Performance Analysis of Supply Chain Resilience Using AI-Driven Predictive and Adaptive Modeling

This study investigates the pivotal function of Artificial Intelligence (AI) in bolstering supply chain resilience by forecasting and addressing disruptions via predictive analytics, real-time monitoring, and data-informed decision-making. In the current dynamic and integrated global economy, supply chain resilience is essential, as disruptions present considerable hazards to operational stability. The study begins with predictive analytics to determine existing risks and model possible disruptions. Artificial intelligence methodologies, including machine learning and reinforcement learning, are used to predict demand variations and improve decision-making procedures. A discrete event simulation model, created with Python, precisely represents the supply chain's performance without impacting real-time operations. The simulation model is evaluated and executed across 40 replications to guarantee reliability. Four AI-augmented resilience strategies are evaluated using AnyLogic simulation software, revealing that the optimal solution yields significant enhancements, including a 35% decrease in response time, an increase in forecast accuracy from 72% to 90%, and an enhancement in resource utilization from 68% to 84%.