A machine learning approach for predicting the best heuristic for a large scaled Capacitated Lotsizing Problem

For some NP-hard lotsizing problems, many different heuristics exist, but they have different solution qualities and computation times depending on the characteristics of the instance. The computation times of the individual heuristics increase significantly with the problem size, so that testing al...

Full description

Saved in:

Bibliographic Details
Published in:	OR Spectrum Vol. 47; no. 3; pp. 889 - 931
Main Authors:	Kärcher, Jens, Meyr, Herbert
Format:	Journal Article
Language:	English
Published:	Berlin, Heidelberg Springer 01.09.2025 Springer Nature B.V
Subjects:	Algorithm selection problem Algorithms Capacitated lotsizing problem Classification Computation Forecasting Heuristic Heuristics Literature reviews Machine learning Mixed-integer linear programming Neural network Neural networks Optimization Production lines Scheduling
ISSN:	1436-6304, 0171-6468, 1436-6304
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	For some NP-hard lotsizing problems, many different heuristics exist, but they have different solution qualities and computation times depending on the characteristics of the instance. The computation times of the individual heuristics increase significantly with the problem size, so that testing all available heuristics for large instances requires extensive time. Therefore, it is necessary to develop a method that allows a prediction of the best heuristic for the respective instance without testing all available heuristics. The Capacitated Lotsizing Problem (CLSP) is chosen as the problem to be solved, since it is a fundamental model in the field of lotsizing, well researched and several different heuristics exist for it. The CLSP addresses the problem of determining lotsizes on a production line given limited capacity, product-dependent setup costs, and deterministic, dynamic demand for multiple products. The objective is to minimize setup and inventory holding costs. Two different forecasting methods are presented. One of them is a two-layer neural network called CLSP-Net. It is trained on small CLSP instances, which can be solved very fast with the considered heuristics. Due to the use of a fixed number of wisely chosen features that are relative, relevant, and computationally efficient, and which leverage problem-specific knowledge, CLSP-Net is also capable of predicting the most suitable heuristic for large instances.
AbstractList	For some NP-hard lotsizing problems, many different heuristics exist, but they have different solution qualities and computation times depending on the characteristics of the instance. The computation times of the individual heuristics increase significantly with the problem size, so that testing all available heuristics for large instances requires extensive time. Therefore, it is necessary to develop a method that allows a prediction of the best heuristic for the respective instance without testing all available heuristics. The Capacitated Lotsizing Problem (CLSP) is chosen as the problem to be solved, since it is a fundamental model in the field of lotsizing, well researched and several different heuristics exist for it. The CLSP addresses the problem of determining lotsizes on a production line given limited capacity, product-dependent setup costs, and deterministic, dynamic demand for multiple products. The objective is to minimize setup and inventory holding costs. Two different forecasting methods are presented. One of them is a two-layer neural network called CLSP-Net. It is trained on small CLSP instances, which can be solved very fast with the considered heuristics. Due to the use of a fixed number of wisely chosen features that are relative, relevant, and computationally efficient, and which leverage problem-specific knowledge, CLSP-Net is also capable of predicting the most suitable heuristic for large instances.
Author	Kärcher, Jens Meyr, Herbert
Author_xml	– sequence: 1 givenname: Jens surname: Kärcher fullname: Kärcher, Jens – sequence: 2 givenname: Herbert surname: Meyr fullname: Meyr, Herbert
BookMark	eNp9kEFrGzEQhUVJobbbP1AoCHreZrQje3ePxiRpwdAekrOQ5FlbZi1tJfmQ_PrI3h5CDznNMLxv5s2bsxsfPDH2VcAPAdDcJoC6ExXUsgJoQVbdBzYTElfVCkHevOk_sXlKR4Bl02A7Y37NT9oenCc-kI7e-T3X4xhDGfI-RD5G2jmbL_N8IG4oZX6gc3QpO3tVaD7ouCeerB5oxzd61NZlnUu_DTm5lwv7JwYz0Okz-9jrIdGXf3XBnu7vHjc_q-3vh1-b9bayKEUuRluiHuXSWtEbCbaYrcF0hiRCg6JrsTHGINWGgEwnqbY7IXC1A5Rtq3HBvk97yyd_z8WzOoZz9OWkwnrZYduIsmfB2kllY0gpUq-uxl3wOWo3KAHqkq6a0lUlXXVNV3UFrf9Dx-hOOj6_D32bILLBu6QuJeUQFSIsUeIrUwyJTQ
CitedBy_id	crossref_primary_10_3390_electronics14132642
Cites_doi	10.1016/S0065-2458(08)60520-3 10.1007/978-3-031-60599-4_16 10.1080/05695558108974565 10.1016/0167-6377(86)90027-1 10.1080/05695557908974478 10.1016/0377-2217(78)90121-2 10.1016/j.asoc.2012.02.026 10.1007/s10994-008-5077-3 10.1162/evco_a_00242 10.1016/j.ifacol.2019.11.397 10.1007/978-3-030-58942-4_7 10.1007/s10462-011-9290-2 10.1007/978-3-030-58861-8_9 10.1287/mnsc.35.3.353 10.1287/mnsc.28.10.1174 10.1007/s00291-008-0150-7 10.1016/j.ins.2018.10.013 10.1016/S0305-0483(03)00059-8 10.1007/s00291-015-0429-4 10.1016/j.ejor.2005.12.008 10.1016/j.simpat.2004.12.003 10.1109/IJCNN.2008.4634391 10.1016/j.cor.2018.02.007 10.1080/05695557508974999 10.1145/372202.372210 10.1016/S0305-0483(99)00035-3 10.1007/s00170-004-2306-1 10.1016/j.eswa.2018.10.036 10.1080/00207540600902262 10.1109/ICMLA.2011.153 10.1016/0272-6963(81)90033-4 10.1147/sj.71.0030 10.1016/j.ejor.2005.01.066 10.1016/0377-2217(87)90026-9 10.1080/00207543.2022.2056540 10.1007/978-3-642-34487-9_59 10.1109/BRACIS.2018.00037 10.1016/j.apm.2011.08.017 10.1007/BF02248584 10.1016/j.ejor.2021.04.032 10.1007/s10462-011-9272-4 10.1016/j.neucom.2016.04.027 10.1007/978-3-030-53552-0_15 10.1057/jors.1988.169 10.1007/s10462-022-10275-5 10.3923/jas.2010.1991.2000 10.1016/S0377-2217(99)00237-4 10.1007/s00291-004-0170-x 10.1007/978-3-642-13800-3_29 10.1007/978-3-540-73263-1 10.1007/s00521-012-0863-z 10.1016/0377-2217(94)90078-7 10.1109/CEC.2018.8477989
ContentType	Journal Article
Copyright	The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: The Author(s) 2025. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	OT2 AAYXX CITATION 7SP 7TA 7TB 8FD FR3 JG9 JQ2 KR7 L7M
DOI	10.1007/s00291-024-00804-9
DatabaseName	EconStor CrossRef Electronics & Communications Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Technology Research Database Engineering Research Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Materials Research Database Civil Engineering Abstracts Technology Research Database Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Engineering Research Database Advanced Technologies Database with Aerospace Materials Business File
DatabaseTitleList	Materials Research Database CrossRef
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science Business
EISSN	1436-6304
EndPage	931
ExternalDocumentID	10_1007_s00291_024_00804_9 330534
GroupedDBID	-Y2 .86 .VR 06D 0R~ 0VY 123 1SB 203 28- 29N 2J2 2JN 2JY 2KG 2LR 2P1 2VQ 2~H 30V 4.4 406 408 409 40D 40E 5QI 67Z 6NX 7WY 8AO 8FE 8FG 8FL 8TC 8V8 95- 95. 95~ 96X AAAVM AABHQ AABXT AACDK AAHNG AAIAL AAJBT AAJKR AANZL AAPKM AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO ABAKF ABBBX ABBRH ABBXA ABDBE ABDBF ABDZT ABECU ABFSG ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABLJU ABMNI ABMQK ABNWP ABQSL ABRTQ ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABUWG ABWNU ABXPI ACAOD ACBXY ACDTI ACGFO ACGFS ACHSB ACHXU ACIHN ACIWK ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACREN ACSNA ACSTC ACUHS ACZOJ ADHHG ADHIR ADHKG ADIMF ADKNI ADKPE ADMLS ADRFC ADTPH ADURQ ADYFF ADYOE ADZKW AEAQA AEBTG AEFIE AEFQL AEGAL AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AETLH AEVLU AEXYK AEZWR AFBBN AFDZB AFEXP AFFHD AFGCZ AFHIU AFKRA AFLOW AFOHR AFQWF AFWTZ AFYQB AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGQPQ AGRTI AGWZB AGYKE AHAVH AHBYD AHKAY AHPBZ AHQJS AHSBF AHWEU AHYZX AIAKS AIGIU AIIXL AILAN AITGF AIXLP AJBLW AJRNO AJZVZ AKVCP ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMTXH AMXSW AMYLF AMYQR AOCGG ARAPS ARMRJ ASPBG ATHPR AVWKF AXYYD AYFIA AYQZM AZFZN AZQEC B-. B0M BA0 BAPOH BDATZ BENPR BEZIV BGLVJ BPHCQ BSONS CAG CCPQU COF CSCUP DDRTE DL5 DNIVK DPUIP DU5 DWQXO EAD EAP EBLON EBO EBS EBU EIOEI EJD EMK EOH ESBYG ESX FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRNLG FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNUQQ GNWQR GQ7 GQ8 GXS H13 HCIFZ HF~ HG5 HMJXF HQYDN HRMNR HVGLF I-F I09 IHE IJ- IKXTQ IWAJR IXC IXD IXE IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ K1G K60 K6V K6~ K7- KDC KOV LLZTM M0C MA- N2Q N9A NB0 NDZJH NPVJJ NQJWS O93 O9G O9I OAM OT2 P19 P2P P62 P9M PF0 PHGZM PHGZT PQBIZ PQBZA PQGLB PQQKQ PROAC PT4 PT5 Q2X QOK QOS R89 R9I RNS ROL RPX RSV S16 S1Z S26 S28 S3B SAP SBE SCLPG SDH SDM SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE T16 TH9 TSG TSK TSV TUC TUS U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 ZMTXR ZYFGU ~8M AAYXX CITATION 7SP 7TA 7TB 8FD AESKC FR3 JG9 JQ2 KR7 L7M
ID	FETCH-LOGICAL-c341t-638eef345cc1fb40c77320b9be4307319837bbb3e2be0eb94e2cd1136d03488a3
IEDL.DBID	RSV
ISICitedReferencesCount	1
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001412737400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1436-6304 0171-6468
IngestDate	Wed Nov 05 08:38:17 EST 2025 Sat Nov 29 07:08:55 EST 2025 Tue Nov 18 21:51:57 EST 2025 Fri Dec 05 12:07:53 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	3
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c341t-638eef345cc1fb40c77320b9be4307319837bbb3e2be0eb94e2cd1136d03488a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-9856-3789 0009-0000-7022-3558
OpenAccessLink	https://www.econstor.eu/handle/10419/330534
PQID	3259387107
PQPubID	49049
PageCount	43
ParticipantIDs	proquest_journals_3259387107 crossref_citationtrail_10_1007_s00291_024_00804_9 crossref_primary_10_1007_s00291_024_00804_9 econis_econstor_330534
PublicationCentury	2000
PublicationDate	2025-09-01
PublicationDateYYYYMMDD	2025-09-01
PublicationDate_xml	– month: 09 year: 2025 text: 2025-09-01 day: 01
PublicationDecade	2020
PublicationPlace	Berlin, Heidelberg
PublicationPlace_xml	– name: Berlin, Heidelberg – name: Heidelberg
PublicationTitle	OR Spectrum
PublicationYear	2025
Publisher	Springer Springer Nature B.V
Publisher_xml	– name: Springer – name: Springer Nature B.V
References	N Megala (804_CR39) 2006; 27 K Copil (804_CR10) 2017; 39 B Karimi (804_CR29) 2003; 31 H Rummukainen (804_CR49) 2019; 52 J Rohde (804_CR48) 2004; 26 E Aarts (804_CR1) 2000; 122 804_CR63 804_CR23 LK Gaafar (804_CR18) 2000; 28 804_CR66 804_CR27 I Goodfellow (804_CR19) 2016 804_CR28 N Srivastava (804_CR57) 2014; 15 PS Eisenhut (804_CR17) 1975; 7 EA Silver (804_CR53) 1969; 10 L van Hezewijk (804_CR60) 2023; 61 VG Costa (804_CR11) 2023; 56 804_CR36 804_CR35 PS Dixon (804_CR14) 1981; 2 WW Trigeiro (804_CR59) 1989; 35 F Arnold (804_CR2) 2019; 106 A Dogramaci (804_CR15) 1981; 13 J Maes (804_CR38) 1988; 39 CM Bishop (804_CR4) 2006 SB Kotsiantis (804_CR33) 2013; 39 L Buschkühl (804_CR7) 2010; 32 T Stützle (804_CR58) 2006; 174 P Kerschke (804_CR31) 2019; 27 GR Bitran (804_CR5) 1982; 28 KP Murphy (804_CR41) 2012 J-T Wong (804_CR64) 2012; 36 804_CR40 J Maes (804_CR37) 1986; 4 804_CR44 X Chu (804_CR9) 2019; 476 804_CR43 R Jans (804_CR24) 2007; 177 804_CR47 804_CR46 M Karimi-Mamaghan (804_CR30) 2022; 296 W-H Chen (804_CR8) 1990; 26 Ö Kirca (804_CR32) 1994; 75 J Kanda (804_CR26) 2016; 205 M Zennaki (804_CR65) 2010; 10 P Brazdil (804_CR6) 2009 EA Silver (804_CR54) 1973; 14 804_CR52 804_CR51 804_CR50 804_CR3 JJ DeMatteis (804_CR13) 1968; 7 804_CR12 MR Lambrecht (804_CR34) 1979; 11 804_CR56 R Jans (804_CR25) 2008; 46 804_CR55 AE Gutierrez-Rodríguez (804_CR22) 2019; 118 J van Nunen (804_CR61) 1978; 2 CD Paternina-Arboleda (804_CR45) 2005; 13 804_CR16 C Vens (804_CR62) 2008; 73 H-O Günther (804_CR21) 1987; 31 GK Groff (804_CR20) 1979; 20 M Nikolić (804_CR42) 2013; 40
References_xml	– ident: 804_CR47 doi: 10.1016/S0065-2458(08)60520-3 – ident: 804_CR63 doi: 10.1007/978-3-031-60599-4_16 – volume: 13 start-page: 294 issue: 4 year: 1981 ident: 804_CR15 publication-title: AIIE Trans doi: 10.1080/05695558108974565 – ident: 804_CR43 – volume: 4 start-page: 265 issue: 6 year: 1986 ident: 804_CR37 publication-title: Oper Res Lett doi: 10.1016/0167-6377(86)90027-1 – volume: 15 start-page: 1929 issue: 56 year: 2014 ident: 804_CR57 publication-title: J Mach Learn Res – volume: 11 start-page: 319 issue: 4 year: 1979 ident: 804_CR34 publication-title: AIIE Trans doi: 10.1080/05695557908974478 – volume: 2 start-page: 36 issue: 1 year: 1978 ident: 804_CR61 publication-title: Eur J Oper Res doi: 10.1016/0377-2217(78)90121-2 – ident: 804_CR66 – ident: 804_CR52 doi: 10.1016/j.asoc.2012.02.026 – volume: 73 start-page: 185 issue: 2 year: 2008 ident: 804_CR62 publication-title: Mach Learn doi: 10.1007/s10994-008-5077-3 – volume: 27 start-page: 3 issue: 1 year: 2019 ident: 804_CR31 publication-title: Evol Comput doi: 10.1162/evco_a_00242 – volume: 52 start-page: 1415 issue: 13 year: 2019 ident: 804_CR49 publication-title: IFAC-PapersOnLine doi: 10.1016/j.ifacol.2019.11.397 – ident: 804_CR3 doi: 10.1007/978-3-030-58942-4_7 – volume: 40 start-page: 457 issue: 4 year: 2013 ident: 804_CR42 publication-title: Artif Intell Rev doi: 10.1007/s10462-011-9290-2 – ident: 804_CR50 doi: 10.1007/978-3-030-58861-8_9 – volume: 14 start-page: 64 issue: 2 year: 1973 ident: 804_CR54 publication-title: Prod Invent Manag – volume: 35 start-page: 353 issue: 3 year: 1989 ident: 804_CR59 publication-title: Manage Sci doi: 10.1287/mnsc.35.3.353 – volume: 28 start-page: 1174 issue: 10 year: 1982 ident: 804_CR5 publication-title: Manage Sci doi: 10.1287/mnsc.28.10.1174 – volume: 32 start-page: 231 issue: 2 year: 2010 ident: 804_CR7 publication-title: OR Spectrum doi: 10.1007/s00291-008-0150-7 – volume: 476 start-page: 192 year: 2019 ident: 804_CR9 publication-title: Inf Sci doi: 10.1016/j.ins.2018.10.013 – ident: 804_CR44 – ident: 804_CR23 – volume: 31 start-page: 365 issue: 5 year: 2003 ident: 804_CR29 publication-title: Omega doi: 10.1016/S0305-0483(03)00059-8 – volume: 39 start-page: 1 issue: 1 year: 2017 ident: 804_CR10 publication-title: OR Spectrum doi: 10.1007/s00291-015-0429-4 – volume: 177 start-page: 1855 issue: 3 year: 2007 ident: 804_CR24 publication-title: Eur J Oper Res doi: 10.1016/j.ejor.2005.12.008 – volume: 13 start-page: 389 issue: 5 year: 2005 ident: 804_CR45 publication-title: Simul Model Pract Theory doi: 10.1016/j.simpat.2004.12.003 – ident: 804_CR55 doi: 10.1109/IJCNN.2008.4634391 – volume: 106 start-page: 280 year: 2019 ident: 804_CR2 publication-title: Comput Oper Res doi: 10.1016/j.cor.2018.02.007 – volume-title: Deep learning year: 2016 ident: 804_CR19 – volume: 7 start-page: 170 issue: 2 year: 1975 ident: 804_CR17 publication-title: AIIE Trans doi: 10.1080/05695557508974999 – ident: 804_CR35 doi: 10.1145/372202.372210 – volume: 28 start-page: 175 issue: 2 year: 2000 ident: 804_CR18 publication-title: Omega doi: 10.1016/S0305-0483(99)00035-3 – volume: 27 start-page: 1178 issue: 11 year: 2006 ident: 804_CR39 publication-title: Int J Adv Manuf Technol doi: 10.1007/s00170-004-2306-1 – volume: 118 start-page: 470 year: 2019 ident: 804_CR22 publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2018.10.036 – volume: 46 start-page: 1619 issue: 6 year: 2008 ident: 804_CR25 publication-title: Int J Prod Res doi: 10.1080/00207540600902262 – ident: 804_CR27 doi: 10.1109/ICMLA.2011.153 – volume: 2 start-page: 23 issue: 1 year: 1981 ident: 804_CR14 publication-title: J Oper Manag doi: 10.1016/0272-6963(81)90033-4 – volume: 7 start-page: 30 issue: 1 year: 1968 ident: 804_CR13 publication-title: IBM Syst J doi: 10.1147/sj.71.0030 – volume: 174 start-page: 1519 issue: 3 year: 2006 ident: 804_CR58 publication-title: Eur J Oper Res doi: 10.1016/j.ejor.2005.01.066 – volume: 20 start-page: 47 issue: 1 year: 1979 ident: 804_CR20 publication-title: Prod Invent Manag – volume: 31 start-page: 223 issue: 2 year: 1987 ident: 804_CR21 publication-title: Eur J Oper Res doi: 10.1016/0377-2217(87)90026-9 – volume: 61 start-page: 1955 issue: 6 year: 2023 ident: 804_CR60 publication-title: Int J Prod Res doi: 10.1080/00207543.2022.2056540 – ident: 804_CR28 doi: 10.1007/978-3-642-34487-9_59 – ident: 804_CR16 – ident: 804_CR40 doi: 10.1109/BRACIS.2018.00037 – volume: 36 start-page: 2003 issue: 5 year: 2012 ident: 804_CR64 publication-title: Appl Math Model doi: 10.1016/j.apm.2011.08.017 – volume: 26 start-page: 29 issue: 1–4 year: 1990 ident: 804_CR8 publication-title: Annals Oper Res doi: 10.1007/BF02248584 – volume-title: Machine learning: a probabilistic perspective. Adaptive computation and machine learning series year: 2012 ident: 804_CR41 – volume-title: Pattern recognition and machine learning year: 2006 ident: 804_CR4 – volume: 296 start-page: 393 issue: 2 year: 2022 ident: 804_CR30 publication-title: Eur J Oper Res doi: 10.1016/j.ejor.2021.04.032 – volume: 10 start-page: 51 issue: 4 year: 1969 ident: 804_CR53 publication-title: Prod Invent Manag – volume: 39 start-page: 261 issue: 4 year: 2013 ident: 804_CR33 publication-title: Artif Intell Rev doi: 10.1007/s10462-011-9272-4 – volume: 205 start-page: 393 year: 2016 ident: 804_CR26 publication-title: Neurocomputing doi: 10.1016/j.neucom.2016.04.027 – ident: 804_CR46 – ident: 804_CR36 doi: 10.1007/978-3-030-53552-0_15 – volume: 39 start-page: 991 issue: 11 year: 1988 ident: 804_CR38 publication-title: J Oper Res Soc doi: 10.1057/jors.1988.169 – volume: 56 start-page: 4765 issue: 5 year: 2023 ident: 804_CR11 publication-title: Artif Intell Rev doi: 10.1007/s10462-022-10275-5 – volume: 10 start-page: 1991 issue: 18 year: 2010 ident: 804_CR65 publication-title: J Appl Sci doi: 10.3923/jas.2010.1991.2000 – volume: 122 start-page: 339 issue: 2 year: 2000 ident: 804_CR1 publication-title: Eur J Oper Res doi: 10.1016/S0377-2217(99)00237-4 – volume: 26 start-page: 471 issue: 4 year: 2004 ident: 804_CR48 publication-title: OR Spectrum doi: 10.1007/s00291-004-0170-x – ident: 804_CR56 doi: 10.1007/978-3-642-13800-3_29 – volume-title: Metalearning: applications to data mining year: 2009 ident: 804_CR6 doi: 10.1007/978-3-540-73263-1 – ident: 804_CR51 doi: 10.1007/s00521-012-0863-z – volume: 75 start-page: 332 issue: 2 year: 1994 ident: 804_CR32 publication-title: Eur J Oper Res Lotsizing Models Prod Plan doi: 10.1016/0377-2217(94)90078-7 – ident: 804_CR12 doi: 10.1109/CEC.2018.8477989
SSID	ssj0057738 ssj0004889
Score	2.41189
Snippet	For some NP-hard lotsizing problems, many different heuristics exist, but they have different solution qualities and computation times depending on the...
SourceID	proquest crossref econis
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	889
SubjectTerms	Algorithm selection problem Algorithms Capacitated lotsizing problem Classification Computation Forecasting Heuristic Heuristics Literature reviews Machine learning Mixed-integer linear programming Neural network Neural networks Optimization Production lines Scheduling
Title	A machine learning approach for predicting the best heuristic for a large scaled Capacitated Lotsizing Problem
URI	https://www.econstor.eu/handle/10419/330534 https://www.proquest.com/docview/3259387107
Volume	47
WOSCitedRecordID	wos001412737400001&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 Contemporary 1997-Present customDbUrl: eissn: 1436-6304 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0057738 issn: 1436-6304 databaseCode: RSV dateStart: 20020201 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/eLvHCXMwlV1NT9wwEB0hhCo4dNttEUtp5QO31pK_skmOaFXUA0KoLYibFTuTdiXYRZuFQ389M04CrUorcYoj2Yk1Y3tm5Jn3AA5jXmc6oJbk2vM1Y6Zl1aggM0u-dVC1002CzD_JT0-Ly8vybAM-_fMGn-E-DWfnGCfZvXGSq_X01DBdwddvF49FkAXjpncvWZ4nDmsGg5FTNy36cpmnv_eHSdriOHTe_nU0J3tzPHreTF_By96vFEfdQngNG7gYw4shrX0Mo4G-QfS7eQw7v2ERvoHFkbhOiZUoeiaJH2IAHBfk2YqbFd_pcJa0IKdRBJqz-Im3HdJz6lGJK84rFy3pHWsxIzscuYSN2ifLdTv_xWPPOgabt3B-_Pn77IvsyRhkJEO3lrRPERvrshh1E5yKJGKjQhnQ8TGhS4p0QwgWTUCFoXRoYs2EMbWypJrK7sLmYrnAPRBNyMpQKxOxUY48hKIutDN1VRkstdU4AT3ow8ceqZwJM678A8ZykrQnSfskaV9O4OPDmJsOp-O_vXc7NXt-cBqqt3TwWTeBg0Htvt_MrbcUIloKLFW-_6y_vINtw2zBKSPtADbXq1t8D1vxbj1vVx_S6r0H8nPisQ
linkProvider	Springer Nature
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+machine+learning+approach+for+predicting+the+best+heuristic+for+a+large+scaled+Capacitated+Lotsizing+Problem&rft.jtitle=OR+spectrum&rft.au=K%C3%A4rcher%2C+Jens&rft.au=Meyr%2C+Herbert&rft.date=2025-09-01&rft.pub=Springer&rft.issn=1436-6304&rft.volume=47&rft.issue=3&rft.spage=889&rft.epage=931&rft_id=info:doi/10.1007%2Fs00291-024-00804-9&rft.externalDBID=OT2&rft.externalDocID=330534
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1436-6304&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1436-6304&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1436-6304&client=summon