Big Data Analytics and Optimization Models for Intelligent Supply Chain and Operations Management: Empirical Simulation Analysis
Keywords:
Big Data Analytics, Optimization Models, Intelligent Supply Chain, Supply Chain 4.0, Prescriptive Analytics, Inventory Optimization, Empirical Simulation.Abstract
In this research paper, a systematic literature review (SLR) of BDA integrated with optimization models in intelligent SCOM is performed together with the development of an empirical analysis. The analysis is based on the empirical findings derived from over 60 peer-reviewed papers (2011-2025) and includes an overview of BDA applications in the fields of descriptive, predictive, and prescriptive analytics in Supply Chain 4.0. Empirical research reveals that BDA can provide 11-20% expected ROI, improve forecasting accuracy by 200% compared to traditional practices, and significantly decrease costs. An empirical analysis performed using Python programming languages and PuLP & NumPy modules shows that there is 36.63% reduction in inventory costs when BDA-supported dynamic forecasts are used in optimization problems compared to static traditional forecasts.
