Artificial Intelligence for Accurate Service Level Assessment in Modern Inventory Management
Naidu Paila
Abstract
Healthcare supply chains operate under conditions of high product variety, strict regulatory oversight, and time-critical demand, where supply disruptions may directly affect patient care. Planning and forecasting in these environments are often supported by rule-based systems and traditional statistical methods, which can struggle to accommodate demand variability and network complexity. This study examines the application of data-driven optimization methods to healthcare supply chain planning using operational data collected over a 24-month period. The proposed framework integrates demand forecasting, service-level modeling, and multi-echelon inventory optimization within an enterprise planning environment. Statistical modeling and predictive analytics are used to support planning decisions across multiple echelons of the supply chain. The analysis draws on data covering more than 10,000 product SKUs, over 150 hospital locations, and approximately 500,000 surgical procedures. Empirical results indicate sustained improvements in service levels and inventory efficiency, including a 14.78 percentage-point increase in True Service Level, the elimination of 1,857 documented kit shortages, a reduction of $144.2 million in global inventory, and a 55.3% improvement in forecast accuracy. These outcomes were achieved without compromising supply continuity. Overall, the findings suggest that advanced analytics, when embedded within established planning processes, can materially improve healthcare supply chain performance. The study provides evidence from a large-scale implementation and may inform future applications of analytics-based optimization in regulated healthcare settings.