The construction industry faces persistent challenges in managing cost overruns, schedule delays, and project risks, driven by project complexity, resource variability, and dynamic market conditions. Traditional cost estimation and risk management approaches often rely on historical data, expert judgment, and linear predictive models, which may fail to capture nonlinear patterns, interdependencies, and emerging uncertainties. Recent advancements in Artificial Intelligence (AI) offer transformative potential to enhance construction cost prediction, risk identification, and mitigation strategies. AI-driven models, including machine learning algorithms, neural networks, and hybrid predictive systems, enable real-time data analysis, pattern recognition, and probabilistic forecasting, providing more accurate and adaptive decision-making tools for project stakeholders. This proposes a conceptual framework for applying AI to construction cost prediction and risk mitigation, integrating data acquisition, algorithm selection, model training, and decision support mechanisms within the project lifecycle. The framework emphasizes the synergy between AI technologies and project management processes, highlighting how predictive analytics, anomaly detection, and scenario simulation can proactively identify cost drivers, quantify uncertainties, and suggest risk-reducing interventions. By leveraging AI, stakeholders—including project managers, engineers, contractors, and policymakers—can optimize budgeting, enhance resource allocation, and mitigate financial and operational risks. Key insights from the framework suggest that AI adoption can improve forecast accuracy, reduce unforeseen expenditures, and support evidence-based decision-making in complex construction projects. The framework also identifies critical enablers and barriers, including data quality, organizational readiness, technology integration, and regulatory compliance, which influence the successful deployment of AI applications. This conceptual framework provides a foundation for empirical validation, algorithmic refinement, and policy development, facilitating the mainstreaming of AI as a strategic tool for sustainable, cost-effective, and resilient construction project delivery. It offers practical guidance for industry stakeholders and researchers aiming to harness AI’s predictive capabilities to enhance project performance, reduce risks, and achieve more reliable financial and operational outcomes in construction management.
Eyinade et al. (Wed,) studied this question.