Large‐scale complex public projects face greater, more uncertain, and more diverse risks due to their particular characteristics of large size, long duration, and complexity, which bring both opportunities and challenges for construction enterprises. At present, the research on the schedule risk of large‐scale public projects mainly focuses on identifying risk factors causing schedule delays and predicting such delays. However, there is a lack of comprehensive analysis of the interactions among risk factors, and quantitative assessments of the impact intensity and combined effects among these factors are not conducted. Additionally, the use of Bayesian networks (BNs) for quantitative risk assessments faces challenges such as unclear causal and dependency relationships among factors in complex systems and insufficient model interpretability. The purpose of this study is to introduce interpretive structural modeling (ISM) to analyze the relationships among risk factors at various levels, thereby facilitating the construction of a BN for predicting delay risks in large‐scale and complex public projects. This approach aims to effectively address the prevalent issues of incompleteness and uncertainty inherent in such projects. Furthermore, based on this foundation, the study delves into the quantitative relationships and integrated effects among risk factors. Initially, a comprehensive methodology is employed to establish a comprehensive set of schedule risk factors. Subsequently, ISM is utilized to analyze the hierarchical relationships among these factors, which in turn supports the modeling of a BN to construct a schedule delay risk assessment model. This model enables the prediction and quantification of schedule risks, which are then validated through real‐world project cases. Finally, a thorough examination of quantitative relationships, such as factor importance, sensitivity, and integrated effects, is conducted. The results demonstrate that the established model exhibits high accuracy, reusability, enhanced interpretability, and credibility, significantly improving the prediction of schedule delays in practical engineering projects. Moreover, it clarifies the quantitative relationships among the risk factors contributing to schedule delays, providing a scientific and effective theoretical basis and control tool for schedule risk management.
