Evaluating AI-based Decision Support Systems for Resource Efficiency and Waste Reduction in Construction Projects

The construction industry remains one of the most resource-intensive and waste-generating sectors globally, accounting for significant material consumption, energy use, and environmental degradation. Despite advances in project management methodologies, inefficiencies in planning, procurement, and execution persist due to the inherent complexity and uncertainty of construction processes. Artificial Intelligence (AI)-based Decision Support Systems (DSS) have emerged as a promising solution to address these challenges by enabling predictive, adaptive, and data-driven decision-making. This study presents an in-depth evaluation of AI-based DSS applied to resource efficiency and waste reduction in construction projects. Drawing on theoretical foundations, algorithmic mechanisms, and real-world case evidence, the paper examines how AI-driven forecasting, optimization, and real-time monitoring enhance sustainable outcomes. The analysis integrates extended discussions of machine learning, optimization, and reinforcement learning algorithms, alongside case studies from building and infrastructure projects. Evaluation criteria encompassing technical performance, operational impact, sustainability metrics, and human adoption are proposed. The findings suggest that AI-based DSS significantly improve material utilization, reduce waste generation, and support proactive decision-making when aligned with organizational processes and digital infrastructures. However, challenges related to data quality, explainability, scalability, and governance remain critical barriers. The paper concludes by outlining future research directions and practical recommendations for advancing AI-enabled sustainable construction.