Monte Carlo Simulation and Genetic Algorithm for Optimizing Hospital Medicine Inventory Management under Uncertainty

The pharmaceutical industry faces several challenges when managing its inventory. Among these are uncertainty regarding demand and the expiration of products. The paper presents a hybrid framework that integrates Monte Carlo simulation with a genetic algorithm to assess and enhance stochastic inventory strategies. Two standard replenishment policies—(s, Q) and (R, S)—are evaluated over a simulated time horizon using key performance metrics such as total cost and wastage rate. The genetic algorithm’s integration allows for systematic exploration of the parameter space, leading to the identification of robust and cost-effective replenishment strategies that minimize both operational costs and expiries. The results demonstrate the superiority of the (R, S) policy under the hybrid approach and highlight the value of multi-objective optimization for managing trade-offs between waste and cost efficiency. This hybrid methodology provides practical insights for pharmacy and healthcare supply chain managers seeking to minimize losses due to expiration and refine inventory decisions in response to real-world variability.