Gaining insight into crew rostering instances through ML-based sequential assignment

Crew scheduling is typically performed in two stages. First, solving the crew pairing problem generates sequences of flights called pairings. Then, the pairings are assigned to crew members to provide each person with a full schedule. A common way to do this is to solve an optimization problem calle...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	TOP Ročník 32; číslo 3; s. 537 - 578
Hlavní autoři:	Racette, Philippe, Quesnel, Frédéric, Lodi, Andrea, Soumis, François
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Berlin/Heidelberg Springer Berlin Heidelberg 01.10.2024
Témata:	Business and Management Economic Theory/Quantitative Economics/Mathematical Methods Economics Finance Industrial and Production Engineering Insurance Management Operations Research/Decision Theory Optimization Original Paper Statistics for Business 90-08 Computational methods for problems pertaining to operations research and mathematical programming Evolutionary algorithm Machine learning Reinforcement learning Discrete optimization Crew scheduling Crew rostering
ISSN:	1134-5764, 1863-8279
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Crew scheduling is typically performed in two stages. First, solving the crew pairing problem generates sequences of flights called pairings. Then, the pairings are assigned to crew members to provide each person with a full schedule. A common way to do this is to solve an optimization problem called the crew rostering problem (CRP). However, before solving the CRP, the problem instance must be parameterized appropriately while taking different factors such as preassigned days off, crew training, sick leave, reserve duty, or unusual events into account. In this paper, we present a new method for the parameterization of CRP instances for pilots by scheduling planners. A machine learning-based sequential assignment procedure ( seqAsg ) whose arc weights are computed using a policy over state–action pairs for pilots is implemented to generate very fast solutions. We establish a relationship between the quality of the solutions generated by seqAsg and that of solutions produced by a state-of-the-art solver. Based on those results, we formulate recommendations for instance parameterization. Given that the seqAsg procedure takes only a few seconds to run, this allows scheduling workers to reparameterize crew rostering instances many times over the course of the planning process as needed.
AbstractList	Crew scheduling is typically performed in two stages. First, solving the crew pairing problem generates sequences of flights called pairings. Then, the pairings are assigned to crew members to provide each person with a full schedule. A common way to do this is to solve an optimization problem called the crew rostering problem (CRP). However, before solving the CRP, the problem instance must be parameterized appropriately while taking different factors such as preassigned days off, crew training, sick leave, reserve duty, or unusual events into account. In this paper, we present a new method for the parameterization of CRP instances for pilots by scheduling planners. A machine learning-based sequential assignment procedure ( seqAsg ) whose arc weights are computed using a policy over state–action pairs for pilots is implemented to generate very fast solutions. We establish a relationship between the quality of the solutions generated by seqAsg and that of solutions produced by a state-of-the-art solver. Based on those results, we formulate recommendations for instance parameterization. Given that the seqAsg procedure takes only a few seconds to run, this allows scheduling workers to reparameterize crew rostering instances many times over the course of the planning process as needed.
Author	Lodi, Andrea Racette, Philippe Quesnel, Frédéric Soumis, François
Author_xml	– sequence: 1 givenname: Philippe orcidid: 0009-0000-7422-526X surname: Racette fullname: Racette, Philippe email: philippe.racette@gerad.ca organization: Department of Mathematics and Industrial Engineering and GERAD, Polytechnique Montréal, Canada Excellence Research Chair in Data Science for Real-Time Decision-Making, Polytechnique Montréal – sequence: 2 givenname: Frédéric surname: Quesnel fullname: Quesnel, Frédéric organization: Department of Analytics, Operations and Information Technology, Université du Québec à Montréal – sequence: 3 givenname: Andrea surname: Lodi fullname: Lodi, Andrea organization: Canada Excellence Research Chair in Data Science for Real-Time Decision-Making, Polytechnique Montréal, Cornell Tech and Technion-IIT – sequence: 4 givenname: François surname: Soumis fullname: Soumis, François organization: Department of Mathematics and Industrial Engineering and GERAD, Polytechnique Montréal
BookMark	eNp9kMFOAjEQQBuDiYD-gKf9geq0Xdru0RBFE4wXPDfdZQol0MW2xPj3FuHkgdPMZOZNZt6IDEIfkJB7Bg8MQD0mxtQEKPCaAkilqb4iQ6aloJqrZlByJmo6UbK-IaOUNschKWBIFjPrgw-ryofkV-tcYu6rLuJ3FfuUMZ572YYOU5XXsT-s1tX7nLY24bJK-HXAkL3dVjaVDWFXqlty7ew24d05jsnny_Ni-krnH7O36dOcdkKzTNEh1BIQWs2Q8VprkA5kY7lVrZzYRiiuGeNLbJpWOVY7p6VtnBOgwColxkSf9nbl1hTRmc5nm30fcrR-axiYox1zsmOKHfNnx-iC8n_oPvqdjT-XIXGC0v7oBaPZ9IcYyouXqF9YKHqm
CitedBy_id	crossref_primary_10_1007_s11750_024_00688_6
Cites_doi	10.1016/j.ejor.2021.04.032 10.1287/trsc.2019.0892 10.1137/18M1165748 10.1287/opre.46.6.820 10.1287/opre.2022.2267 10.1016/j.ejtl.2020.100020 10.1016/S0965-8564(98)00021-4 10.1007/s10479-007-0216-y 10.1287/opre.47.2.247 10.1287/trsc.1110.0379 10.1016/j.ejor.2020.05.005 10.1016/S0377-2217(96)00195-6 10.1287/trsc.2019.0913 10.1287/trsc.2021.1084 10.1287/trsc.1040.0091 10.1007/978-3-031-20102-8_43 10.1287/opre.1040.0110 10.1016/j.ejor.2019.11.043 10.1007/978-3-642-40137-4 10.1007/s10479-005-3975-3 10.1016/j.ejor.2010.01.040 10.1162/106365601750190398 10.1016/j.cor.2021.105554 10.1007/s11750-011-0245-1 10.1109/TITS.2020.2994779 10.1023/B:ANOR.0000019091.54417.ca 10.1007/3-540-44719-9_34 10.1287/opre.1050.0234 10.1007/s10479-016-2260-y 10.1287/ijoo.2022.0082 10.1016/j.ejtl.2020.100018 10.24963/ijcai.2021/610 10.1287/trsc.2021.1045 10.1007/s13676-015-0080-x 10.1109/CEC.2016.7744084 10.1287/ijoc.1100.0425 10.1007/s00291-020-00615-8 10.1016/j.trb.2009.06.003
ContentType	Journal Article
Copyright	The Author(s) under exclusive licence to Sociedad de Estadística e Investigación Operativa 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Copyright_xml	– notice: The Author(s) under exclusive licence to Sociedad de Estadística e Investigación Operativa 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
DBID	AAYXX CITATION
DOI	10.1007/s11750-024-00678-8
DatabaseName	CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
DeliveryMethod	fulltext_linktorsrc
Discipline	Economics Mathematics
EISSN	1863-8279
EndPage	578
ExternalDocumentID	10_1007_s11750_024_00678_8
GrantInformation_xml	– fundername: Natural Sciences and Engineering Research Council of Canada grantid: CRDPJ-477127-14 funderid: http://dx.doi.org/10.13039/501100000038 – fundername: IBS
GroupedDBID	-4X -57 -5G -BR -EM -Y2 -~C .VR 06D 0R~ 0VY 123 1N0 1SB 2.D 203 29Q 2J2 2JN 2JY 2KG 2LR 2VQ 2~H 30V 4.4 406 408 40D 40E 5VS 67Z 6NX 8TC 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABDZT ABECU ABFTV ABHQN ABJNI ABJOX ABKCH ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACHSB ACIWK ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACSNA ACZOJ ADHHG ADHIR ADINQ ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFEXP AFGCZ AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGWIL AGWZB AGYKE AHAVH AHBYD AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALFXC ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARMRJ ASPBG AVWKF AXYYD AYQZM AZFZN B-. BA0 BAPOH BBWZM BDATZ BGNMA CAG COF CS3 CSCUP DDRTE DNIVK DPUIP DU5 EBLON EBS EIOEI EJD ESBYG FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNWQR GQ6 GQ7 H13 HF~ HG5 HG6 HMJXF HRMNR HVGLF HZ~ IJ- IKXTQ ITM IWAJR IXC IXE IZQ I~X I~Z J-C J0Z JBSCW JZLTJ KDC KOV LLZTM M4Y MA- N2Q NB0 NDZJH NF0 NPVJJ NQJWS NU0 O9- O93 O9G O9I O9J OAM P19 P2P P9M PF0 PT4 PT5 QOK QOS R4E R89 R9I RHV RNI ROL RPX RSV RZK S16 S1Z S26 S27 S28 S3B SAP SBE SCF SCLPG SDH SDM SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 T16 TSG TSK TSV TUC U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W48 WK8 YLTOR Z45 ZMTXR ZYFGU ~A9 ~EX AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC ADHKG AEZWR AFDZB AFHIU AFOHR AGQPQ AHPBZ AHWEU AIXLP ATHPR AYFIA CITATION
ID	FETCH-LOGICAL-c381t-efe0460e0b81e1248806f069a2a7b65a93728112de99b7f14ff86a9ff3070a773
IEDL.DBID	RSV
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001254035700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1134-5764
IngestDate	Sat Nov 29 04:34:06 EST 2025 Tue Nov 18 21:43:55 EST 2025 Fri Feb 21 02:37:05 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	3
Keywords	90-08 Computational methods for problems pertaining to operations research and mathematical programming Evolutionary algorithm Machine learning Reinforcement learning Discrete optimization Crew scheduling Crew rostering
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c381t-efe0460e0b81e1248806f069a2a7b65a93728112de99b7f14ff86a9ff3070a773
ORCID	0009-0000-7422-526X
PageCount	42
ParticipantIDs	crossref_citationtrail_10_1007_s11750_024_00678_8 crossref_primary_10_1007_s11750_024_00678_8 springer_journals_10_1007_s11750_024_00678_8
PublicationCentury	2000
PublicationDate	2024-10-01
PublicationDateYYYYMMDD	2024-10-01
PublicationDate_xml	– month: 10 year: 2024 text: 2024-10-01 day: 01
PublicationDecade	2020
PublicationPlace	Berlin/Heidelberg
PublicationPlace_xml	– name: Berlin/Heidelberg
PublicationSubtitle	Transactions in Operations Research
PublicationTitle	TOP
PublicationTitleAbbrev	TOP
PublicationYear	2024
Publisher	Springer Berlin Heidelberg
Publisher_xml	– name: Springer Berlin Heidelberg
References	FurianNO’SullivanMWalkerCÇelaEA machine learning-based branch and price algorithm for a sampled vehicle routing problemOR Spectr20214369373210.1007/s00291-020-00615-8 Nazari M, Oroojlooy A, Snyder LV, Takáč M (2018) Deep reinforcement learning for solving the vehicle routing problem. Adv Neural Inf Process Syst 31 Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate, arXiv preprint. arXiv:1409.0473 BonamiPLodiAZarpellonGA classifier to decide on the linearization of mixed-integer quadratic problems in CPLEXOper Res20227063303332010.1287/opre.2022.2267 Boufaied C, Trabelsi R, Masri H, Krichen S (2016) A construction of rotations-based rosters with a genetic algorithm. In: 2016 IEEE congress on evolutionary computation (CEC). IEEE, pp 2389–2394 BeulenMScherpLSantosBFDynamic evaluation of airline crew’s flight requests using a neural networkEURO J Transp Logist20209410.1016/j.ejtl.2020.100018 JuanAAFaulinJFerrerALourençoHRBarriosBMIRHA: multi-start biased randomization of heuristics with adaptive local search for solving non-smooth routing problemsTOP20132110913210.1007/s11750-011-0245-1 Salismans T, Ho J, Chen X, Sidor S, Sutskever I (2017) Evolution strategies as a scalable alternative to reinforcement learning. arXiv preprint, arXiv:1703.03864 Vinyals O, Fortunato M, Jaitly N (2015) Pointer networks. Adv Neural Inf Process Syst 28 KasirzadehASaddouneMSoumisFAirline crew scheduling: models, algorithms, and data setsEURO J Transp Logist20176211113710.1007/s13676-015-0080-x Kool W, van Hoof H, Welling M (2019) Attention, learn to solve routing problems! arXiv preprint arXiv:1803.08475 LučicPTeodorovicDSimulated annealing for the multi-objective aircrew rostering problemTransp Res Part A Policy Pract1999331194510.1016/S0965-8564(98)00021-4 Bello I, Pham H, Le QV, Norouzi M, Bengio S (2016) Neural combinatorial optimization with reinforcement learning, arXiv preprint. arXiv:1611.09940 Morabit M, Desaulniers G, Lodi A (2023). Machine-learning-based arc selection for constrained shortest path problems in column generation. INFORMS J Optim 5(2). https://doi.org/10.1287/ijoo.2022.0082 DesaulniersGDesrosiersJDumasYMarcSRiouxBSolomonMMSoumisFCrew pairing at Air FranceEur J Oper Res199797224525910.1016/S0377-2217(96)00195-6 KohlNKarischSEAirline crew rostering: problem types, modeling, and optimizationAnn Oper Res20041271–422325710.1023/B:ANOR.0000019091.54417.ca Karimi-MamaghanMMohammadiMMeyerPKarimi-MamaghanAMTalbiE-GMachine learning at the service of meta-heuristics for solving combinatorial optimization problems: a state-of-the-artEur J Oper Res2022296239342210.1016/j.ejor.2021.04.032 Yaakoubi Y, Soumis F, Lacoste-Julien S (2020a) Flight-connection prediction for airline crew scheduling to construct initial clusters for OR optimizer. arXiv preprint, arXiv:2009.12501 HansenNOstermeierACompletely derandomized self-adaptation in evolution strategiesEvol Comput20019215919510.1162/106365601750190398 El Moudani W, Alberto Nunes Cosenza C, de Coligny M, Mora-Camino F (2001) A bi-criterion approach for the airlines crew rostering problem. In: Evolutionary multi-criterion optimization: first international conference. EMO 2001 Zurich, Switzerland, March 7–9, 2001 Proceedings 1. Springer, pp 486–500 TahirAQuesnelFDesaulniersGElhallaouiIYaakoubiYAn improved integral column generation algorithm using machine learning for aircrew pairingTransp Sci20215561411142910.1287/trsc.2021.1084 CappaneraPGalloGA multicommodity flow approach to the crew rostering problemOper Res200452458359610.1287/opre.1040.0110 ElhallaouiIMetraneADesaulniersGSoumisFAn improved primal simplex algorithm for degenerate linear programsINFORMS J Comput201123456957710.1287/ijoc.1100.0425 GopalakrishnanBJohnsonELAirline crew scheduling: state-of-the-artAnn Oper Res200514030533710.1007/s10479-005-3975-3 Zhou T, Chen X, Wu X, Yang C (2022) A hybrid multi-objective genetic-particle swarm optimization algorithm for airline crew rostering problem with fairness and satisfaction. In: International conference on machine learning for cyber security. Springer, pp 563–575 Quesnel F, Desaulniers G, Soumis F (2020a) A branch-and-price heuristic for the crew pairing problem with language constraints. Eur J Oper Res 283(3):1040–1054. https://doi.org/10.1016/j.ejor.2019.11.043 BäckTFoussetteCKrausePContemporary evolution strategies2013BerlinSpringer10.1007/978-3-642-40137-4 BoubakerKDesaulniersGElhallaouiIBidline scheduling with equity by heuristic dynamic constraint aggregationTransp Res Part B Methodol2010441506110.1016/j.trb.2009.06.003 Quesnel F, Wu A, Desaulniers G, Soumis F (2022) Deep-learning-based partial pricing in a branch-and-price algorithm for personalized crew rostering. Comput Oper Res 138:105554. https://doi.org/10.1016/j.cor.2021.105554 ZeighamiVSoumisFCombining Benders’ decomposition and column generation for integrated crew pairing and personalized crew assignment problemsTransp Sci20195351479149910.1287/trsc.2019.0892 LučićPTeodorovićDMetaheuristics approach to the aircrew rostering problemAnn Oper Res200715531133810.1007/s10479-007-0216-y Quesnel F, Desaulniers G, Soumis F (2020b) Improving air crew rostering by considering crew preferences in the crew pairing problem. Transp Sci 54(1):97–114. https://doi.org/10.1287/trsc.2019.0913 HighamCFHighamDJDeep learning: an introduction for applied mathematiciansSIAM Rev201961486089110.1137/18M1165748 SchaeferAJJohnsonELKleywegtAJNemhauserGLAirline crew scheduling under uncertaintyTransp Sci200539334034810.1287/trsc.1040.0091 Kotary J, Fioretto F, Van Hentenryck P, Wilder B (2021) End-to-end constrained optimization learning: a survey. arXiv preprint arXiv:2103.16378 Yaakoubi Y, Soumis F, Lacoste-Julien S (2020b) Machine learning in airline crew pairing to construct initial clusters for dynamic constraint aggregation. EURO J Transp Logist 9(4):100020. https://doi.org/10.1016/j.ejtl.2020.100020 ZeighamiVSaddouneMSoumisFAlternating lagrangian decomposition for integrated airline crew scheduling problemEur J Oper Res2020287121122410.1016/j.ejor.2020.05.005 LübbeckeMEDesrosiersJSelected topics in column generationOper Res20055361007102310.1287/opre.1050.0234 MorabitMDesaulniersGLodiAMachine-learning-based column selection for column generationTransp Sci202155481583110.1287/trsc.2021.1045 MaenhoutBVanhouckeMA hybrid scatter search heuristic for personalized crew rostering in the airline industryEur J Oper Res2010206115516710.1016/j.ejor.2010.01.040 Silver D, Lever G, Heess N, Degris T, Wierstra D, Riedmiller M (2014). Deterministic policy gradient algorithms. In: International conference on machine learning. PMLR, pp 387–395 ZhouS-ZZhanZ-HChenZ-GKwongSZhangJA multi-objective ant colony system algorithm for airline crew rostering problem with fairness and satisfactionIEEE Trans Intell Transp Syst202022116784679810.1109/TITS.2020.2994779 CapraraATothPVigoDFischettiMModeling and solving the crew rostering problemOper Res199846682083010.1287/opre.46.6.820 de ArmasJCadarsoLJuanAAFaulinJA multi-start randomized heuristic for real-life crew rostering problems in airlines with work-balancing goalsAnn Oper Res201725882584810.1007/s10479-016-2260-y SaddouneMDesaulniersGElhallaouiISoumisFIntegrated airline crew pairing and crew assignment by dynamic constraint aggregationTransp Sci2012461395510.1287/trsc.1110.0379 GamacheMSoumisFMarquisGDesrosiersJA column generation approach for large-scale aircrew rostering problemsOper Res199947224726310.1287/opre.47.2.247 P Bonami (678_CR5) 2022; 70 678_CR24 678_CR46 M Beulen (678_CR4) 2020; 9 678_CR23 CF Higham (678_CR18) 2019; 61 J de Armas (678_CR10) 2017; 258 ME Lübbecke (678_CR25) 2005; 53 M Saddoune (678_CR35) 2012; 46 678_CR42 678_CR41 AJ Schaefer (678_CR37) 2005; 39 678_CR40 B Maenhout (678_CR28) 2010; 206 678_CR3 V Zeighami (678_CR43) 2019; 53 P Cappanera (678_CR8) 2004; 52 B Gopalakrishnan (678_CR16) 2005; 140 T Bäck (678_CR1) 2013 678_CR2 S-Z Zhou (678_CR45) 2020; 22 G Desaulniers (678_CR11) 1997; 97 A Caprara (678_CR9) 1998; 46 I Elhallaoui (678_CR13) 2011; 23 A Kasirzadeh (678_CR21) 2017; 6 678_CR38 678_CR36 678_CR12 678_CR34 M Gamache (678_CR15) 1999; 47 AA Juan (678_CR19) 2013; 21 N Kohl (678_CR22) 2004; 127 678_CR33 A Tahir (678_CR39) 2021; 55 678_CR32 678_CR31 M Karimi-Mamaghan (678_CR20) 2022; 296 678_CR30 678_CR7 P Lučić (678_CR27) 2007; 155 K Boubaker (678_CR6) 2010; 44 N Hansen (678_CR17) 2001; 9 P Lučic (678_CR26) 1999; 33 M Morabit (678_CR29) 2021; 55 N Furian (678_CR14) 2021; 43 V Zeighami (678_CR44) 2020; 287
References_xml	– reference: CapraraATothPVigoDFischettiMModeling and solving the crew rostering problemOper Res199846682083010.1287/opre.46.6.820 – reference: BoubakerKDesaulniersGElhallaouiIBidline scheduling with equity by heuristic dynamic constraint aggregationTransp Res Part B Methodol2010441506110.1016/j.trb.2009.06.003 – reference: Vinyals O, Fortunato M, Jaitly N (2015) Pointer networks. Adv Neural Inf Process Syst 28 – reference: BäckTFoussetteCKrausePContemporary evolution strategies2013BerlinSpringer10.1007/978-3-642-40137-4 – reference: KasirzadehASaddouneMSoumisFAirline crew scheduling: models, algorithms, and data setsEURO J Transp Logist20176211113710.1007/s13676-015-0080-x – reference: Kool W, van Hoof H, Welling M (2019) Attention, learn to solve routing problems! arXiv preprint arXiv:1803.08475 – reference: Quesnel F, Desaulniers G, Soumis F (2020a) A branch-and-price heuristic for the crew pairing problem with language constraints. Eur J Oper Res 283(3):1040–1054. https://doi.org/10.1016/j.ejor.2019.11.043 – reference: KohlNKarischSEAirline crew rostering: problem types, modeling, and optimizationAnn Oper Res20041271–422325710.1023/B:ANOR.0000019091.54417.ca – reference: Quesnel F, Desaulniers G, Soumis F (2020b) Improving air crew rostering by considering crew preferences in the crew pairing problem. Transp Sci 54(1):97–114. https://doi.org/10.1287/trsc.2019.0913 – reference: Quesnel F, Wu A, Desaulniers G, Soumis F (2022) Deep-learning-based partial pricing in a branch-and-price algorithm for personalized crew rostering. Comput Oper Res 138:105554. https://doi.org/10.1016/j.cor.2021.105554 – reference: DesaulniersGDesrosiersJDumasYMarcSRiouxBSolomonMMSoumisFCrew pairing at Air FranceEur J Oper Res199797224525910.1016/S0377-2217(96)00195-6 – reference: SaddouneMDesaulniersGElhallaouiISoumisFIntegrated airline crew pairing and crew assignment by dynamic constraint aggregationTransp Sci2012461395510.1287/trsc.1110.0379 – reference: TahirAQuesnelFDesaulniersGElhallaouiIYaakoubiYAn improved integral column generation algorithm using machine learning for aircrew pairingTransp Sci20215561411142910.1287/trsc.2021.1084 – reference: Zhou T, Chen X, Wu X, Yang C (2022) A hybrid multi-objective genetic-particle swarm optimization algorithm for airline crew rostering problem with fairness and satisfaction. In: International conference on machine learning for cyber security. Springer, pp 563–575 – reference: BeulenMScherpLSantosBFDynamic evaluation of airline crew’s flight requests using a neural networkEURO J Transp Logist20209410.1016/j.ejtl.2020.100018 – reference: El Moudani W, Alberto Nunes Cosenza C, de Coligny M, Mora-Camino F (2001) A bi-criterion approach for the airlines crew rostering problem. In: Evolutionary multi-criterion optimization: first international conference. EMO 2001 Zurich, Switzerland, March 7–9, 2001 Proceedings 1. Springer, pp 486–500 – reference: ZhouS-ZZhanZ-HChenZ-GKwongSZhangJA multi-objective ant colony system algorithm for airline crew rostering problem with fairness and satisfactionIEEE Trans Intell Transp Syst202022116784679810.1109/TITS.2020.2994779 – reference: ZeighamiVSoumisFCombining Benders’ decomposition and column generation for integrated crew pairing and personalized crew assignment problemsTransp Sci20195351479149910.1287/trsc.2019.0892 – reference: Boufaied C, Trabelsi R, Masri H, Krichen S (2016) A construction of rotations-based rosters with a genetic algorithm. In: 2016 IEEE congress on evolutionary computation (CEC). IEEE, pp 2389–2394 – reference: Salismans T, Ho J, Chen X, Sidor S, Sutskever I (2017) Evolution strategies as a scalable alternative to reinforcement learning. arXiv preprint, arXiv:1703.03864 – reference: JuanAAFaulinJFerrerALourençoHRBarriosBMIRHA: multi-start biased randomization of heuristics with adaptive local search for solving non-smooth routing problemsTOP20132110913210.1007/s11750-011-0245-1 – reference: BonamiPLodiAZarpellonGA classifier to decide on the linearization of mixed-integer quadratic problems in CPLEXOper Res20227063303332010.1287/opre.2022.2267 – reference: LübbeckeMEDesrosiersJSelected topics in column generationOper Res20055361007102310.1287/opre.1050.0234 – reference: Bello I, Pham H, Le QV, Norouzi M, Bengio S (2016) Neural combinatorial optimization with reinforcement learning, arXiv preprint. arXiv:1611.09940 – reference: LučicPTeodorovicDSimulated annealing for the multi-objective aircrew rostering problemTransp Res Part A Policy Pract1999331194510.1016/S0965-8564(98)00021-4 – reference: MorabitMDesaulniersGLodiAMachine-learning-based column selection for column generationTransp Sci202155481583110.1287/trsc.2021.1045 – reference: HighamCFHighamDJDeep learning: an introduction for applied mathematiciansSIAM Rev201961486089110.1137/18M1165748 – reference: SchaeferAJJohnsonELKleywegtAJNemhauserGLAirline crew scheduling under uncertaintyTransp Sci200539334034810.1287/trsc.1040.0091 – reference: FurianNO’SullivanMWalkerCÇelaEA machine learning-based branch and price algorithm for a sampled vehicle routing problemOR Spectr20214369373210.1007/s00291-020-00615-8 – reference: LučićPTeodorovićDMetaheuristics approach to the aircrew rostering problemAnn Oper Res200715531133810.1007/s10479-007-0216-y – reference: Yaakoubi Y, Soumis F, Lacoste-Julien S (2020a) Flight-connection prediction for airline crew scheduling to construct initial clusters for OR optimizer. arXiv preprint, arXiv:2009.12501 – reference: ZeighamiVSaddouneMSoumisFAlternating lagrangian decomposition for integrated airline crew scheduling problemEur J Oper Res2020287121122410.1016/j.ejor.2020.05.005 – reference: MaenhoutBVanhouckeMA hybrid scatter search heuristic for personalized crew rostering in the airline industryEur J Oper Res2010206115516710.1016/j.ejor.2010.01.040 – reference: Nazari M, Oroojlooy A, Snyder LV, Takáč M (2018) Deep reinforcement learning for solving the vehicle routing problem. Adv Neural Inf Process Syst 31 – reference: de ArmasJCadarsoLJuanAAFaulinJA multi-start randomized heuristic for real-life crew rostering problems in airlines with work-balancing goalsAnn Oper Res201725882584810.1007/s10479-016-2260-y – reference: CappaneraPGalloGA multicommodity flow approach to the crew rostering problemOper Res200452458359610.1287/opre.1040.0110 – reference: Silver D, Lever G, Heess N, Degris T, Wierstra D, Riedmiller M (2014). Deterministic policy gradient algorithms. In: International conference on machine learning. PMLR, pp 387–395 – reference: ElhallaouiIMetraneADesaulniersGSoumisFAn improved primal simplex algorithm for degenerate linear programsINFORMS J Comput201123456957710.1287/ijoc.1100.0425 – reference: GamacheMSoumisFMarquisGDesrosiersJA column generation approach for large-scale aircrew rostering problemsOper Res199947224726310.1287/opre.47.2.247 – reference: Morabit M, Desaulniers G, Lodi A (2023). Machine-learning-based arc selection for constrained shortest path problems in column generation. INFORMS J Optim 5(2). https://doi.org/10.1287/ijoo.2022.0082 – reference: Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate, arXiv preprint. arXiv:1409.0473 – reference: GopalakrishnanBJohnsonELAirline crew scheduling: state-of-the-artAnn Oper Res200514030533710.1007/s10479-005-3975-3 – reference: HansenNOstermeierACompletely derandomized self-adaptation in evolution strategiesEvol Comput20019215919510.1162/106365601750190398 – reference: Kotary J, Fioretto F, Van Hentenryck P, Wilder B (2021) End-to-end constrained optimization learning: a survey. arXiv preprint arXiv:2103.16378 – reference: Yaakoubi Y, Soumis F, Lacoste-Julien S (2020b) Machine learning in airline crew pairing to construct initial clusters for dynamic constraint aggregation. EURO J Transp Logist 9(4):100020. https://doi.org/10.1016/j.ejtl.2020.100020 – reference: Karimi-MamaghanMMohammadiMMeyerPKarimi-MamaghanAMTalbiE-GMachine learning at the service of meta-heuristics for solving combinatorial optimization problems: a state-of-the-artEur J Oper Res2022296239342210.1016/j.ejor.2021.04.032 – ident: 678_CR3 – volume: 296 start-page: 393 issue: 2 year: 2022 ident: 678_CR20 publication-title: Eur J Oper Res doi: 10.1016/j.ejor.2021.04.032 – ident: 678_CR40 – volume: 53 start-page: 1479 issue: 5 year: 2019 ident: 678_CR43 publication-title: Transp Sci doi: 10.1287/trsc.2019.0892 – volume: 61 start-page: 860 issue: 4 year: 2019 ident: 678_CR18 publication-title: SIAM Rev doi: 10.1137/18M1165748 – volume: 46 start-page: 820 issue: 6 year: 1998 ident: 678_CR9 publication-title: Oper Res doi: 10.1287/opre.46.6.820 – ident: 678_CR23 – volume: 70 start-page: 3303 issue: 6 year: 2022 ident: 678_CR5 publication-title: Oper Res doi: 10.1287/opre.2022.2267 – ident: 678_CR42 doi: 10.1016/j.ejtl.2020.100020 – volume: 33 start-page: 19 issue: 1 year: 1999 ident: 678_CR26 publication-title: Transp Res Part A Policy Pract doi: 10.1016/S0965-8564(98)00021-4 – volume: 155 start-page: 311 year: 2007 ident: 678_CR27 publication-title: Ann Oper Res doi: 10.1007/s10479-007-0216-y – volume: 47 start-page: 247 issue: 2 year: 1999 ident: 678_CR15 publication-title: Oper Res doi: 10.1287/opre.47.2.247 – volume: 46 start-page: 39 issue: 1 year: 2012 ident: 678_CR35 publication-title: Transp Sci doi: 10.1287/trsc.1110.0379 – volume: 287 start-page: 211 issue: 1 year: 2020 ident: 678_CR44 publication-title: Eur J Oper Res doi: 10.1016/j.ejor.2020.05.005 – volume: 97 start-page: 245 issue: 2 year: 1997 ident: 678_CR11 publication-title: Eur J Oper Res doi: 10.1016/S0377-2217(96)00195-6 – ident: 678_CR33 doi: 10.1287/trsc.2019.0913 – ident: 678_CR36 – volume: 55 start-page: 1411 issue: 6 year: 2021 ident: 678_CR39 publication-title: Transp Sci doi: 10.1287/trsc.2021.1084 – volume: 39 start-page: 340 issue: 3 year: 2005 ident: 678_CR37 publication-title: Transp Sci doi: 10.1287/trsc.1040.0091 – ident: 678_CR46 doi: 10.1007/978-3-031-20102-8_43 – volume: 52 start-page: 583 issue: 4 year: 2004 ident: 678_CR8 publication-title: Oper Res doi: 10.1287/opre.1040.0110 – ident: 678_CR32 doi: 10.1016/j.ejor.2019.11.043 – ident: 678_CR38 – ident: 678_CR41 – volume-title: Contemporary evolution strategies year: 2013 ident: 678_CR1 doi: 10.1007/978-3-642-40137-4 – volume: 140 start-page: 305 year: 2005 ident: 678_CR16 publication-title: Ann Oper Res doi: 10.1007/s10479-005-3975-3 – ident: 678_CR2 – volume: 206 start-page: 155 issue: 1 year: 2010 ident: 678_CR28 publication-title: Eur J Oper Res doi: 10.1016/j.ejor.2010.01.040 – volume: 9 start-page: 159 issue: 2 year: 2001 ident: 678_CR17 publication-title: Evol Comput doi: 10.1162/106365601750190398 – ident: 678_CR34 doi: 10.1016/j.cor.2021.105554 – volume: 21 start-page: 109 year: 2013 ident: 678_CR19 publication-title: TOP doi: 10.1007/s11750-011-0245-1 – volume: 22 start-page: 6784 issue: 11 year: 2020 ident: 678_CR45 publication-title: IEEE Trans Intell Transp Syst doi: 10.1109/TITS.2020.2994779 – volume: 127 start-page: 223 issue: 1–4 year: 2004 ident: 678_CR22 publication-title: Ann Oper Res doi: 10.1023/B:ANOR.0000019091.54417.ca – ident: 678_CR12 doi: 10.1007/3-540-44719-9_34 – volume: 53 start-page: 1007 issue: 6 year: 2005 ident: 678_CR25 publication-title: Oper Res doi: 10.1287/opre.1050.0234 – volume: 258 start-page: 825 year: 2017 ident: 678_CR10 publication-title: Ann Oper Res doi: 10.1007/s10479-016-2260-y – ident: 678_CR31 – ident: 678_CR30 doi: 10.1287/ijoo.2022.0082 – volume: 9 issue: 4 year: 2020 ident: 678_CR4 publication-title: EURO J Transp Logist doi: 10.1016/j.ejtl.2020.100018 – ident: 678_CR24 doi: 10.24963/ijcai.2021/610 – volume: 55 start-page: 815 issue: 4 year: 2021 ident: 678_CR29 publication-title: Transp Sci doi: 10.1287/trsc.2021.1045 – volume: 6 start-page: 111 issue: 2 year: 2017 ident: 678_CR21 publication-title: EURO J Transp Logist doi: 10.1007/s13676-015-0080-x – ident: 678_CR7 doi: 10.1109/CEC.2016.7744084 – volume: 23 start-page: 569 issue: 4 year: 2011 ident: 678_CR13 publication-title: INFORMS J Comput doi: 10.1287/ijoc.1100.0425 – volume: 43 start-page: 693 year: 2021 ident: 678_CR14 publication-title: OR Spectr doi: 10.1007/s00291-020-00615-8 – volume: 44 start-page: 50 issue: 1 year: 2010 ident: 678_CR6 publication-title: Transp Res Part B Methodol doi: 10.1016/j.trb.2009.06.003
SSID	ssj0067630
Score	2.3086236
Snippet	Crew scheduling is typically performed in two stages. First, solving the crew pairing problem generates sequences of flights called pairings. Then, the...
SourceID	crossref springer
SourceType	Enrichment Source Index Database Publisher
StartPage	537
SubjectTerms	Business and Management Economic Theory/Quantitative Economics/Mathematical Methods Economics Finance Industrial and Production Engineering Insurance Management Operations Research/Decision Theory Optimization Original Paper Statistics for Business
Title	Gaining insight into crew rostering instances through ML-based sequential assignment
URI	https://link.springer.com/article/10.1007/s11750-024-00678-8
Volume	32
WOSCitedRecordID	wos001254035700001&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: PRVAVX databaseName: SpringerLink Journals customDbUrl: eissn: 1863-8279 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0067630 issn: 1134-5764 databaseCode: RSV dateStart: 19970101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEF60CurBR1WsL_bgTRfy2Cabo4iPgy2iVXoLk31IoaTSRP37zm6SloIU9JRDJiHMzsw3YR4fIRcqk1kAoWEARjDOuWIgVMZULAWEUgUA4Mgm4n5fDIfJUz0UVjTd7k1J0kXq-bAbIp3HEFOYC7FMrJI1hDthCRueX96a-Buhx7gxSD_kDLNpXo_K_P6ORTharIU6iLnb-d_H7ZLtOqWk15UN7JEVnbfJRjNxXLTJVm-2m7XYJ4P7ihSCjvLC_pnjtZxQTB6_qZ0AcasJ7b3S2kNBayIf2ntkFvEUrZqvMTCMKSbeo3fXTnBAXu9uBzcPrOZWYBIxumTaaFsS1V4mfI0Yj24cGS9KIIA4i7qAWUsgMBdTOkmy2PjcGBFBYoyNERDH4SFp5ZNcHxHKE4gszZVENOTKk2BrbXbtXqIVZN2gQ_xGxamsF49b_otxOl-ZbLWXovZSp71UdMjl7JmPau3GUumr5lTS2gWLJeLHfxM_IZuBPVjXwXdKWuX0U5-RdflVjorpubO9H7gq0zk
linkProvider	Springer Nature
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB60CurBR1Wszz1404U8tsnmKGKt2BbRKr2FSXZXCqWVJurfd3eTtBSkoKccMglhdma-CTPzDcClSNLEQ19RRMUpY0xQ5CKhIkw5-qnwENEumwh7PT4YRE_lUFhWdbtXJUkbqefDbhrpHKoxhdoQS_kqrDGNWIYx__nlrYq_gfYYOwbp-ozqbJqVozK_v2MRjhZroRZiWjv_-7hd2C5TSnJT2MAerMhxHTaqieOsDlvdGTdrtg_9-2IpBBmOM_Nnrq_5hOjk8ZuYCRBLTWju5cYeMlIu8iHdDjWIJ0jRfK0Dw4joxHv4btsJDuC1dde_bdNytwJNNUbnVCppSqLSSbgrNcZrNw6UE0ToYZgETdRZi8d1LiZkFCWhcplSPMBIKRMjMAz9Q6iNJ2N5BIRFGJg1V6lGQyacFE2tzdDuRVJg0vQa4FYqjtOSeNzsvxjFc8pko71Yay-22ot5A65mz3wUtBtLpa-rU4lLF8yWiB__TfwCNtr9bifuPPQeT2DTM4dsu_lOoZZPP-UZrKdf-TCbnls7_AGogdYd
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1bS8MwFD7oFC8PXqbivObBNw1ru6xNH0WditsYOGVvJc1FBqMba9W_b5K2m4IMxKc-NCnlJDnfCed83wG4EDGPPdZQmDFFMSFEYEZFjEXAKWtw4THGbLOJoNulg0HY-8bit9XuZUoy5zQYlaYkq0-Eqs-Jbxr1HKzxBVt3i-kyrBBTSG_u68-vpS_29emxlEi3QbCOrElBm_n9Gz-h6Wde1MJNa_v_P7oDW0Woia7zvbELSzKpwnrJRE6rsNmZabame9C_z5tFoGGSmhu7fmZjpIPKT2SYIVay0LzLzD5JUdHgB3Xa2CChQHlRtnYYI6QD8uGbLTPYh5fWXf_mARc9FzDX2J1hqaRJlUonpq7U2K-Pt68cP2QeC2K_yXQ041EdowkZhnGgXKIU9VmolPEdLAgaB1BJxok8BERC5pv2V1yjJBEOZyYHZ-T4QilY3PRq4JbmjnghSG76YoyiuZSysV6krRdZ60W0BpezOZNcjmPh6KtyhaLiaKYLhh_9bfg5rPVuW1H7sft0DBueWWNb5HcClWz6Lk9hlX9kw3R6ZrfkFyyy3wE
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=Gaining+insight+into+crew+rostering+instances+through+ML-based+sequential+assignment&rft.jtitle=TOP&rft.au=Racette%2C+Philippe&rft.au=Quesnel%2C+Fr%C3%A9d%C3%A9ric&rft.au=Lodi%2C+Andrea&rft.au=Soumis%2C+Fran%C3%A7ois&rft.date=2024-10-01&rft.pub=Springer+Berlin+Heidelberg&rft.issn=1134-5764&rft.eissn=1863-8279&rft.volume=32&rft.issue=3&rft.spage=537&rft.epage=578&rft_id=info:doi/10.1007%2Fs11750-024-00678-8&rft.externalDocID=10_1007_s11750_024_00678_8
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1134-5764&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1134-5764&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1134-5764&client=summon