An explainable fuzzy collaborative intelligence approach for prioritizing possible measures to tackle challenges in semiconductor manufacturing supply chain localization

Tin-Chih Toly Chen (), Yu-Cheng Wang () and Hsin-Chieh Wu ()
Additional contact information
Tin-Chih Toly Chen: National Yang Ming Chiao Tung University, Department of Industrial Engineering and Management
Yu-Cheng Wang: Chaoyang University of Technology, Department of Aeronautical Engineering
Hsin-Chieh Wu: Chaoyang University of Technology, Department of Industrial Engineering and Management

Operational Research, 2026, vol. 26, issue 1, No 7, 32 pages

Abstract: Abstract Wafer foundries face several challenges that need to be overcome in semiconductor supply chain localization. To overcome these challenges, major foundries proposed a range of possible measures. Limited budget, time and other resources to implement these measures force foundries to prioritize them. To this end, an explainable fuzzy collaborative intelligence (EFCI) approach is proposed in this study. In the proposed methodology, decision makers first choose fuzzy multi-criteria decision-making methods from their perspectives. A novel aggregation mechanism, modified fuzzy weighted intersection, is then used to aggregate their evaluation results in a posteriori way into a type-2 fuzzy approximation. However, posterior aggregation makes the importance levels of criteria less obvious. To address this issue, Shapley additive explanations (SHAP) analysis, a technique for quantifying the contribution of each input feature to the model’s prediction for a particular instance, is useful. To account for the uncertainty in the data, we perform a fuzzy SHAP analysis instead. The EFCI approach has been applied to a real case. According to the experimental results, the best-performing possible measure was “early mass production,” while “designing staggered shift systems” had the worst overall performance. In addition, the importance levels assessed using fuzzy SHAP analysis were different from those assessed with (crisp) SHAP analysis. The most important criteria for different possible measures were not the same either. One management implication is to eliminate various uncertainties in advance so as to make reliable decisions; another management implication is to pursue satisfactory performances when optimizing various criteria so that more possible measures can be taken.

Keywords: Localization; Semiconductor supply chain; Challenges; Fuzzy group decision making; Shapley additive explanations; Fuzzy weighted intersection (search for similar items in EconPapers)
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s12351-025-00995-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:operea:v:26:y:2026:i:1:d:10.1007_s12351-025-00995-1

Ordering information: This journal article can be ordered from
https://www.springer ... search/journal/12351

DOI: 10.1007/s12351-025-00995-1

Access Statistics for this article

Operational Research is currently edited by Nikolaos F. Matsatsinis, John Psarras and Constantin Zopounidis

More articles in Operational Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().