This study examines the role of Artificial Intelligence (AI) in improving supply chain planning and demand forecasting. With increasing market uncertainty and data complexity, traditional forecasting methods often fail to deliver accurate and timely results. AI-based techniques, especially machine learning and deep learning models, provide better prediction capabilities by analyzing large datasets and identifying hidden patterns. However, the adoption of AI in supply chains is limited due to a lack of transparency and understanding of model outputs. To address this issue, the concept of Explainable Artificial Intelligence (XAI) is introduced, which helps decision-makers interpret and trust AI-based forecasts. The study uses a quantitative research approach based on secondary data from the FMCG sector. It highlights how AI improves forecasting accuracy, reduces inventory waste, and supports sustainable supply chain practices. The findings suggest that integrating AI with explainability can enhance decision-making, operational efficiency, and environmental performance. The study concludes by proposing a simple framework that combines AI, explainability, and sustainability for better supply chain management in emerging economies like India.
Sadhu et al. (2026) studied this question.