A new deep neural network algorithm for multiple stopping with applications in options pricing

In this paper, we propose a deep learning method to solve high-dimensional optimal multiple stopping problems. We represent the policies of multiple stopping problems by the composition of functions. Using the new representation, we approximate the optimal stopping policy recursively with simulation...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Communications in nonlinear science & numerical simulation Jg. 117; S. 106881
Hauptverfasser: Han, Yuecai, Li, Nan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.02.2023
Schlagworte:
ISSN:1007-5704, 1878-7274
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In this paper, we propose a deep learning method to solve high-dimensional optimal multiple stopping problems. We represent the policies of multiple stopping problems by the composition of functions. Using the new representation, we approximate the optimal stopping policy recursively with simulation samples. We also derive lower and upper bounds and confidence intervals for the values. Finally, we apply the algorithm to the pricing of swing options, and it produces accurate results in high-dimensional problems. •A deep learning-based algorithm for optimal multiple stopping problems is introduced.•Lower bounds and upper bounds for the optimal value are constructed.•Applications to high-dimensional swing options are considered.
AbstractList In this paper, we propose a deep learning method to solve high-dimensional optimal multiple stopping problems. We represent the policies of multiple stopping problems by the composition of functions. Using the new representation, we approximate the optimal stopping policy recursively with simulation samples. We also derive lower and upper bounds and confidence intervals for the values. Finally, we apply the algorithm to the pricing of swing options, and it produces accurate results in high-dimensional problems. •A deep learning-based algorithm for optimal multiple stopping problems is introduced.•Lower bounds and upper bounds for the optimal value are constructed.•Applications to high-dimensional swing options are considered.
ArticleNumber 106881
Author Li, Nan
Han, Yuecai
Author_xml – sequence: 1
  givenname: Yuecai
  orcidid: 0000-0001-7403-632X
  surname: Han
  fullname: Han, Yuecai
  organization: Mathematics School of Jilin University, Changchun 130012, China
– sequence: 2
  givenname: Nan
  surname: Li
  fullname: Li, Nan
  email: nli19@mails.jlu.edu.cn
  organization: Mathematics School of Jilin University, Changchun 130012, China
BookMark eNqFkMtOwzAQRS1UJNrCF7DxD6T4kcTJgkVV8ZIqsYEtlmtPiktqR7ZLxd_jtqxYwGquZuaM7twJGjnvAKFrSmaU0PpmM9MuujhjhLHcqZuGnqExbURTCCbKUdaEiKISpLxAkxg3JFNtVY7R2xw72GMDMGSxC6rPJe19-MCqX_tg0_sWdz7g7a5PdugBx-SHwbo13ucZVsPQW62S9S5i67AfTnIIVuelS3TeqT7C1U-dotf7u5fFY7F8fnhazJeF5oSngrYraFeGq24lSkJaqqEUlBOoiSlN07G6zj1uaqoraErRiUrxPCOiYoYxw6eoPd3VwccYoJPapqOrFJTtJSXyEJTcyGNQ8hCUPAWVWf6Lzea3Knz9Q92eKMhvfVoIMmoLToOxAXSSxts_-W-NXocr
CitedBy_id crossref_primary_10_1007_s10614_025_10994_1
crossref_primary_10_1007_s11785_025_01802_7
Cites_doi 10.1287/mnsc.1040.0240
10.1214/10-AAP727
10.1109/72.935083
10.1073/pnas.1718942115
10.1038/nature24270
10.1016/j.cnsns.2021.105989
10.1016/j.neucom.2018.06.056
10.1007/s00780-010-0149-1
10.1016/S0167-6687(96)00004-2
10.1016/j.orl.2010.11.003
10.1145/1390156.1390177
10.1109/CVPR.2016.90
10.1111/j.0960-1627.2004.00205.x
10.1038/nature14539
10.1111/j.1467-9965.2010.00404.x
10.1214/18-AOS1747
ContentType Journal Article
Copyright 2022 Elsevier B.V.
Copyright_xml – notice: 2022 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.cnsns.2022.106881
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISSN 1878-7274
ExternalDocumentID 10_1016_j_cnsns_2022_106881
S1007570422003689
GroupedDBID --K
--M
-01
-0A
-0I
-0Y
-SA
-S~
.~1
0R~
1B1
1RT
1~.
1~5
29F
4.4
457
4G.
5GY
5VR
5VS
7-5
71M
8P~
92M
9D9
9DA
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
ABAOU
ABFNM
ABJNI
ABMAC
ABNEU
ABXDB
ABYKQ
ACAZW
ACDAQ
ACFVG
ACGFS
ACNNM
ACRLP
ADBBV
ADEZE
ADGUI
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AFUIB
AGHFR
AGUBO
AGYEJ
AHJVU
AIEXJ
AIGVJ
AIKHN
AITUG
AIVDX
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ARUGR
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CAJEA
CAJUS
CCEZO
CCVFK
CHBEP
CS3
CUBFJ
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FA0
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
HVGLF
HZ~
IHE
J1W
JJJVA
JUIAU
KOM
M41
MHUIS
MO0
N9A
O-L
O9-
OAUVE
OGIMB
OZT
P-8
P-9
P2P
PC.
Q--
Q-0
Q38
R-A
R-I
R2-
RIG
ROL
RPZ
RT1
RT9
S..
SDF
SDG
SES
SEW
SPC
SPCBC
SPD
SSQ
SST
SSW
SSZ
T5K
T8Q
T8Y
U1F
U1G
U5A
U5I
U5K
UHS
~G-
~LA
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c303t-19be9bd3afb740091ce47130e60d4d8f26691c3d61c5e847f75a360d0752d22d3
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000887744300005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1007-5704
IngestDate Tue Nov 18 21:49:51 EST 2025
Sat Nov 29 07:07:04 EST 2025
Fri Feb 23 02:40:02 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Multiple optimal stopping
Swing options
Monte Carlo
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c303t-19be9bd3afb740091ce47130e60d4d8f26691c3d61c5e847f75a360d0752d22d3
ORCID 0000-0001-7403-632X
ParticipantIDs crossref_citationtrail_10_1016_j_cnsns_2022_106881
crossref_primary_10_1016_j_cnsns_2022_106881
elsevier_sciencedirect_doi_10_1016_j_cnsns_2022_106881
PublicationCentury 2000
PublicationDate February 2023
2023-02-00
PublicationDateYYYYMMDD 2023-02-01
PublicationDate_xml – month: 02
  year: 2023
  text: February 2023
PublicationDecade 2020
PublicationTitle Communications in nonlinear science & numerical simulation
PublicationYear 2023
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References He Kaiming, Zhang Xiangyu, Ren Shaoqing, Sun Jian. Deep Residual Learning for Image Recognition. In: 2016 IEEE conference on computer vision and pattern recognition. 2016, p. 770–8.
Silver, Schrittwieser, Simonyan, Antonoglou, Huang, Guez (b22) 2017; 550
Glasserman (b18) 2003
Fan, Ma, Zhong (b8) 2019
Sutton, Barto (b16) 2018
Kobylanski, Quenez, Rouy-Mironescu (b4) 2011; 21
Marshall, Reesor (b5) 2011; 39
Domingo, Borondo (b9) 2021; 103
Carriere (b6) 1996; 19
Becker, Cheridito, Jentzen (b13) 2019; 20
Ioffe Sergey, Szegedy Christian. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In: Proceedings of the 32nd international conference on machine learning. 2015, p. 448–56.
Bauer, Kohler (b10) 2019; 47
Simonyan Karen, Zisserman Andrew. Very Deep Convolutional Networks for Large-Scale Image Recognition. In: International conference on learning representations. 2015.
Meinshausen, Hambly (b2) 2004; 14
Durrett (b17) 2019
Han, Jentzen, Weinan (b14) 2018; 115
Fakoor Rasool, Ladhak Faisal, Nazi Azade, Huber Manfred. Using deep learning to enhance cancer diagnosis and classification. In: Proceedings of the ICML workshop on the role of machine learning in transforming healthcare. 2013.
Collobert Ronan, Weston Jason. A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning. In: Proceedings of the 25th international conference on machine learning. 2008, p. 160–7.
LeCun, Bengio, Hinton (b19) 2015; 521
Kingma Diederik P, Ba Jimmy Lei. Adam: A Method for Stochastic Optimization. In: International conference on learning representations. 2015.
Kohler, Krzyżak, Todorovic (b12) 2010; 20
Jaillet, Ronn, Tompaidis (b1) 2004; 50
Schoenmakers (b3) 2012; 16
Schmidt-Hieber (b11) 2020; 48
Tsitsiklis, Roy (b7) 2001; 12
Berg, Nyström (b15) 2018; 317
Sutton (10.1016/j.cnsns.2022.106881_b16) 2018
LeCun (10.1016/j.cnsns.2022.106881_b19) 2015; 521
10.1016/j.cnsns.2022.106881_b26
Fan (10.1016/j.cnsns.2022.106881_b8) 2019
Schmidt-Hieber (10.1016/j.cnsns.2022.106881_b11) 2020; 48
Silver (10.1016/j.cnsns.2022.106881_b22) 2017; 550
Jaillet (10.1016/j.cnsns.2022.106881_b1) 2004; 50
Berg (10.1016/j.cnsns.2022.106881_b15) 2018; 317
Marshall (10.1016/j.cnsns.2022.106881_b5) 2011; 39
Carriere (10.1016/j.cnsns.2022.106881_b6) 1996; 19
Durrett (10.1016/j.cnsns.2022.106881_b17) 2019
Becker (10.1016/j.cnsns.2022.106881_b13) 2019; 20
10.1016/j.cnsns.2022.106881_b21
10.1016/j.cnsns.2022.106881_b20
10.1016/j.cnsns.2022.106881_b23
10.1016/j.cnsns.2022.106881_b25
10.1016/j.cnsns.2022.106881_b24
Schoenmakers (10.1016/j.cnsns.2022.106881_b3) 2012; 16
Tsitsiklis (10.1016/j.cnsns.2022.106881_b7) 2001; 12
Domingo (10.1016/j.cnsns.2022.106881_b9) 2021; 103
Kohler (10.1016/j.cnsns.2022.106881_b12) 2010; 20
Kobylanski (10.1016/j.cnsns.2022.106881_b4) 2011; 21
Glasserman (10.1016/j.cnsns.2022.106881_b18) 2003
Han (10.1016/j.cnsns.2022.106881_b14) 2018; 115
Bauer (10.1016/j.cnsns.2022.106881_b10) 2019; 47
Meinshausen (10.1016/j.cnsns.2022.106881_b2) 2004; 14
References_xml – volume: 317
  start-page: 28
  year: 2018
  end-page: 41
  ident: b15
  article-title: A unified deep artificial neural network approach to partial differential equations in complex geometries
  publication-title: Neurocomputing
– volume: 115
  start-page: 8505
  year: 2018
  end-page: 8510
  ident: b14
  article-title: Solving high-dimensional partial differential equations using deep learning
  publication-title: Proc Natl Acad Sci
– volume: 20
  start-page: 383
  year: 2010
  end-page: 410
  ident: b12
  article-title: Pricing of high-dimensional American options by neural networks
  publication-title: Math Finance
– volume: 521
  start-page: 436
  year: 2015
  end-page: 444
  ident: b19
  article-title: Deep learning
  publication-title: Nature
– volume: 14
  start-page: 557
  year: 2004
  end-page: 583
  ident: b2
  article-title: Monte Carlo methods for the valuation of multiple-exercise options
  publication-title: Math Finance
– year: 2019
  ident: b8
  article-title: A selective overview of deep learning
– year: 2019
  ident: b17
  article-title: Probability: theory and examples. Vol. 49
– volume: 19
  start-page: 19
  year: 1996
  end-page: 30
  ident: b6
  article-title: Valuation of the early-exercise price for options using simulations and nonparametric regression
  publication-title: Insurance Math Econ
– volume: 50
  start-page: 909
  year: 2004
  end-page: 921
  ident: b1
  article-title: Valuation of commodity-based swing options
  publication-title: Manage Sci
– reference: Simonyan Karen, Zisserman Andrew. Very Deep Convolutional Networks for Large-Scale Image Recognition. In: International conference on learning representations. 2015.
– reference: Fakoor Rasool, Ladhak Faisal, Nazi Azade, Huber Manfred. Using deep learning to enhance cancer diagnosis and classification. In: Proceedings of the ICML workshop on the role of machine learning in transforming healthcare. 2013.
– volume: 39
  start-page: 17
  year: 2011
  end-page: 21
  ident: b5
  article-title: Forest of stochastic meshes: A new method for valuing high-dimensional swing options
  publication-title: Oper Res Lett
– volume: 12
  start-page: 694
  year: 2001
  end-page: 703
  ident: b7
  article-title: Regression methods for pricing complex American-style options
  publication-title: IEEE Trans Neural Netw
– year: 2003
  ident: b18
  article-title: Monte Carlo methods in financial engineering. Vol. 53
– volume: 550
  start-page: 354
  year: 2017
  end-page: 359
  ident: b22
  article-title: Mastering the game of go without human knowledge
  publication-title: Nature
– reference: Kingma Diederik P, Ba Jimmy Lei. Adam: A Method for Stochastic Optimization. In: International conference on learning representations. 2015.
– volume: 103
  year: 2021
  ident: b9
  article-title: Deep learning methods for the computation of vibrational wavefunctions
  publication-title: Commun Nonlinear Sci Numer Simul
– year: 2018
  ident: b16
  article-title: Reinforcement learning: an introduction
– volume: 48
  start-page: 1875
  year: 2020
  end-page: 1897
  ident: b11
  article-title: Nonparametric regression using deep neural networks with ReLU activation function
  publication-title: Ann Statist
– reference: Collobert Ronan, Weston Jason. A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning. In: Proceedings of the 25th international conference on machine learning. 2008, p. 160–7.
– reference: He Kaiming, Zhang Xiangyu, Ren Shaoqing, Sun Jian. Deep Residual Learning for Image Recognition. In: 2016 IEEE conference on computer vision and pattern recognition. 2016, p. 770–8.
– volume: 16
  start-page: 319
  year: 2012
  end-page: 334
  ident: b3
  article-title: A pure martingale dual for multiple stopping
  publication-title: Finance Stoch
– volume: 21
  start-page: 1365
  year: 2011
  end-page: 1399
  ident: b4
  article-title: Optimal multiple stopping time problem
  publication-title: Ann Appl Probab
– volume: 20
  start-page: 74
  year: 2019
  ident: b13
  article-title: Deep optimal stopping
  publication-title: J Mach Learn Res
– reference: Ioffe Sergey, Szegedy Christian. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In: Proceedings of the 32nd international conference on machine learning. 2015, p. 448–56.
– volume: 47
  start-page: 2261
  year: 2019
  end-page: 2285
  ident: b10
  article-title: On deep learning as a remedy for the curse of dimensionality in nonparametric regression
  publication-title: Ann Statist
– ident: 10.1016/j.cnsns.2022.106881_b25
– volume: 50
  start-page: 909
  issue: 7
  year: 2004
  ident: 10.1016/j.cnsns.2022.106881_b1
  article-title: Valuation of commodity-based swing options
  publication-title: Manage Sci
  doi: 10.1287/mnsc.1040.0240
– volume: 21
  start-page: 1365
  issue: 4
  year: 2011
  ident: 10.1016/j.cnsns.2022.106881_b4
  article-title: Optimal multiple stopping time problem
  publication-title: Ann Appl Probab
  doi: 10.1214/10-AAP727
– volume: 12
  start-page: 694
  issue: 4
  year: 2001
  ident: 10.1016/j.cnsns.2022.106881_b7
  article-title: Regression methods for pricing complex American-style options
  publication-title: IEEE Trans Neural Netw
  doi: 10.1109/72.935083
– volume: 48
  start-page: 1875
  issue: 4
  year: 2020
  ident: 10.1016/j.cnsns.2022.106881_b11
  article-title: Nonparametric regression using deep neural networks with ReLU activation function
  publication-title: Ann Statist
– year: 2019
  ident: 10.1016/j.cnsns.2022.106881_b17
– ident: 10.1016/j.cnsns.2022.106881_b23
– volume: 115
  start-page: 8505
  issue: 34
  year: 2018
  ident: 10.1016/j.cnsns.2022.106881_b14
  article-title: Solving high-dimensional partial differential equations using deep learning
  publication-title: Proc Natl Acad Sci
  doi: 10.1073/pnas.1718942115
– volume: 550
  start-page: 354
  issue: 7676
  year: 2017
  ident: 10.1016/j.cnsns.2022.106881_b22
  article-title: Mastering the game of go without human knowledge
  publication-title: Nature
  doi: 10.1038/nature24270
– volume: 103
  year: 2021
  ident: 10.1016/j.cnsns.2022.106881_b9
  article-title: Deep learning methods for the computation of vibrational wavefunctions
  publication-title: Commun Nonlinear Sci Numer Simul
  doi: 10.1016/j.cnsns.2021.105989
– year: 2019
  ident: 10.1016/j.cnsns.2022.106881_b8
– volume: 317
  start-page: 28
  year: 2018
  ident: 10.1016/j.cnsns.2022.106881_b15
  article-title: A unified deep artificial neural network approach to partial differential equations in complex geometries
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2018.06.056
– year: 2003
  ident: 10.1016/j.cnsns.2022.106881_b18
– volume: 16
  start-page: 319
  issue: 2
  year: 2012
  ident: 10.1016/j.cnsns.2022.106881_b3
  article-title: A pure martingale dual for multiple stopping
  publication-title: Finance Stoch
  doi: 10.1007/s00780-010-0149-1
– volume: 19
  start-page: 19
  issue: 1
  year: 1996
  ident: 10.1016/j.cnsns.2022.106881_b6
  article-title: Valuation of the early-exercise price for options using simulations and nonparametric regression
  publication-title: Insurance Math Econ
  doi: 10.1016/S0167-6687(96)00004-2
– year: 2018
  ident: 10.1016/j.cnsns.2022.106881_b16
– ident: 10.1016/j.cnsns.2022.106881_b24
– ident: 10.1016/j.cnsns.2022.106881_b26
– volume: 39
  start-page: 17
  issue: 1
  year: 2011
  ident: 10.1016/j.cnsns.2022.106881_b5
  article-title: Forest of stochastic meshes: A new method for valuing high-dimensional swing options
  publication-title: Oper Res Lett
  doi: 10.1016/j.orl.2010.11.003
– ident: 10.1016/j.cnsns.2022.106881_b21
  doi: 10.1145/1390156.1390177
– ident: 10.1016/j.cnsns.2022.106881_b20
  doi: 10.1109/CVPR.2016.90
– volume: 14
  start-page: 557
  issue: 4
  year: 2004
  ident: 10.1016/j.cnsns.2022.106881_b2
  article-title: Monte Carlo methods for the valuation of multiple-exercise options
  publication-title: Math Finance
  doi: 10.1111/j.0960-1627.2004.00205.x
– volume: 521
  start-page: 436
  issue: 7553
  year: 2015
  ident: 10.1016/j.cnsns.2022.106881_b19
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– volume: 20
  start-page: 383
  issue: 3
  year: 2010
  ident: 10.1016/j.cnsns.2022.106881_b12
  article-title: Pricing of high-dimensional American options by neural networks
  publication-title: Math Finance
  doi: 10.1111/j.1467-9965.2010.00404.x
– volume: 20
  start-page: 74
  year: 2019
  ident: 10.1016/j.cnsns.2022.106881_b13
  article-title: Deep optimal stopping
  publication-title: J Mach Learn Res
– volume: 47
  start-page: 2261
  issue: 4
  year: 2019
  ident: 10.1016/j.cnsns.2022.106881_b10
  article-title: On deep learning as a remedy for the curse of dimensionality in nonparametric regression
  publication-title: Ann Statist
  doi: 10.1214/18-AOS1747
SSID ssj0016954
Score 2.3769042
Snippet In this paper, we propose a deep learning method to solve high-dimensional optimal multiple stopping problems. We represent the policies of multiple stopping...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 106881
SubjectTerms Deep learning
Monte Carlo
Multiple optimal stopping
Swing options
Title A new deep neural network algorithm for multiple stopping with applications in options pricing
URI https://dx.doi.org/10.1016/j.cnsns.2022.106881
Volume 117
WOSCitedRecordID wos000887744300005&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: 1878-7274
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0016954
  issn: 1007-5704
  databaseCode: AIEXJ
  dateStart: 19960101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELag5cCFN6K85AO3kKqx87CPK1QECFVIFGm5EDn2pKTaulGyi_rzGcdOmrKoAiQu0cobx9HMp8nn8TwIeSV0prNEm9goyOJUqiRWAqoYeJ5UVVJAroaS-R-LoyOxXMpPIdy2H9oJFNaKiwvZ_ldV4xgq26XO_oW6p4fiAP5GpeMV1Y7XP1L8wnUJjwxAG7lilagC60O9I7U6Oe-a9fezIbZwCiV0tQXaySc7P9F2zpBzH_UStZ07gz-Zk9krySXDzdYX3lBdNKYLOWTZjT8WWkV9cxbahV1avsHsfd2AVs0UHdQEwz_3STA-hjGPjrKtZJnBtjqvaFb4bsP74McEbmKRQqVXDLLP5twy7t7PcLqvbW9dpXXGcCwXvuXLL1WzP7vV3GLMRd_lQt4ku6zIJJrC3cX7w-WH6agpl0OrvOntxtJUQxDg1lK_py8zSnJ8j9wJewm68Bi4T26AfUDuhn0FDVa7f0i-LShCgjpIUA8JGiBBJ0hQhAQdIUFHSFAHCTqHBG0sDZCgARKPyJe3h8dv3sWhr0askbCs40RWICvDVV0VaMJlogEpCj-A_MCkRtTI2XCMmzzRGSB7qYtMcfwPBcoMY4Y_JjuIJ3hCqOGg6hRSDhVPmWZCAH41wNQaaW5dyz3CRnGVOhSdd71PVuUYXXhaDjIunYxLL-M98nqa1PqaK9ffno96KAO4PR0sETjXTXz6rxOfkduXqH9OdtbdBl6QW_rHuum7lwFgPwGx6ZdA
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=A+new+deep+neural+network+algorithm+for+multiple+stopping+with+applications+in+options+pricing&rft.jtitle=Communications+in+nonlinear+science+%26+numerical+simulation&rft.au=Han%2C+Yuecai&rft.au=Li%2C+Nan&rft.date=2023-02-01&rft.pub=Elsevier+B.V&rft.issn=1007-5704&rft.eissn=1878-7274&rft.volume=117&rft_id=info:doi/10.1016%2Fj.cnsns.2022.106881&rft.externalDocID=S1007570422003689
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1007-5704&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1007-5704&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1007-5704&client=summon