Asian Research Journal of Mathematics

In the era of Industry 4.0 and heightened environmental awareness, traditional Economic Order Quantity (EOQ) models fall short in addressing the complexities of modern supply chains characterized by dynamic demand, sustainability constraints, and technological integration. This study proposes a novel Smart EOQ model that integrates artificial intelligence (AI), green logistics practices, and real-time demand forecasting to optimize inventory decisions while minimizing environmental impact. The proposed framework incorporates carbon emission costs, energy-efficient transportation, and AI-driven prediction models to dynamically adjust order quantities and frequencies. A hybrid methodology combining machine learning-based forecasting, multi-objective optimization, and life cycle carbon analysis is employed to assess model performance. Numerical experiments using industry-relevant data demonstrate significant improvements in cost efficiency, order responsiveness, and environmental performance, with up to 18% reduction in total cost and 22% reduction in carbon emissions compared to classical EOQ models. This research offers a robust decision-support tool for supply chain managers aiming to achieve operational excellence while aligning with global sustainability goals.