Kramer, K.J.; Rokoss, A.; Schmidt, M.: Do We Really Know The Benefit Of Machine Learning In Production Planning And Control? A Systematic Review Of Industry Case Studies.. In: Herberger, D.; Hübner, M. (Eds.): Proceedings of the Conference on Production Systems and Logistics : CPSL 2021. Hannover : publish-Ing., 2021, S. 223-233. DOI: https://doi.org/10.15488/11296
Zusammenfassung: | |
The field of machine learning (ML) is of specific interest for production companies as it displays aperspective to handle the increased complexity within their production planning and control (PPC) processesin an economic and ecologic effective as well as efficient way. Several studies investigate applications ofML to different use cases. However, the research field lacks in research on industry case studies. A broadunderstanding from a practical perspective and in this context, an evaluation from a data mining and businessstandpoint is key for gaining trust in ML solutions. Therefore, this paper gives a comprehensive overviewof evaluation dimensions and outlines the current state of research in ML-PPC by conducting a systematicresearch overview. First, the present work provides key dimensions of business and data mining objectivesas evaluation metric. Business objectives are clustered into economic, ecological and social objectives anddata mining objectives are grouped into prediction accuracy, model’s explainability, model’s runtime, andmodel’s energy use. Secondly, the systematic literature review identifies 45 industry case studies in MLPPC from 2010-2020. The work shows that the scientific publications only rarely reflect in detail on a widerange of evaluation metrics. Instead, researchers mainly focus on prediction accuracy and seldom investigatethe effect of their results to a business context. Positively, some papers reflect on further aspects and caninspire future research. This resulting transparency supports decision makers of companies in theirprioritization process when setting up a future ML-roadmap. In addition, the research gaps identified hereininvite researchers to join the research field. | |
Lizenzbestimmungen: | CC BY 3.0 DE |
Publikationstyp: | BookPart |
Publikationsstatus: | publishedVersion |
Erstveröffentlichung: | 2021 |
Die Publikation erscheint in Sammlung(en): | Proceedings CPSL 2021 Proceedings CPSL 2021 |
Pos. | Land | Downloads | ||
---|---|---|---|---|
Anzahl | Proz. | |||
1 | Germany | 212 | 41,98% | |
2 | United States | 50 | 9,90% | |
3 | United Kingdom | 43 | 8,51% | |
4 | India | 15 | 2,97% | |
5 | No geo information available | 12 | 2,38% | |
6 | United Arab Emirates | 12 | 2,38% | |
7 | Turkey | 11 | 2,18% | |
8 | Canada | 10 | 1,98% | |
9 | Netherlands | 9 | 1,78% | |
10 | Australia | 7 | 1,39% | |
andere | 124 | 24,55% |
Hinweis
Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.