This study outlines a revolutionary approach towards the optimization of pharmaceutical sales through the use of Explainable AI (XAI), multi-objective optimization, and customer behavior analytics. It deals with the drawbacks of the traditional ways first by the increasing of prediction accuracy, the real-time adaptability, and the interpretable treatment of the issues. Highly specialized machine learning models like the long short-term memory (LSTM) and Gaussian Process. Regression are used to combine XAI techniques in this study that indeed are able to predict results that are not only transparent but also actionable. Multi-objective optimization makes it possible to achieve sales, inventory, and drug distribution targets by examining trade-offs between the goals from various angles. Personalized marketing is done through customer behavior analytics which enable regional and demographic segmentation of marketing and resource allocations. The platform is built through cloud-based GPU and is user-friendly and interactive for users through a Business Intelligence (BI) dashboard, which provides visualized information in real-time and allows for a swifter decision-making process. Experimental findings suggest that the framework is the most prominent in accuracy, scalability, and the possibility of immediate adaptability thereby giving a concrete and intelligible means to control drugs sales in a dynamic market. The article gives a thorough approach towards improving health care sales optimization that brings decision-makers to the point of being able to deal with a paradigm shift in the market and the fluctuation of demands among the consumers.