This paper presents the development of a dynamic demand forecasting platform designed to predict
demand accurately and quantify its added value in supply chain management using advanced machine
learning and operations management algorithms. The platform collects and processes real-time data from
multiple sources, including point-of-sale systems, e-commerce transactions, competitor pricing, weather
conditions, and consumer sentiment data. By integrating environmental and product-specific factors, the
platform optimizes inventory levels, delivery routing, and operational efficiency. It achieves superior
predictive accuracy by leveraging models such as XGBoost and Support Vector Regression (SVR), which
consistently outperform traditional methods. The solution is designed to be scalable, cost-effective, and
user-friendly, making it particularly accessible to small and medium-sized enterprises (SMEs) that often
struggle to implement advanced forecasting systems due to technological and financial constraints. The
system’s implementation significantly enhances decision-making processes, resulting in reduced
operational costs and improved customer satisfaction.
