IGLC.net
EXPORT DATE: 19 June 2026

@CONFERENCE{Francesconi2026,
author={Francesconi, Caroll and Forcael, Eric and Valdebenito, Reinaldo },
editor={Hamzeh, Farook and Poshdar, Mani and Garcia-Lopez,, Nelly P. },
title={A digital lean framework for early-stage urban regulatory decision-making}, 
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={307-316},
url={http://www.iglc.net/papers/details/2584},
doi={10.24928/2026/0307},
affiliation={Assistant Professor, Facultad de Ingeniería, Universidad San Sebastián, Concepción 4081339, Chile; caroll.francesconi@uss.cl, orcid.org/0009-0008-0667-1805 ; Professor, Facultad de Ingeniería, Universidad San Sebastián, Concepción 4081339, Chile; eric.forcael@uss.cl, orcid.org/0000-0002-3036-4329 ; Lecturer, Department of Construction and Risk Prevention, Universidad Técnica Federico Santa María, Concepción 4603255, Chile; reinaldo.valdebenito@usm.cl, orcid.org/0009-0003-8384-032X },
abstract={Early-stage regulatory decisions play a critical role in the delivery of construction projects. However, regulatory processes are frequently characterized by fragmented information, limited transparency, and iterative rework, generating significant waste that contradicts Lean Construction principles. From a Lean perspective, regulatory decision-making can be understood as a production system whose performance directly affects downstream planning, cost, and schedule reliability. This paper proposes a digital, Lean-oriented framework that supports early-stage regulatory decision-making by classifying administrative records using data-driven methods. Using secondary, publicly available data from urban land-use certificates and building permit records, the study applies Machine Learning techniques to structure, classify, and standardize regulatory information, illustrating how such data can be organized to support earlier feasibility analysis. The proposed framework shifts regulatory analysis from expert-dependent interpretation to a system-level information flow, potentially enhancing predictability and reducing rework at the front end of projects. Because of its exploratory nature, the findings of the present study provide a structured basis for improving interpretability and consistency in regulatory decision-making. In this sense, the research contributes to the Lean Construction literature by extending Lean thinking to regulatory processes and proposing a transferable, data-driven framework for complex urban development contexts. },
author_keywords={Lean construction, urban regulations, decision-making, machine learning. },
address={Singapore, Singapore },
issn={2789-0015 },
publisher={ },
language={English},
document_type={Conference Paper},
source={IGLC},
}