Risk Identification, Assessments, and Prediction for Mega Construction Projects: A Risk Prediction Paradigm Based on Cross Analytical-Machine Learning Model

Risk identification and management are the two most important parts of construction project management. Better risk can help in determining future consequences, but identifying possible factors has a direct indirect impact on process. In this paper, prediction system based cross analytical-machine learning model was developed for megaprojects. A total 63 pertaining to cost, time, quality, scope megaproject primary data were collected from industry experts five-point Likert scale. The obtained sample further processed statistically generate significantly large set features perform K-means clustering high-risk factor allied sub-risk component identification. Descriptive analysis, followed by synthetic minority over-sampling technique (SMOTE) Wilcoxon rank-sum test performed retain significant scope. Eventually, unlike classical clustering, genetic-algorithm-based algorithm (GA–K-means) applied with dual-objective functions segment components. proposed identified different factors, which cumulatively overall performance. Thus, these corresponding components stakeholders achieving success.