Machine Learning and Statistics: A Study for assessing innovative Demand Forecasting Models

Machine Learning and Statistics: A Study for assessing innovative Demand Forecasting Models

Besides increasing dynamics in market demands, companies strive to avoid short-term changes in their supply chain planning. Therefore, an essential lever to improve supply chain performance is the optimization of the demand forecast. In this regard, artificial intelligence is a widely adopted techni...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Moroff, Nikolas Ulrich, Kurt, Ersin, Kamphues, Josef
Format: Artikel
Sprache:eng
Schlagworte:
deep learning
Demand Forecast
machine learning
statistical method
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Moroff, Nikolas Ulrich
Kurt, Ersin
Kamphues, Josef
description Besides increasing dynamics in market demands, companies strive to avoid short-term changes in their supply chain planning. Therefore, an essential lever to improve supply chain performance is the optimization of the demand forecast. In this regard, artificial intelligence is a widely adopted technique in Industry 4.0 that is associated with high expectations. Against this background, six different forecasting models from statistics and machine learning were evaluated in respect to forecast quality and effort for implementation. The results underline the potential of innovative forecasting models as well as the necessity for an intensive and application-specific evaluation of the advantages and disadvantages of the available approaches.
doi_str_mv 10.1016/j.procs.2021.01.127
format Article
fullrecord <record><control><sourceid>fraunhofer_E3A</sourceid><recordid>TN_cdi_fraunhofer_primary_oai_fraunhofer_de_N_637681</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>oai_fraunhofer_de_N_637681</sourcerecordid><originalsourceid>FETCH-fraunhofer_primary_oai_fraunhofer_de_N_6376813</originalsourceid><addsrcrecordid>eNqdi7EOgjAURbs4GPULXPoDVooGjJtRiYO46ObQvJSH1EBL-oCEvxcSB2enm3vvOYwtZSBkIKP1W9TeaRJhEEoRSCHDeMqeKejCWORXBG-NfXGwGb830BhqjKY9PwytzXqeO8-BCIlGyljrugHqkJ-wGp3EedQwSMObugxLmrNJDiXh4psztk3Oj-NllXtobeFy9Kr2pgLfKwdG_cwZqpuKNnG0k5s_tQ8_OFNn</addsrcrecordid><sourcetype>Institutional Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Machine Learning and Statistics: A Study for assessing innovative Demand Forecasting Models</title><source>Fraunhofer-ePrints</source><creator>Moroff, Nikolas Ulrich ; Kurt, Ersin ; Kamphues, Josef</creator><creatorcontrib>Moroff, Nikolas Ulrich ; Kurt, Ersin ; Kamphues, Josef</creatorcontrib><description>Besides increasing dynamics in market demands, companies strive to avoid short-term changes in their supply chain planning. Therefore, an essential lever to improve supply chain performance is the optimization of the demand forecast. In this regard, artificial intelligence is a widely adopted technique in Industry 4.0 that is associated with high expectations. Against this background, six different forecasting models from statistics and machine learning were evaluated in respect to forecast quality and effort for implementation. The results underline the potential of innovative forecasting models as well as the necessity for an intensive and application-specific evaluation of the advantages and disadvantages of the available approaches.</description><identifier>DOI: 10.1016/j.procs.2021.01.127</identifier><language>eng</language><subject>deep learning ; Demand Forecast ; machine learning ; statistical method</subject><creationdate>2021</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,780,27859</link.rule.ids><linktorsrc>$$Uhttp://publica.fraunhofer.de/documents/N-637681.html$$EView_record_in_Fraunhofer-Gesellschaft$$FView_record_in_$$GFraunhofer-Gesellschaft$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Moroff, Nikolas Ulrich</creatorcontrib><creatorcontrib>Kurt, Ersin</creatorcontrib><creatorcontrib>Kamphues, Josef</creatorcontrib><title>Machine Learning and Statistics: A Study for assessing innovative Demand Forecasting Models</title><description>Besides increasing dynamics in market demands, companies strive to avoid short-term changes in their supply chain planning. Therefore, an essential lever to improve supply chain performance is the optimization of the demand forecast. In this regard, artificial intelligence is a widely adopted technique in Industry 4.0 that is associated with high expectations. Against this background, six different forecasting models from statistics and machine learning were evaluated in respect to forecast quality and effort for implementation. The results underline the potential of innovative forecasting models as well as the necessity for an intensive and application-specific evaluation of the advantages and disadvantages of the available approaches.</description><subject>deep learning</subject><subject>Demand Forecast</subject><subject>machine learning</subject><subject>statistical method</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>AFSUM</sourceid><sourceid>E3A</sourceid><recordid>eNqdi7EOgjAURbs4GPULXPoDVooGjJtRiYO46ObQvJSH1EBL-oCEvxcSB2enm3vvOYwtZSBkIKP1W9TeaRJhEEoRSCHDeMqeKejCWORXBG-NfXGwGb830BhqjKY9PwytzXqeO8-BCIlGyljrugHqkJ-wGp3EedQwSMObugxLmrNJDiXh4psztk3Oj-NllXtobeFy9Kr2pgLfKwdG_cwZqpuKNnG0k5s_tQ8_OFNn</recordid><startdate>2021</startdate><enddate>2021</enddate><creator>Moroff, Nikolas Ulrich</creator><creator>Kurt, Ersin</creator><creator>Kamphues, Josef</creator><scope>AFSUM</scope><scope>E3A</scope></search><sort><creationdate>2021</creationdate><title>Machine Learning and Statistics: A Study for assessing innovative Demand Forecasting Models</title><author>Moroff, Nikolas Ulrich ; Kurt, Ersin ; Kamphues, Josef</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-fraunhofer_primary_oai_fraunhofer_de_N_6376813</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>deep learning</topic><topic>Demand Forecast</topic><topic>machine learning</topic><topic>statistical method</topic><toplevel>online_resources</toplevel><creatorcontrib>Moroff, Nikolas Ulrich</creatorcontrib><creatorcontrib>Kurt, Ersin</creatorcontrib><creatorcontrib>Kamphues, Josef</creatorcontrib><collection>Fraunhofer-ePrints - FT</collection><collection>Fraunhofer-ePrints</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Moroff, Nikolas Ulrich</au><au>Kurt, Ersin</au><au>Kamphues, Josef</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine Learning and Statistics: A Study for assessing innovative Demand Forecasting Models</atitle><date>2021</date><risdate>2021</risdate><abstract>Besides increasing dynamics in market demands, companies strive to avoid short-term changes in their supply chain planning. Therefore, an essential lever to improve supply chain performance is the optimization of the demand forecast. In this regard, artificial intelligence is a widely adopted technique in Industry 4.0 that is associated with high expectations. Against this background, six different forecasting models from statistics and machine learning were evaluated in respect to forecast quality and effort for implementation. The results underline the potential of innovative forecasting models as well as the necessity for an intensive and application-specific evaluation of the advantages and disadvantages of the available approaches.</abstract><doi>10.1016/j.procs.2021.01.127</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.1016/j.procs.2021.01.127
ispartof
issn
language eng
recordid cdi_fraunhofer_primary_oai_fraunhofer_de_N_637681
source Fraunhofer-ePrints
subjects deep learning
Demand Forecast
machine learning
statistical method
title Machine Learning and Statistics: A Study for assessing innovative Demand Forecasting Models
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T22%3A30%3A49IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-fraunhofer_E3A&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20Learning%20and%20Statistics:%20A%20Study%20for%20assessing%20innovative%20Demand%20Forecasting%20Models&rft.au=Moroff,%20Nikolas%20Ulrich&rft.date=2021&rft_id=info:doi/10.1016/j.procs.2021.01.127&rft_dat=%3Cfraunhofer_E3A%3Eoai_fraunhofer_de_N_637681%3C/fraunhofer_E3A%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true