Risk identification and management are the two most important parts of construction project management. Better risk management can help in determining the future consequences, but identifying possible risk factors has a direct and indirect impact on the risk management process. In this paper, a risk prediction system based on a cross analytical-machine learning model was developed for construction megaprojects. A total of 63 risk factors pertaining to the cost, time, quality, and scope of the megaproject and primary data were collected from industry experts on a five-point Likert scale. The obtained sample was further processed statistically to generate a significantly large set of features to perform K-means clustering based on high-risk factor and allied sub-risk component identification. Descriptive analysis, followed by the synthetic minority over-sampling technique (SMOTE) and the Wilcoxon rank-sum test was performed to retain the most significant features pertaining to cost, time, quality, and scope. Eventually, unlike classical K-means clustering, a genetic-algorithm-based K-means clustering algorithm (GA–K-means) was applied with dual-objective functions to segment high-risk factors and allied sub-risk components. The proposed model identified different high-risk factors and sub-risk factors, which cumulatively can impact overall performance. Thus, identifying these high-risk factors and corresponding sub-risk components can help stakeholders in achieving project success. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.