In pharmaceutical supply chain management, machine learning is a game-changing technology that has the potential to completely improve demand forecasting, inventory optimization, and operational efficiency. Utilizing complex algorithms and vast datasets, machine learning empowers businesses to obtain detailed predictive insights that decrease overproduction, lower expenses, and strengthen supply chain resilience. The empirical validation through XGBoost modeling, illustrated by a low Root Mean Square Error (RMSE) of 2.8287, confirms the ability of machine learning to produce accurate medicine consumption predictions, optimize resource allocation, and reduce risks such as stockouts and drug expiration. Apart from improving operations, machine learning-based approaches also promote critical trust between stakeholders by ensuring consistent drug availability, maximizing budget allocation, and creating more patient-centered, responsive supply chains. The research highlights a future where data-driven technologies not only address current pharmaceutical logistics challenges but also proactively adapt to complex, dynamic healthcare environments, ultimately contributing to more sustainable, efficient, and reliable medication distribution systems.