Energy-intensive sectors, particularly industry and transportation, are essential to economic development but remain major sources of energy consumption and GHG emissions. Although digital technologies generate vast operational data from industrial processes and transportation fleets, their value is often underused due to fragmented data management, limited interpretability, and heuristic decision-making. This highlights the need for intelligent, explainable decision support systems that translate complex data into actionable insights. This research develops an AI-driven decision-support framework that integrates data preprocessing, pattern recognition, and multi-criteria decision methods to support transparent, evidence-based decisions for improving energy efficiency and sustainability.