Cover Image

Applying machine learning and particle swarm optimization for predictive modeling and cost optimization in construction project management

The process of cost optimization in construction projects entails the systematic reduction of expenses and the maximization of value through the efficient management of resources, cost control, and the attainment of project objectives within the limitations of the budget. This study examines the uti...

Full description

Saved in:
Bibliographic Details
Main Authors: almahameed, Bader aldeen, Bisharah, Majdi
Format: Article
Published: Institute for Ionics 2024
Online Access:http://psasir.upm.edu.my/id/eprint/105697/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85165693883&doi=10.1007%2fs42107-023-00843-7&partnerID=40&md5=5cf58a212a77baf3a2055d132957de1b
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.upm.eprints.105697
record_format eprints
spelling my.upm.eprints.1056972024-02-15T03:44:29Z http://psasir.upm.edu.my/id/eprint/105697/ Applying machine learning and particle swarm optimization for predictive modeling and cost optimization in construction project management almahameed, Bader aldeen Bisharah, Majdi The process of cost optimization in construction projects entails the systematic reduction of expenses and the maximization of value through the efficient management of resources, cost control, and the attainment of project objectives within the limitations of the budget. This study examines the utilization of different Machine Learning algorithms, such as Linear Regression, Decision Trees, Support Vector Machines (SVM), Gradient Boosting, Random Forest, K-Nearest Neighbors (KNN), Convolutional Neural Network (CNN) Regression, and Particle Swarm Optimization (PSO), in the domain of predictive modeling and cost optimization in the field of construction project management. The primary aims of this study encompass the improvement of cost estimation precision, the identification of pivotal factors that impact project costs, and the implementation of strategies aimed at reducing costs. Evaluation metrics such as Mean Squared Error, Root Mean Squared Error, Mean Absolute Error, and R-squared are commonly employed in the assessment of Machine Learning models' performance. The Voting regression, which leverages the collective predictive power of multiple models, exhibits superior performance in comparison to individual algorithms. Feature selection methods play a crucial role in identifying the variables that have a significant impact on project costs. By employing these methods, organizations can effectively allocate resources and exercise control over costs. Particle Swarm Optimization (PSO) has demonstrated its efficacy in addressing the issue of construction waste reduction and enhancing the accuracy of cost estimation through the identification of optimal combinations of variables. This study emphasizes the importance of Machine Learning and Particle Swarm Optimization (PSO) in the context of predictive modeling and cost optimization within the field of construction project management. The results of this study can provide valuable insights for professionals in the construction industry, aiding them in making informed decisions, allocating resources effectively, achieving project success, and enhancing profitability. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG. Institute for Ionics 2024 Article PeerReviewed almahameed, Bader aldeen and Bisharah, Majdi (2024) Applying machine learning and particle swarm optimization for predictive modeling and cost optimization in construction project management. Asian Journal of Civil Engineering, 25 (2). pp. 1281-1294. ISSN 1563-0854; ESSN: 2522-011X https://www.scopus.com/inward/record.uri?eid=2-s2.0-85165693883&doi=10.1007%2fs42107-023-00843-7&partnerID=40&md5=5cf58a212a77baf3a2055d132957de1b 10.1007/s42107-023-00843-7
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
description The process of cost optimization in construction projects entails the systematic reduction of expenses and the maximization of value through the efficient management of resources, cost control, and the attainment of project objectives within the limitations of the budget. This study examines the utilization of different Machine Learning algorithms, such as Linear Regression, Decision Trees, Support Vector Machines (SVM), Gradient Boosting, Random Forest, K-Nearest Neighbors (KNN), Convolutional Neural Network (CNN) Regression, and Particle Swarm Optimization (PSO), in the domain of predictive modeling and cost optimization in the field of construction project management. The primary aims of this study encompass the improvement of cost estimation precision, the identification of pivotal factors that impact project costs, and the implementation of strategies aimed at reducing costs. Evaluation metrics such as Mean Squared Error, Root Mean Squared Error, Mean Absolute Error, and R-squared are commonly employed in the assessment of Machine Learning models' performance. The Voting regression, which leverages the collective predictive power of multiple models, exhibits superior performance in comparison to individual algorithms. Feature selection methods play a crucial role in identifying the variables that have a significant impact on project costs. By employing these methods, organizations can effectively allocate resources and exercise control over costs. Particle Swarm Optimization (PSO) has demonstrated its efficacy in addressing the issue of construction waste reduction and enhancing the accuracy of cost estimation through the identification of optimal combinations of variables. This study emphasizes the importance of Machine Learning and Particle Swarm Optimization (PSO) in the context of predictive modeling and cost optimization within the field of construction project management. The results of this study can provide valuable insights for professionals in the construction industry, aiding them in making informed decisions, allocating resources effectively, achieving project success, and enhancing profitability. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.
format Article
author almahameed, Bader aldeen
Bisharah, Majdi
spellingShingle almahameed, Bader aldeen
Bisharah, Majdi
Applying machine learning and particle swarm optimization for predictive modeling and cost optimization in construction project management
author_facet almahameed, Bader aldeen
Bisharah, Majdi
author_sort almahameed, Bader aldeen
title Applying machine learning and particle swarm optimization for predictive modeling and cost optimization in construction project management
title_short Applying machine learning and particle swarm optimization for predictive modeling and cost optimization in construction project management
title_full Applying machine learning and particle swarm optimization for predictive modeling and cost optimization in construction project management
title_fullStr Applying machine learning and particle swarm optimization for predictive modeling and cost optimization in construction project management
title_full_unstemmed Applying machine learning and particle swarm optimization for predictive modeling and cost optimization in construction project management
title_sort applying machine learning and particle swarm optimization for predictive modeling and cost optimization in construction project management
publisher Institute for Ionics
publishDate 2024
url http://psasir.upm.edu.my/id/eprint/105697/
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85165693883&doi=10.1007%2fs42107-023-00843-7&partnerID=40&md5=5cf58a212a77baf3a2055d132957de1b
_version_ 1792154559667240960
score 13.211869

Similar Items