Published Paper Details:

Supply chain management (SCM) that makes use of BDA is becoming more prevalent. The wide range of SCM applications of BDA, including demand prediction, trend analysis, and consumer behaviour, is the reason for this. This study aims to enhance precision and efficiency in demand forecasting and SCM through the application of BDA. Despite advancements, challenges persist such as reliance on isolated datasets, underutilisation of advanced machine learning models, and limited incorporation of external variables. Demand forecasting, crucial for supply chain decisions like production planning and inventory control, is hindered by demand volatility influenced by factors such as promotions and market trends. This study leverages integrated, real-time data sources and sophisticated analytics to improve prediction accuracy and operational efficiency, thereby enabling businesses to better manage uncertainties in demand, supply, and costs. The research also identifies gaps in current literature, including the need for more robust models, comprehensive external variable analysis, and broader validation across industries. By addressing these gaps, the research contributes to a development of more resilient and responsive supply chains