STUDY OF SUPPLY CHAIN RISK MANAGEMENT USING DATA ANALYTICS AND MACHINE LEARNING ALGORITHMS

As global supply chains continue to grow in complexity, risk management effectively has become the core activity. This paper explores the utilization of data analytics and machine learning.in the development of supply chain risk-management by it permits anticipating and mitigating disruption. Traditional SCRM strategies remain largely unresponsive to modern needs. In today's fluid environment. By reviewing the methodologies these models are logistic regression, support vector machines, and Anomaly detection, this paper will outline how ML can improve resilience in real time by detecting patterns as well as anomalies. It points out challenges in implementing Data-driven SCRM, which encompasses data quality and integration. Major issues and future directions use analytics on Agile and secured supply chain. Data-driven models give organizations valuable insights through resilience enhancement by identifying patterns and anomalies in real time, thereby allowing for earlier interventions. This research also addresses the challenges of data science within supply chain contexts, including issues of data quality, integration, and the adaptability of predictive models to changing risks. It synthesizes existing literature to offer recommendations for future research avenues. This paper will outline the transformative capability of data analytics and machine learning for supply chains. It will depict a shift from reactive to proactive risk management. Such a shift is not only good for enhancing the resilience of supply chains toward risks but also gives an organization the agility required in today's dynamic business environment. Keywords— Supply Chain Risk Management, Data Analytics, Machine Learning, Predictive Analytics, Supply Chain Security, Anomaly Detection, Resilience