Artificial Neural Network Model to relate Organization Characteristics and Construction Project Delivery Methods

Abstract

This study aims to relate organizational characteristics on preferences for project delivery methods (PDMs) in construction industry of Pakistan. Artificial Neural Network (ANN) based model is developed for predicting proportion of projects done by different types of organizations under various PDMs. It is found that ANN model give satisfactory accuracy in predicting these proportions for test and training datasets. It is found that client organizations are more inclined towards traditional methods, especially Design-Bid-Build (DBB). Consultant organizations had relatively higher proportion of projects done by Design-Build (DB) and other non-traditional methods. Most of the construction organizations belong to the private sector which showed an inclination towards DBB and DB methods. The non-traditional PDMs had relatively higher preference for organizations who are involved in infrastructure or other specialized projects. Organizations who have more projects showed more tendency towards non-traditional PDMs. (C) 2018 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/3.0/) Peer-review under responsibility of the scientific committee of the 13th International Conference on Future Networks and Communications, FNC-2018 and the 15th International Conference on Mobile Systems and Pervasive Computing, MobiSPC 2018.