Abstract
Due to drivers like Industry 4.0, reshoring recently receives more attention. In order to increase understanding, in this novel field of research, k-means clustering is performed to find groups of enterprises, which differ regarding their reshoring incentives. Based on these clusters, manufacturing enterprises are classified by the combination of an intra variance analysis and prior knowledge. Therefore, an own enlarged sample, encompassing 94 German industrial enterprises with global sourcing and production activities is used. It is investigated that five clusters segment the sample optimally and that the importance of innovation as well as trust and sustainability are decisive for the classification of German manufacturing enterprises regarding their reshoring incentives. These findings contribute to the body of knowledge about reshoring incentives in terms of methodology and content, since unsupervised learning is used for the first time within that context and enables insight into previously unexplored structures of the reshoring phenomenon.
Original language | English |
---|---|
Pages (from-to) | 696-705 |
Number of pages | 10 |
Journal | Procedia - Computer Science |
Volume | 180 |
DOIs | |
Publication status | Published - 2021 |
Externally published | Yes |
Bibliographical note
Publisher Copyright:© 2021 Elsevier B.V.. All rights reserved.
Keywords
- Reshoring
- Industry 4.0
- Unsupervised learning
- k-Means Clustering
- K-Means Clustering
- Unsupervised Learning
Fields of Science and Technology Classification 2012
- 502 Economics