Project details
This is a three-year project working in collaboration with international construction consultant Gleeds to develop the capability to automate construction cost forecasts using the latest research in data analytics and machine learning.
Building on significant research and expertise into construction cost analysis and benchmarking, this project will elevate the potential to generate quick, risk-based, informative and useable construction cost forecasts. The project requires detailed consideration of a significant volume of existing data, the analysis and profiling of construction project characteristics, the development of data analytics methods to model the data plus an easy-to-access user interface and user experience.
The project will create a new predictable and efficient way of working by embedding intelligence in the design process; it will also provide advanced tools to meet the Construction 2025 efficiency targets.
The application of advanced data analytics and machine learning for construction cost forecasting will fundamentally change cost modelling and cost management practices. At present, cost modelling is typically a manual process and generating accurate cost models relies heavily on individual expertise. There is no quick, simple, and efficient way to provide an accurate cost model and analyse it for risk.
Creating functionality and outputs that generate easy to understand, reliable cost models will aid the optimisation of design and value and will improve predictability of project delivery. It will help construction clients to deliver the same or better performing projects for less cost and will improve collaboration. Overall, the project will enable Gleeds and the University of Nottingham to become key advocates for the digital transformation of the construction industry.