A review on unsupervised learning algorithms and applications in supply chain management

Benjamin Rolf, Alexander Beier, Ilya Jackson, Marcel Müller, Tobias Reggelin, Heiner Stuckenschmidt and Sebastian Lang

International Journal of Production Research, 2025, vol. 63, issue 5, 1933-1983

Abstract: Due to pressing challenges such as high market volatility, complex global logistics, geopolitical turmoil and environmental sustainability, compounded by radical events such as the COVID-19 pandemic, the complexity of supply chain management has reached unprecedented levels. Together with increasing data availability and computing power, machine learning algorithms can help to address these challenges. In particular, unsupervised learning can be invaluable in extracting new knowledge from unstructured, unlabelled data. This article systematically reviews the current state of research on unsupervised learning techniques in supply chain management. We propose a classification framework that categorises the literature sample based on supply chain drivers, sectors, data sources, and UL algorithms, and reveal the following insights. The most common applications are information processing and typical operations research optimisation problems such as location planning and vehicle routing. From an algorithmic perspective, clustering and other traditional unsupervised learning techniques dominate recent approaches, owing their popularity to algorithmic simplicity, robustness and accessibility. More advanced and generative techniques have been slow to gain acceptance. In contrast to other machine learning paradigms, unsupervised learning mainly plays a supporting role. The large number of publications using real-world data confirms the importance and maturity of unsupervised learning in supply chain management.Abbreviations: ARM: Association rule mining; AE: Autoencoder; BIRCH: Balanced iterative reducing and clustering hierarchies; DBSCAN: Density-based clustering for applications with noise; FA: Factor analysis; GAN: Generative adversarial network; ML: Machine learning; ISIC: International Standard Industrial Classification; OR: Operations research; PCA: Principal component analysis; SOM: Self-organising map; SICE: Sparse inverse covariance estimation; SCM: Supply chain management; UL: Unsupervised learning

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/00207543.2024.2390968 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:tprsxx:v:63:y:2025:i:5:p:1933-1983

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/TPRS20

DOI: 10.1080/00207543.2024.2390968

Access Statistics for this article

International Journal of Production Research is currently edited by Professor A. Dolgui

More articles in International Journal of Production Research from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().