In today’s dynamic retail landscape, supply chain management is a crucial component for ensuring efficiency, cost reduction, and customer satisfaction. The adoption of artificial intelligence (AI) and cloud computing has significantly transformed traditional supply chain operations by enabling real-time decision-making, predictive analytics, and logistics optimization. However, existing supply chain models often face challenges such as high operational costs, demand uncertainty, inefficient inventory management, and suboptimal logistics planning, leading to increased lead times, stock imbalances, and higher defect rates. To mitigate these inefficiencies, this research presents an AI-driven predictive and prescriptive analytics framework that integrates machine learning, reinforcement learning, and cloud-based optimization to enhance demand forecasting, inventory control, and logistics efficiency. Experimental findings demonstrate that XGBoost improves demand forecasting accuracy, reducing forecasting errors and optimizing stock levels. Furthermore, reinforcement learning enhances inventory replenishment and real-time route optimization, significantly lowering transportation costs. AI-powered supplier performance assessment and IoT-enabled shipment tracking improve supply chain visibility and minimize delays. The results validate that AI-driven methodologies enhance supply chain agility, minimize operational risks, and optimize cost efficiency, making them highly scalable and adaptable for real-world retail applications.