The object of research is the potential application of digital twins and neural network modeling for optimizing construction processes. Method. Adopting a perspective approach, the research conducts an extensive review of existing literature and delineates a theoretical framework for integrating digital twins and neural network modeling technologies. Insights from the literature review inform the development of methodologies, while case studies and practical applications are explored to deepen understanding of these integrated approaches to system construction optimization. Results. The review yields the following key findings: Digital Twins: Offer the capability to create high-fidelity virtual representations of physical construction systems, enabling real-time data collection, analysis, and visualization throughout the project lifecycle. This allows for proactive decision-making, improved constructability analysis, and enhanced coordination between design and field operations. Neural Network Modeling: Possesses the power to learn complex relationships from vast datasets, enabling predictive modeling and optimization of construction system behavior. Neural networks can be employed to forecast project timelines, identify potential risks, and optimize construction scheduling and resource allocation. Integration of Digital Twins and Neural Networks: Presents a transformative avenue for optimizing construction processes by facilitating data-driven design, predictive maintenance of equipment and infrastructure, and real-time performance monitoring. This synergistic approach can lead to significant improvements in construction efficiency, reduced project costs, and enhanced overall project quality.