An integrated BIM-AI framework for intelligent cost management

Accurate cost estimation and adaptive budget control remain central challenges in building project delivery, where traditional methods are often slow, subjective, and poorly equipped to respond to design changes or market volatility. Building information modeling (BIM) provides a digital foundation for integrating cost and design data, whereas artificial intelligence (AI) offers both predictive and adaptive capabilities. However, their integration into practice remains limited. This study addresses this gap by developing and testing an integrated BIM-AI framework for intelligent cost management. A single case study of a proposed residential building was used to operationalize the framework. Machine learning regression models were applied to predict the total project cost and cost per square meter. Random forests identified the most influential cost drivers, while neural networks captured non-linear relationships between design variables and cost outcomes. Natural language processing was used to extract material quantities and specifications from textual data, and computer vision techniques were used to quantify components directly from the building documentation. Optimization algorithms were then applied to suggest cost-effective materials and design alternatives. The results demonstrated that regression models produced reliable baseline estimation, with neural networks improving the predictive accuracy by handling complex design–cost interactions. Random forest analysis revealed material choices, structural specifications, and finish quality as the most significant cost drivers. Optimization runs showed that substituting selected materials could reduce the overall cost by up to 12% without compromising the performance. The findings confirm that integrated BIM-AI techniques can intelligently generate cost estimation, adapt to dynamic project conditions, and optimize budget allocations. This research advances knowledge by bridging methodological gaps and provides practical insights for digital construction management.