Cost overrun risks are declared to be dynamic and interdependent. Ignoring the relationship between cost overrun risks during the risk assessment process is one of the primary reasons construction projects go over budget. Conversely, recent studies have failed to account for potential interrelationships between risk factors in their machine learning (ML) models. Additionally, the presented ML models are not interpretable. Thus, this study contributes to the entire ML process using a Bayesian network (BN) classifier model by considering the possible interactions between predictors, which are cost overrun risks, to predict cost overrun and assess cost overrun risks. Furthermore, this study compared the BN classifier model’s performance accuracy to that of the Naive Bayes (NB) and decision tree (DT) models to determine the effect of considering possible correlations between cost overrun risks on prediction accuracy. Moreover, the most critical risks and their relationships are identified by interpreting the learned BN model. The results indicated that the 18 BN models demonstrated an average prediction accuracy of 78.86%, significantly higher than the NB and DT. The present study identified the most significant risks as an increase in the cost of materials, lack of knowledge and experience among human resources, and inflation.

The construction industry involves a variety of construction works, all of which differ in terms of the frequency and probability of fatal incidents and types of accidents. Accordingly, the risk level of various construction works should be defined for effective safety management at the design and construction phases. This study proposes an approach for quantifying the risk level of fatal incidents in construction works based on frequency and probability analysis using estimation and clustering methods. The main study objective is accomplished in four steps. It was found that the average normalized ranking (ANR) ranged from 2.51 to 26.88, with the most dangerous construction works being scaffolding and demolition works (2.51). Based on the ANR, 27 construction works were categorized into five groups with risk levels ranked from 1 to 5. Risk level 5, the most dangerous group of construction works, was composed of scaffolding and demolition works and roofing and sheet metal construction works, both of which were higher than other construction works considering the frequency and probability of fatal incidents.