kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Effektivisering av fordon leveranskedjan med hjälp av maskininlärning
KTH, School of Industrial Engineering and Management (ITM), Industrial Economics and Management (Dept.).
2024 (Swedish)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Optimization of the Vehicle Spply Chain Using Machine Learning (English)
Abstract [sv]

Denna avhandling utforskar hur effektiviteten i fordonsindustrins leveranskedja kan förbättras genom integration av maskininlärningstekniker (ML). Eftersom fordonsindustrin hanterar hög volatilitet och snabba förändringar, blir exakt efterfrågeprognos avgörande för operationell effektivitet. Arbetet fokuserar på potentialen hos ML-teknologier att generera precisa och tillförlitliga efterfrågeprognoser, jämfört med traditionella prognosmetoder som används inom branschen. Studien använder en systematisk litteraturöversikt i kombination med en fallstudie som involverar DinBil AB, en ledande bilhandlare i Sverige. Genom detta flerdimensionella metodologiska tillvägagångssätt bedömer avhandlingen förmågorna hos olika ML-algoritmer att hantera de unika utmaningarna som fordonssektorn ställer. Dessutom undersöker arbetet implementeringsutmaningar och praktiska fördelar med ML i verkliga tillämpningar, med särskild tonvikt på förbättrad lagerhantering och minskade leveranskedjekostnader. Resultaten tyder på att integration av ML i leveranskedjeoperationer kan förbättra noggrannheten i efterfrågeprognoser avsevärt jämfört med traditionella metoder. Dessutom visar ML-tillämpningar att de anpassar sig mer dynamiskt till marknadsförändringar, vilket stödjer en smidig och kostnadseffektiv hantering av leveranskedjan. Avhandlingen avslutas med rekommendationer för bilföretag att anta ML-drivna prognoslösningar, vilket möjliggör en djupare integration av avancerad analys i leveranskedjesystem.

Abstract [en]

This thesis explores the enhancement of automotive supply chain efficiency through the integration of machine learning (ML) techniques. As the automotive industry contends with high volatility and rapid changes, accurate demand forecasting becomes crucial for operational efficiency. The research focuses on the potential of ML technologies to generate precise and reliable demand forecasts, comparing these against traditional forecasting methods used within the industry. The study utilizes a systematic literature review coupled with a case study involving DinBil AB, a leading automotive dealership in Sweden. Through this multifaceted methodological approach, the thesis assesses the capabilities of various ML algorithms in addressing the unique challenges posed by the automotive sector. Additionally, the research examines the implementation challenges and practical benefits of ML in real-world applications, with a particular emphasis on improving inventory management and reducing supply chain costs. The findings suggest that integrating ML into supply chain operations can significantly enhance the accuracy of demand forecasts compared to traditional methods. Moreover, ML applications are shown to adapt more dynamically to market changes, thereby supporting more agile and cost-effective supply chain management. The thesis concludes with recommendations for automotive companies to adopt ML-driven forecasting solutions, providing a framework for further integration of advanced analytics into supply chain systems.

Place, publisher, year, edition, pages
2024. , p. 40
Series
TRITA-ITM-EX ; 2024:306
Keywords [en]
Machine Learning, Artificial Intelligence, Forecasting, Demand Forecasting, Logistics, Supply Chain, Automotive Industry
Keywords [sv]
Maskininlärning, Artificiell intelligens, Prognostisering, Efterfrågeprognoser, Logistik, Försörjningskedja, Bilindustrin
National Category
Other Engineering and Technologies Economics and Business
Identifiers
URN: urn:nbn:se:kth:diva-348810OAI: oai:DiVA.org:kth-348810DiVA, id: diva2:1878814
External cooperation
Dinbil AB
Subject / course
Industrial Economics and Management
Educational program
Master of Science - Industrial Engineering and Management
Presentation
2024-06-14, 00:00
Supervisors
Examiners
Available from: 2024-06-27 Created: 2024-06-27 Last updated: 2024-06-27Bibliographically approved

Open Access in DiVA

fulltext(729 kB)69 downloads
File information
File name FULLTEXT01.pdfFile size 729 kBChecksum SHA-512
ef44a6a3cf755037c50ba207d11cb7af265578a3595d3dde7c207abddd40089980099866a6220211a92bba3658e1d76f5e694597222d6202328931d8156aeaac
Type fulltextMimetype application/pdf

By organisation
Industrial Economics and Management (Dept.)
Other Engineering and TechnologiesEconomics and Business

Search outside of DiVA

GoogleGoogle Scholar
Total: 69 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 246 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf