Sustainable-resilient supplier evaluation for high-consumption drugs during COVID-19 pandemic using a data-driven decision-making approach

Abstract

The recent pandemic of COVID-19 has had severe impacts on healthcare services especially the Food and Drug Administration for providing necessary medications for patients. The supplier selection problem in the COVID-19 pandemic is a crucial problem. This research aims to develop a data-driven model for sustainable and resilient supplier evaluation. At the outset, we identify the related criteria based on literature and experts and then calculate their weights using Fuzzy-Bests-Worst-Method (FBWM). Afterward, the Fuzzy Inference System (FIS) method is employed to evaluate the performance of the supplier. Finally, three different classification machine learning models are developed based on the supplier historical data in every criterion and also the FIS output as the target column. This study provides 22 criteria are identified and categorized into three-dimension (economic, social, environmental, and resilient). The results show that the case study managers pay more attention to ‘Responsiveness’ and ‘Ability’. The two-stage FIS results indicate that 35 records were evaluated as very poor, 70 ones as poor, 98 ones as moderate, 90 ones as good, and 57 as very good ones. Other companies could use the same model for their supplier selection decision-making to have a better decision based on historical data of their suppliers.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 34 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.