IGLC.net
EXPORT DATE: 19 June 2026

@CONFERENCE{Bidhendi2026,
author={Bidhendi, Ali and Golsorkhi, Sina and Poshdar, Mani and Jelodar, Mostafa Babaeian },
editor={Hamzeh, Farook and Poshdar, Mani and Garcia-Lopez,, Nelly P. },
title={Mapping AI and lean construction integration: a network analysis framework for construction productivity}, 
journal={Proceedings of the 34th Annual Conference of the International Group for Lean Construction (IGLC 34)}, 
booktitle={Proceedings of the 34th Annual Conference of the International Group for Lean Construction (IGLC 34)}, 
year={2026},
pages={155-168},
url={http://www.iglc.net/papers/details/2522},
doi={10.24928/2026/0223},
affiliation={Auckland University of Technology (AUT), New Zealand, ali.bidhendi@autuni.ac.nz, orcid.org/0000-0002-8285-5859 ; Auckland University of Technology (AUT), New Zealand, sina.golsorkhi@autuni.ac.nz, orcid.org/0009-0003-3047-3634 ; Auckland University of Technology (AUT), New Zealand, mani.poshdar@aut.ac.nz, orcid.org/0000-0001-9132-2985 ; Massey University, New Zealand, M.B.Jelodar@massey.ac.nz, orcid.org/0000-0003-1956-7384 },
abstract={The construction industry continues to face persistent productivity challenges, including inefficiencies, schedule delays, and resource underutilisation. While artificial intelligence has shown potential in construction applications for sensing, predicting, and explaining process behaviour, capabilities that align with lean construction's focus on flow reliability, waste visibility, and continuous learning, their systematic integration with lean principles remains fragmented. This study employs Social Network Analysis to systematically examine relationships between AI approaches and lean construction constructs. A systematic literature review of peer-reviewed studies (2015–2025) was conducted to map interconnections between AI approaches and 14 lean construction constructs, using weighted adjacency matrices and degree centrality measures to quantify relationship patterns. Key findings reveal significant variation in connectivity, with real-time analytics, machine learning, and computer vision showing the broadest coverage across lean constructs. The analysis identifies natural alignment opportunities: predictive analytics with continuous improvement processes, and computer 14vision with visual management and waste reduction. Based on these findings, we propose a three-tier integration framework enabling organisations to prioritise AI approaches based on (i) breadth of lean alignment and (ii) their lean priorities and implementation readiness. This research provides evidence-based prioritisation guidance for construction practitioners and contributes to theoretical understanding of digital transformation in lean construction. },
author_keywords={AI, lean construction, construction productivity, digital transformation. },
address={Singapore, Singapore },
issn={2789-0015 },
publisher={ },
language={English},
document_type={Conference Paper},
source={IGLC},
}