This research endeavors to address the challenges posed by uncertainty in inventory management within modern supply chains. The goal is to create a hybrid optimization framework that combines the simplicity of linear programming with the robustness of stochastic modeling. Therefore, this research wants to give decision-makers an adaptable instrument for optimizing inventory policies under inherent uncertainties of dynamic supply chain systems. The indicators for minimizing expected total cost in this suggested hybrid model are Order Quantities and the binary scenario. This also means stock levels must never go down below zero and few restriction or constraints must be checked and ensured for maximum quantity limitation, so that the idea of demand is always precise and correct. This also includes binary variables related to certain situation for various items and operating conditions. The scenario that includes managing complex inventories we should consider using deterministicity theory amalgamation of deterministic part with stochastic components. The large number of equations and inequalities used in representing this model go on to prove its applicability across many industries. The hybrid approach is one that optimizes stock decisions at the least aggregate cost expected considering uncertainties such as demand variability, lead time variation among other key points. Results shown here therefore matches robust inventory management strategies created through these types of models because they easily incorporate real-world data, thereby making them more relevant in practical supply chain settings. Thus, equating the concept as inventory models should comprise of stochastic and deterministic factors in a way that which leads organizations flex with such systems as networks whose future states are hard to project based on what is already known.