Digital Twins and AI Decision Models: Advancing Cost Modelling in Off-Site Construction

The rising demand for housing continues to outpace traditional construction processes, highlighting the need for innovative, efficient, and sustainable delivery models. Off-site construction (OSC) has emerged as a promising alternative, offering faster project timelines and enhanced cost management. However, current research on cost models for OSC, particularly in automating material take-offs and optimising cost performance, remains limited. This study addresses this gap by proposing a new cost model integrating Digital Twin (DT) technology and AI-driven decision models for modular housing in the UK. The research explores the role of DTs in enhancing cost estimation and decision-making processes. By leveraging DTs and AI, the proposed model evaluates the impact of emergent technologies on cost performance, material efficiency, and sustainability across social, environmental, and economic dimensions. As proposed, this integrated approach enables a cost model tailored for OSC systems, providing a data-driven foundation for cost optimisation and material take-offs. The study’s findings highlight the potential of combining DTs and AI decision models to enhance cost modelling in modular construction, offering new capabilities to support sustainable and performance-driven housing delivery. The paper introduces a dynamic, data-driven cost model integrating real-time data acquisition through DTs and AI-powered predictive analytics. This dynamic approach enhances cost accuracy, reduces lifecycle cost variability, and supports adaptive decision-making throughout the OSC project lifecycle.