Dynamic Resilience Scoring in Supply Chain Management using Predictive Analytics

Abstract

Supply chain disruptions have become increasingly frequent and structurally complex, exposing the limitations of static resilience assessments. This article proposes a dynamic resilience scoring framework that integrates predictive analytics with real time operational data to continuously assess supply chain resilience. The proposed approach captures anticipation, absorption, adaptation, and recovery capabilities using forward looking indicators derived from machine learning models. A model centric architecture is developed and evaluated using simulated multi tier supply networks. Results demonstrate that dynamic resilience scores provide earlier warnings, more granular insights, and stronger decision support than conventional resilience metrics. The findings highlight the value of predictive, continuously updated resilience assessment for proactive supply chain risk management.