Actual construction cost prediction using hypergraph deep learning techniques

Abstract

Accurate construction cost estimation at early stages is critical to enable project stakeholders to make financial decisions (e.g., set up the project budget). However, the heavy reliance on cost engineers’ subjective experience and manual effort in practice makes the estimation an error-prone and time-consuming process. To this end, this study proposes a novel hypergraph deep learning-based framework to predict the actual costs of construction projects accurately and efficiently at early stages. It starts with a systematic hypergraph formulation incorporating construction cost factors and their interrelationships. A hypergraph deep learning model is then developed based on the formulated hypergraph for end-to-end construction cost prediction. Afterwards, model interpretation is undertaken to reveal the cost factor importance from the model training results in a quantitative manner. The framework is validated using an actual construction cost dataset of school projects. The results show high accuracy in cost prediction without human intervention and meaningful interpretations of cost factor importance for better understanding of construction cost patterns.