DATA-DRIVEN APPROACHES FOR SUPPLY CHAIN RESILIENCE: A REVIEW OF PREDICTIVE ANALYTICS, OPTIMIZATION, AND RISK MODELING

Supply chain resilience has become a central theme in the face of global disruptions, from pandemics, naturaldisasters, climate change, and geopolitical instability. This review explores data-driven approaches that enhanceresilience by integrating predictive analytics, optimization, and risk modeling. Predictive analytics enablesorganizations to anticipate demand fluctuations, supplier risks, and external shocks through statistical, machinelearning, and hybrid methods. Optimization techniques strengthen supply chain continuity by balancing costefficiency, flexibility, sustainability, and redundancy. Risk modeling frameworks, including stochasticsimulations, network-based approaches, and AI-driven systems, provide structured tools for quantifyingvulnerabilities and stress-testing supply chain networks. Applications across sectors such as healthcare, retail,energy, and transportation demonstrate how these methods support adaptability and continuity in uncertainenvironments. Building on this synthesis, the paper proposes an integrated framework that connects predictiveanalytics, optimization, and risk modeling, offering a pathway toward robust, adaptive, and sustainable supplychains. The review concludes with a discussion of limitations, emerging trends, and future researchopportunities to guide both academics and practitioners in advancing supply chain resilience.