Enhanced Construction Schedule Prediction Using Ensemble Machine Learning: A Comparative Case Study
Journal of Architecture and Civil Engineering · 2024
DOI: 10.35629/8193-09022836 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Architecture and Civil Engineering, 2024. Verfasst von Sai Kothapalli Sai Kothapalli.
Abstract (Originalsprache)
Construction projects are notorious for schedule overruns, leading to significant financial losses and stakeholder dissatisfaction. This research presents a novel machine learning (ML) approach to predict construction schedules with enhanced accuracy. This research methodology employs a comparative analysis of multiple ML algorithms trained on historical project data from 87 commercial construction projects completed between 2018-2023. Results demonstrate that the ensemble model achieves a 27% improvement in schedule prediction accuracy compared to traditional Critical Path Method (CPM) estimations, with a mean absolute percentage error (MAPE) of 8.3%. The findings provide construction professionals with a reliable tool to mitigate scheduling risks and improve project delivery outcomes.
Zitieren
APA
Kothapalli, S. K. S. (2024). Enhanced Construction Schedule Prediction Using Ensemble Machine Learning: A Comparative Case Study. Journal of Architecture and Civil Engineering. https://doi.org/10.35629/8193-09022836
Vancouver
Kothapalli SKS. Enhanced Construction Schedule Prediction Using Ensemble Machine Learning: A Comparative Case Study. Journal of Architecture and Civil Engineering. 2024. doi:10.35629/8193-09022836
BibTeX
@article{Kothapalli2024,
author = {Kothapalli, Sai Kothapalli Sai},
title = {Enhanced Construction Schedule Prediction Using Ensemble Machine Learning: A Comparative Case Study},
journal = {Journal of Architecture and Civil Engineering},
year = {2024},
doi = {10.35629/8193-09022836}
}
EUVIMED