<p>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.</p>