AI-Driven Schedule Delay Prediction and Mitigation in Construction Projects: A Systematic Literature Review

Abstract

Construction project delays remain a persistent challenge in the industry, often leading to significant cost overruns and contractual disputes. The objective of this systematic literature review is to synthesize and critically evaluate the existing research on artificial intelligence (AI) applications for predicting and mitigating schedule delays in construction projects. We conducted a systematic search across major academic databases, followed by a rigorous screening and quality assessment process to identify relevant peer-reviewed studies. Our methodology involved a thematic analysis of the selected papers, categorizing the literature into six principal dimensions: AI-driven cost estimation and financial risk prediction, schedule delay prediction and time optimization models, holistic risk management and mitigation strategies, the integration of AI with Building Information Modeling (BIM) and digital twins, the role of generative AI and large language models in decision support, and finally, bibliometric analyses of AI adoption trends. The results reveal that machine learning and deep learning models, particularly those trained on historical project data, demonstrate high accuracy in forecasting delays, while reinforcement learning approaches show promise for dynamic schedule optimization. Furthermore, we found that the synergistic integration of AI with BIM and digital twins provides a powerful framework for real-time monitoring and proactive mitigation, although practical implementation remains limited by data quality and organizational barriers. In conclusion, this review provides a comprehensive map of the current state of the art, identifies critical research gaps such as the scarcity of studies on generative AI in this domain, and proposes a conceptual framework for future research. The findings offer actionable insights for practitioners and a clear research agenda for academics aiming to advance predictive and prescriptive analytics in construction schedule management.