Selection of the Project Delivery Systems for China’s Construction Projects with Artificial Neural Network and Data Envelopment Analysis

Purpose – The suitability of the project delivery system (PDS) selected for a project greatly influences the efficiency with which the project is executed. It is not an easy task to select an appropriate PDS as a large amount of ambiguous information exists. The aim of this paper is therefore to develop a PDS selection Model to help owner’s decision-making. Design/methodology/approach – Similar projects are identified through the similarity metrics between the target project to be predicted and those in the database. Then some of the indicator values are examined and modified through DEA-BND model and then are trained by ANN model to predict an appropriate PDS for the target project. A survey was conducted by postal questionnaire to empirically validate the reliability of the model. Findings – The indicator system of the PDS selection is established. Through the comparison of predicted results from different models, it is found out that the developed PDS selection model in this paper can predict PDS more precisely and shows higher reliability than the ANN model. Originality/value – A new PDS selection model is developed by inputting project-specific data, which proves to be more accurate and less dependent on experts’ judgment. Its practical application will benefit the owner’s decision making in selecting the PDS. Key Word: Construction Project, Project Delivery System, Data Envelopment Analysis, Artificial Neural Network, China