An Integrated Machine Learning Framework for Predictive and Sustainable Road Construction Project Management

The increasing demand for proactive and sustainable project management in road construction has created a need for integrated data-driven prediction frameworks. Road construction projects are frequently affected by cost overruns, schedule delays, technical uncertainty, and coordination challenges, which reduce project efficiency and complicate effective control. This study proposes an integrated machine learning framework for predictive and sustainable road construction project management. The framework uses structured project data to predict key outcomes, including actual cost, actual duration, risk level, and completion percentage. It combines target-specific models, overrun-based target engineering, logical output constraints, and an interpretable explanation layer. The framework was developed using a dataset of 1,500 road construction projects and evaluated on 100 holdout projects. The results show strong predictive performance for the main targets. Cost prediction achieved a MAPE of 2.89% and an R² of 0.99, while duration prediction achieved a MAPE of 3.09% and an R² of 0.97. Risk classification reached an accuracy of 90%, while completion percentage showed comparatively strong performance and is therefore treated as a supporting indicator. Overall, the findings demonstrate that the proposed framework can provide accurate, interpretable, and practically useful support for road project forecasting. This study provides a transferable decision-support framework for more proactive and sustainable infrastructure delivery.