2003
  end-page: 635
  ident: bib0006
  article-title: Benchmarking state-of-the-art classification algorithms for credit scoring
  publication-title: Journal of the Operational Research Society
– year: 1941
  ident: bib0018
  article-title: Risk elements in consumer installment financing
– year: 2011
  ident: bib0035
  article-title: Doing Bayesian data analysis: A tutorial with R and BUGS
– volume: 61
  start-page: 85
  year: 2015
  end-page: 117
  ident: bib0057
  article-title: Deep learning in neural networks: An overview
  publication-title: Neural Networks
– volume: 277
  start-page: 20
  year: 2019
  end-page: 31
  ident: bib0033
  article-title: A prediction-driven mixture cure model and its application in credit scoring
  publication-title: European Journal of Operational Research
– volume: 38
  start-page: 15392
  year: 2011
  end-page: 15399
  ident: bib0076
  article-title: Credit risk evaluation using a weighted least squares SVM classifier with design of experiment for parameter selection
  publication-title: Expert Systems with Applications
– volume: 25
  start-page: 174
  year: 2018
  end-page: 189
  ident: bib0061
  article-title: Predicting credit card delinquencies: An application of deep neural networks
  publication-title: Intelligent Systems in Accounting, Finance and Management
– volume: 118
  start-page: 33
  year: 2019
  end-page: 45
  ident: bib0054
  article-title: Two-stage consumer credit risk modelling using heterogeneous ensemble learning
  publication-title: Decision Support Systems
– reference: .
– volume: 247
  start-page: 124
  year: 2015
  end-page: 136
  ident: bib0040
  article-title: Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research
  publication-title: European Journal of Operational Research
– volume: 7
  start-page: 720
  year: 2006
  end-page: 747
  ident: bib0031
  article-title: Evaluation of neural networks and data mining methods on a credit assessment task for class imbalance problem
  publication-title: Nonlinear Analysis: Real World Applications
– volume: 42
  start-page: 1131
  year: 2006
  end-page: 1151
  ident: bib0065
  article-title: A process model to develop an internal rating system: Sovereign credit ratings
  publication-title: Decision Support Systems
– volume: 5
  start-page: 115
  year: 1943
  end-page: 133
  ident: bib0047
  article-title: A logical calculus of the ideas immanent in nervous activity
  publication-title: The Bulletin of Mathematical Biophysics
– volume: 25
  start-page: 178
  year: 2018
  end-page: 206
  ident: bib0037
  article-title: The Bayesian new statistics: Hypothesis testing, estimation, meta-analysis, and power analysis from a Bayesian perspective
  publication-title: Psychonomic Bulletin & Review
– volume: 521
  start-page: 436
  year: 2015
  ident: bib0038
  article-title: Deep learning
  publication-title: Nature
– volume: 98
  start-page: 105
  year: 2018
  end-page: 117
  ident: bib0024
  article-title: A novel ensemble method for credit scoring: Adaption of different imbalance ratios
  publication-title: Expert Systems with Applications
– volume: 78
  start-page: 225
  year: 2017
  end-page: 241
  ident: bib0073
  article-title: A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring
  publication-title: Expert Systems with Applications
– year: 2016
  ident: bib0020
  article-title: Deep learning
– volume: 18
  start-page: 2653
  year: 2017
  end-page: 2688
  ident: bib0007
  article-title: Time for a change: A tutorial for comparing multiple classifiers through Bayesian analysis
  publication-title: The Journal of Machine Learning Research
– start-page: 328
  year: 2018
  end-page: 333
  ident: bib0071
  article-title: Personal credit risk assessment based on stacking ensemble model
  publication-title: Proceedings of the international conference on intelligent information processing
– start-page: 4765
  year: 2017
  end-page: 4774
  ident: bib0042
  article-title: A unified approach to interpreting model predictions
  publication-title: Proceedings of the advances in neural information processing systems
– volume: 39
  start-page: 43
  year: 1997
  end-page: 62
  ident: bib0062
  article-title: Introduction to multi-layer feed-forward neural networks
  publication-title: Chemometrics and Intelligent Laboratory Systems
– volume: 37
  start-page: 127
  year: 2010
  end-page: 133
  ident: bib0078
  article-title: Least squares support vector machines ensemble models for credit scoring
  publication-title: Expert Systems with Applications
– volume: 7
  start-page: 1
  year: 2006
  end-page: 30
  ident: bib0015
  article-title: Statistical comparisons of classifiers over multiple data sets
  publication-title: Journal of Machine Learning Research
– year: 2015
  ident: bib0041
  article-title: Machine learning for adaptive many-core machines – A practical approach
– volume: 506
  start-page: 150
  year: 2014
  ident: bib0052
  article-title: Scientific method: Statistical errors
  publication-title: Nature News
– year: 1941
  ident: 10.1016/j.ejor.2021.03.006_bib0018
– volume: 122
  start-page: 100
  year: 2013
  ident: 10.1016/j.ejor.2021.03.006_bib0056
  article-title: A granular computing-based approach to credit scoring modeling
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2013.05.020
– start-page: 407
  year: 2019
  ident: 10.1016/j.ejor.2021.03.006_bib0051
  article-title: Advanced neural network approach, its explanation with lime for credit scoring application
– volume: 25
  start-page: 174
  issue: 4
  year: 2018
  ident: 10.1016/j.ejor.2021.03.006_bib0061
  article-title: Predicting credit card delinquencies: An application of deep neural networks
  publication-title: Intelligent Systems in Accounting, Finance and Management
  doi: 10.1002/isaf.1437
– volume: 222
  start-page: 168
  issue: 1
  year: 2012
  ident: 10.1016/j.ejor.2021.03.006_bib0003
  article-title: An empirical comparison of conventional techniques, neural networks and the three stage hybrid adaptive neuro fuzzy inference system (ANFIS) model for credit scoring analysis: The case of turkish credit card data
  publication-title: European Journal of Operational Research
  doi: 10.1016/j.ejor.2012.04.009
– volume: 45
  start-page: 5
  issue: 1
  year: 2001
  ident: 10.1016/j.ejor.2021.03.006_bib0011
  article-title: Random forests
  publication-title: Machine Learning
  doi: 10.1023/A:1010933404324
– volume: 25
  start-page: 178
  issue: 1
  year: 2018
  ident: 10.1016/j.ejor.2021.03.006_bib0037
  article-title: The Bayesian new statistics: Hypothesis testing, estimation, meta-analysis, and power analysis from a Bayesian perspective
  publication-title: Psychonomic Bulletin & Review
  doi: 10.3758/s13423-016-1221-4
– volume: 70
  start-page: 129
  issue: 2
  year: 2016
  ident: 10.1016/j.ejor.2021.03.006_bib0072
  article-title: The ASA’s statement on p-values: Context, process, and purpose
  publication-title: The American Statistician
  doi: 10.1080/00031305.2016.1154108
– ident: 10.1016/j.ejor.2021.03.006_bib0009
– volume: 237
  start-page: 335
  issue: 1
  year: 2014
  ident: 10.1016/j.ejor.2021.03.006_bib0077
  article-title: Credit risk evaluation using multi-criteria optimization classifier with kernel, fuzzification and penalty factors
  publication-title: European Journal of Operational Research
  doi: 10.1016/j.ejor.2014.01.044
– volume: 238
  start-page: 505
  issue: 2
  year: 2014
  ident: 10.1016/j.ejor.2021.03.006_bib0068
  article-title: Development and application of consumer credit scoring models using profit-based classification measures
  publication-title: European Journal of Operational Research
  doi: 10.1016/j.ejor.2014.04.001
– volume: 4
  issue: 2
  year: 2014
  ident: 10.1016/j.ejor.2021.03.006_bib0029
  article-title: A comparative study of decision tree ID3 and C4.5
  publication-title: International Journal of Advanced Computer Science and Applications
  doi: 10.14569/SpecialIssue.2014.040203
– start-page: 205
  year: 2018
  ident: 10.1016/j.ejor.2021.03.006_bib0079
  article-title: A hybrid deep learning model for consumer credit scoring
– ident: 10.1016/j.ejor.2021.03.006_bib0045
  doi: 10.1016/j.knosys.2020.105758
– volume: 98
  start-page: 105
  year: 2018
  ident: 10.1016/j.ejor.2021.03.006_bib0024
  article-title: A novel ensemble method for credit scoring: Adaption of different imbalance ratios
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2018.01.012
– volume: 7
  start-page: 1
  issue: Jan
  year: 2006
  ident: 10.1016/j.ejor.2021.03.006_bib0015
  article-title: Statistical comparisons of classifiers over multiple data sets
  publication-title: Journal of Machine Learning Research
– volume: 4
  start-page: 26
  issue: 2
  year: 2012
  ident: 10.1016/j.ejor.2021.03.006_bib0064
  article-title: Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude
  publication-title: COURSERA: Neural Networks for Machine Learning
– volume: 3
  year: 2014
  ident: 10.1016/j.ejor.2021.03.006_bib0016
  article-title: A tutorial survey of architectures, algorithms, and applications for deep learning
  publication-title: APSIPA Transactions on Signal and Information Processing
– year: 2012
  ident: 10.1016/j.ejor.2021.03.006_bib0039
– start-page: 328
  year: 2018
  ident: 10.1016/j.ejor.2021.03.006_bib0071
  article-title: Personal credit risk assessment based on stacking ensemble model
– volume: 5
  start-page: 115
  issue: 4
  year: 1943
  ident: 10.1016/j.ejor.2021.03.006_bib0047
  article-title: A logical calculus of the ideas immanent in nervous activity
  publication-title: The Bulletin of Mathematical Biophysics
  doi: 10.1007/BF02478259
– volume: 6
  start-page: 52138
  year: 2018
  ident: 10.1016/j.ejor.2021.03.006_bib0001
  article-title: Peeking inside the black-box: A survey on explainable artificial intelligence (XAI)
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2018.2870052
– year: 2002
  ident: 10.1016/j.ejor.2021.03.006_bib0063
– start-page: 4596
  year: 2011
  ident: 10.1016/j.ejor.2021.03.006_bib0069
  article-title: Comparing multilayer perceptron to deep belief network tandem features for robust ASR
– volume: 6
  start-page: 38
  issue: 2
  year: 2018
  ident: 10.1016/j.ejor.2021.03.006_bib0002
  article-title: Credit risk analysis using machine and deep learning models
  publication-title: Risks
  doi: 10.3390/risks6020038
– year: 2014
  ident: 10.1016/j.ejor.2021.03.006_bib0004
– start-page: 599
  year: 2012
  ident: 10.1016/j.ejor.2021.03.006_bib0025
  article-title: A practical guide to training restricted Boltzmann machines
– year: 2015
  ident: 10.1016/j.ejor.2021.03.006_bib0041
– volume: 104
  start-page: 113
  year: 2017
  ident: 10.1016/j.ejor.2021.03.006_bib0044
  article-title: Integrated framework for profit-based feature selection and SVM classification in credit scoring
  publication-title: Decision Support Systems
  doi: 10.1016/j.dss.2017.10.007
– volume: 7
  start-page: 2161
  year: 2018
  ident: 10.1016/j.ejor.2021.03.006_bib0070
  article-title: A deep learning approach for credit scoring of peer-to-peer lending using attention mechanism LSTM
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2018.2887138
– volume: 65
  start-page: 465
  year: 2017
  ident: 10.1016/j.ejor.2021.03.006_bib0043
  article-title: A deep learning approach for credit scoring using credit default swaps
  publication-title: Engineering Applications of Artificial Intelligence
  doi: 10.1016/j.engappai.2016.12.002
– volume: 180
  start-page: 2044
  issue: 10
  year: 2010
  ident: 10.1016/j.ejor.2021.03.006_bib0019
  article-title: Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: Experimental analysis of power
  publication-title: Information Sciences
  doi: 10.1016/j.ins.2009.12.010
– volume: 36
  start-page: 2473
  issue: 2
  year: 2009
  ident: 10.1016/j.ejor.2021.03.006_bib0075
  article-title: The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2007.12.020
– year: 2020
  ident: 10.1016/j.ejor.2021.03.006_bib0012
  article-title: Predicting mortgage early delinquency with machine learning methods
  publication-title: European Journal of Operational Research
– volume: 37
  start-page: 127
  issue: 1
  year: 2010
  ident: 10.1016/j.ejor.2021.03.006_bib0078
  article-title: Least squares support vector machines ensemble models for credit scoring
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2009.05.024
– volume: 521
  start-page: 436
  issue: 7553
  year: 2015
  ident: 10.1016/j.ejor.2021.03.006_bib0038
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– ident: 10.1016/j.ejor.2021.03.006_bib0017
– start-page: 4765
  year: 2017
  ident: 10.1016/j.ejor.2021.03.006_bib0042
  article-title: A unified approach to interpreting model predictions
– year: 2016
  ident: 10.1016/j.ejor.2021.03.006_bib0020
– volume: 11
  start-page: 12
  issue: 1
  year: 2018
  ident: 10.1016/j.ejor.2021.03.006_bib0022
  article-title: Ensemble learning or deep learning? Application to default risk analysis
  publication-title: Journal of Risk and Financial Management
  doi: 10.3390/jrfm11010012
– start-page: 1026
  year: 2014
  ident: 10.1016/j.ejor.2021.03.006_bib0008
  article-title: A Bayesian Wilcoxon signed-rank test based on the Dirichlet process
– volume: 31
  start-page: 337
  issue: 4
  year: 2016
  ident: 10.1016/j.ejor.2021.03.006_bib0021
  article-title: Statistical tests, p values, confidence intervals, and power: A guide to misinterpretations
  publication-title: European Journal of Epidemiology
  doi: 10.1007/s10654-016-0149-3
– year: 2011
  ident: 10.1016/j.ejor.2021.03.006_bib0035
– volume: 54
  year: 2016
  ident: 10.1016/j.ejor.2021.03.006_bib0067
  article-title: Credit scoring with a feature selection approach based deep learning
– volume: 54
  start-page: 627
  issue: 6
  year: 2003
  ident: 10.1016/j.ejor.2021.03.006_bib0006
  article-title: Benchmarking state-of-the-art classification algorithms for credit scoring
  publication-title: Journal of the Operational Research Society
  doi: 10.1057/palgrave.jors.2601545
– volume: 118
  start-page: 33
  year: 2019
  ident: 10.1016/j.ejor.2021.03.006_bib0054
  article-title: Two-stage consumer credit risk modelling using heterogeneous ensemble learning
  publication-title: Decision Support Systems
  doi: 10.1016/j.dss.2019.01.002
– volume: 1
  issue: 4
  year: 2005
  ident: 10.1016/j.ejor.2021.03.006_bib0066
  article-title: Linear and nonlinear credit scoring by combining logistic regression and support vector machines
  publication-title: Journal of Credit Risk
  doi: 10.21314/JCR.2005.025
– volume: 18
  start-page: 2653
  issue: 1
  year: 2017
  ident: 10.1016/j.ejor.2021.03.006_bib0007
  article-title: Time for a change: A tutorial for comparing multiple classifiers through Bayesian analysis
  publication-title: The Journal of Machine Learning Research
– start-page: 785
  year: 2016
  ident: 10.1016/j.ejor.2021.03.006_bib0013
  article-title: XGBoost: A scalable tree boosting system
– ident: 10.1016/j.ejor.2021.03.006_bib0059
– volume: 61
  start-page: 85
  year: 2015
  ident: 10.1016/j.ejor.2021.03.006_bib0057
  article-title: Deep learning in neural networks: An overview
  publication-title: Neural Networks
  doi: 10.1016/j.neunet.2014.09.003
– volume: 15
  start-page: 722
  issue: 4
  year: 2012
  ident: 10.1016/j.ejor.2021.03.006_bib0036
  article-title: The time has come: Bayesian methods for data analysis in the organizational sciences
  publication-title: Organizational Research Methods
  doi: 10.1177/1094428112457829
– volume: 15
  start-page: 419
  issue: 4
  year: 2006
  ident: 10.1016/j.ejor.2021.03.006_bib0074
  article-title: A comparative study of data mining methods in consumer loans credit scoring management
  publication-title: Journal of Systems Science and Systems Engineering
  doi: 10.1007/s11518-006-5023-5
– volume: 2
  year: 1994
  ident: 10.1016/j.ejor.2021.03.006_bib0023
– start-page: 5060
  year: 2011
  ident: 10.1016/j.ejor.2021.03.006_bib0050
  article-title: Deep belief networks using discriminative features for phone recognition.
– volume: 247
  start-page: 124
  issue: 1
  year: 2015
  ident: 10.1016/j.ejor.2021.03.006_bib0040
  article-title: Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research
  publication-title: European Journal of Operational Research
  doi: 10.1016/j.ejor.2015.05.030
– volume: 277
  start-page: 20
  issue: 1
  year: 2019
  ident: 10.1016/j.ejor.2021.03.006_bib0033
  article-title: A prediction-driven mixture cure model and its application in credit scoring
  publication-title: European Journal of Operational Research
  doi: 10.1016/j.ejor.2019.01.072
– volume: 281
  start-page: 628
  issue: 3
  year: 2020
  ident: 10.1016/j.ejor.2021.03.006_bib0034
  article-title: Deep learning in business analytics and operations research: Models, applications and managerial implications
  publication-title: European Journal of Operational Research
  doi: 10.1016/j.ejor.2019.09.018
– start-page: 1
  year: 2015
  ident: 10.1016/j.ejor.2021.03.006_bib0030
  article-title: Deep belief networks and deep learning
– volume: 74
  start-page: 26
  year: 2019
  ident: 10.1016/j.ejor.2021.03.006_bib0053
  article-title: The value of big data for credit scoring: Enhancing financial inclusion using mobile phone data and social network analytics
  publication-title: Applied Soft Computing
  doi: 10.1016/j.asoc.2018.10.004
– ident: 10.1016/j.ejor.2021.03.006_bib0060
  doi: 10.1016/j.ejor.2021.03.008
– start-page: 39
  year: 2009
  ident: 10.1016/j.ejor.2021.03.006_sbref0048
  article-title: Deep belief networks for phone recognition
– volume: 39
  start-page: 43
  issue: 1
  year: 1997
  ident: 10.1016/j.ejor.2021.03.006_bib0062
  article-title: Introduction to multi-layer feed-forward neural networks
  publication-title: Chemometrics and Intelligent Laboratory Systems
  doi: 10.1016/S0169-7439(97)00061-0
– volume: 313
  start-page: 504
  issue: 5786
  year: 2006
  ident: 10.1016/j.ejor.2021.03.006_bib0026
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
  doi: 10.1126/science.1127647
– year: 2016
  ident: 10.1016/j.ejor.2021.03.006_bib0005
– volume: 20
  start-page: 14
  issue: 1
  year: 2012
  ident: 10.1016/j.ejor.2021.03.006_bib0049
  article-title: Acoustic modeling using deep belief networks
  publication-title: IEEE Transactions on Audio, Speech, and Language Processing
  doi: 10.1109/TASL.2011.2109382
– start-page: 1135
  year: 2016
  ident: 10.1016/j.ejor.2021.03.006_bib0055
  article-title: “Why should I trust you?” Explaining the predictions of any classifier
– volume: 506
  start-page: 150
  issue: 7487
  year: 2014
  ident: 10.1016/j.ejor.2021.03.006_bib0052
  article-title: Scientific method: Statistical errors
  publication-title: Nature News
  doi: 10.1038/506150a
– volume: 398
  year: 2013
  ident: 10.1016/j.ejor.2021.03.006_bib0028
– volume: 106
  start-page: 1817
  issue: 11
  year: 2017
  ident: 10.1016/j.ejor.2021.03.006_bib0014
  article-title: Statistical comparison of classifiers through Bayesian hierarchical modelling
  publication-title: Machine Learning
  doi: 10.1007/s10994-017-5641-9
– volume: 39
  start-page: 10916
  issue: 12
  year: 2012
  ident: 10.1016/j.ejor.2021.03.006_bib0046
  article-title: Two-level classifier ensembles for credit risk assessment
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2012.03.033
– volume: 30
  start-page: 1145
  issue: 7
  year: 1997
  ident: 10.1016/j.ejor.2021.03.006_bib0010
  article-title: The use of the area under the ROC curve in the evaluation of machine learning algorithms
  publication-title: Pattern Recognition
  doi: 10.1016/S0031-3203(96)00142-2
– volume: 82
  issue: 16
  year: 2013
  ident: 10.1016/j.ejor.2021.03.006_bib0058
  article-title: Classification through machine learning technique: C4.5 algorithm based on various entropies
  publication-title: International Journal of Computer Applications
  doi: 10.5120/14249-2444
– volume: 38
  start-page: 15392
  issue: 12
  year: 2011
  ident: 10.1016/j.ejor.2021.03.006_bib0076
  article-title: Credit risk evaluation using a weighted least squares SVM classifier with design of experiment for parameter selection
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2011.06.023
– volume: 751
  year: 2014
  ident: 10.1016/j.ejor.2021.03.006_bib0027
– volume: 42
  start-page: 1131
  issue: 2
  year: 2006
  ident: 10.1016/j.ejor.2021.03.006_bib0065
  article-title: A process model to develop an internal rating system: Sovereign credit ratings
  publication-title: Decision Support Systems
  doi: 10.1016/j.dss.2005.10.001
– volume: 78
  start-page: 225
  year: 2017
  ident: 10.1016/j.ejor.2021.03.006_bib0073
  article-title: A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring
  publication-title: Expert Systems with Applications
  doi: 10.1016/j.eswa.2017.02.017
– volume: 7
  start-page: 720
  issue: 4
  year: 2006
  ident: 10.1016/j.ejor.2021.03.006_bib0031
  article-title: Evaluation of neural networks and data mining methods on a credit assessment task for class imbalance problem
  publication-title: Nonlinear Analysis: Real World Applications
– ident: 10.1016/j.ejor.2021.03.006_bib0032
SSID ssj0001515
Score 2.6843553
Snippet •Deep learning techniques are compared to both conventional methods and ensemble methods for credit scoring.•This comparison is executed over a significant...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 292
SubjectTerms Bayesian statistical testing
Credit scoring
Decision support systems
Deep learning
Risk analysis
Title Deep learning for credit scoring: Do or don’t?
URI https://dx.doi.org/10.1016/j.ejor.2021.03.006
Volume 295
WOSCitedRecordID wos000661773000019&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: 1872-6860
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001515
  issn: 0377-2217
  databaseCode: AIEXJ
  dateStart: 19950105
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3NjtMwELZKFyE48FMWsfwpB25VVokdxzYXtEuXP6EVgkXqLUocW2pZJVEaqj3yGjwGr8STMI7tbOmiFSBxiSqrdhLPF894PN8MQk9FoVIGwg5pXCYhaAgSFoTIkJdMQ4dEK9WnzH_Hjo_5fC7ej0bfPRdmfcqqip-diea_ihraQNiGOvsX4h4GhQb4DUKHK4gdrn8k-JlSjS8GYYMkTVLQRTddyT7YzvgAZrWJQzd1PFysg-i2I_w2vfTOYoWG1vsOXZKgwZn8Cgxh2CM7_tbh0hzAH6ZtNf2Q6wF_a-OxrgBPtYnm6B2vqmnOz_VzQ4VauWOQIR7HDCXI6jMMX_bDkq5btI5o1B_0z_JN5wWODYvPciutR-0Cq8YyuRgLMbaczn1lF2bOcJhyW3vAr9zY1uf8BaJuHbYF9pxKJz2z-6K2sI6L5b5a1iY1LI5tvtut1Ny9sv9oHso8E477lELzK2gHMyr4GO0cvDmavx3Uv7EQ-6Mr9xKOqWWDCrfv9HtraMPCObmNbrqtSXBgIXUHjVQ1Qdc8M2KCbvkKIIFTCBN0YyOd5V0UGegFHnoBQC-w0Asc9J4FszqAVgDej6_fuue76NPLo5MXr0NXkSOUJKVdmEZaR6ksY5WnpUyo1pKqUnChMZWE6bSguU7zSEpc5EJysAUVNBAJ-4ycFZTcQ-OqrtR9FBTK2LKSRnFBwUBK8pzzIokV2A5cCUH3UOxnJpMuXb2pmnKa-bjEZWZmMzOzmUUkg9ncQ9OhT2OTtVz6b-onPHPmpjUjM8DHJf0e_GO_h-j6-SfwCI279ot6jK7KdbdYtU8cjH4C5Ayf-A
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=Deep+learning+for+credit+scoring%3A+Do+or+don%E2%80%99t%3F&rft.jtitle=European+journal+of+operational+research&rft.au=Gunnarsson%2C+Bj%C3%B6rn+Rafn&rft.au=vanden+Broucke%2C+Seppe&rft.au=Baesens%2C+Bart&rft.au=%C3%93skarsd%C3%B3ttir%2C+Mar%C3%ADa&rft.date=2021-11-16&rft.pub=Elsevier+B.V&rft.issn=0377-2217&rft.eissn=1872-6860&rft.volume=295&rft.issue=1&rft.spage=292&rft.epage=305&rft_id=info:doi/10.1016%2Fj.ejor.2021.03.006&rft.externalDocID=S037722172100196X
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0377-2217&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0377-2217&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0377-2217&client=summon