Supply Chain Network (SCN) Resilient Pattern Recognition and Intelligent Strategy Recommender Approach for the Post-COVID-19 Era

Abstract

The Coronavirus outbreak and its different variants have damaged the global supply chains and affected suppliers for both goods and service providers unprecedentedly. The post-COVID-19 era could be considered full of uncertainty based on many changes that have happened. Some new parameters are introduced because of the outbreak and bring out new circumstances. These new challenges consequently will increase the ambiguity around the supply chain networks. This study is designed to investigate and evaluate the vagueness of supply chain networks in the post-COVID-19 time. The paper aims to study the strength of the SCN systems and find the related disruption patterns for each of the SCNs and then recommend appropriate strategies to increase the resilience of SCN systems. In the literature review part, we reviewed many articles that categorized the challenges. To catch the goal of evaluating the resilience of supply chain networks, some significant challenges are identified based on the literature part. An algorithm consists of three stages, first defining the uncertainty, second pattern recognition of disruption patterns, and third strategy recommender system to increase SCN resilience is proposed based on the SFS aggregation operator and logarithmic f-similarity measure. An illustrative example of the SCN resilience problem is evaluated by the proposed algorithm under the spherical fuzzy structure to show the applicability and reliability of the proposed method. Finally, this paper provides guidelines and strategies for increasing the resilience of supply chain networks in the post-COVID-19 outbreak.