Estimating labor resource requirements in construction projects using machine learning

IF 3.1 Q2 CONSTRUCTION & BUILDING TECHNOLOGY
Hamidreza Golabchi, A. Hammad
{"title":"Estimating labor resource requirements in construction projects using machine learning","authors":"Hamidreza Golabchi, A. Hammad","doi":"10.1108/ci-11-2021-0211","DOIUrl":null,"url":null,"abstract":"\nPurpose\nExisting labor estimation models typically consider only certain construction project types or specific influencing factors. These models are focused on quantifying the total labor hours required, while the utilization rate of the labor during the project is not usually accounted for. This study aims to develop a novel machine learning model to predict the time series of labor resource utilization rate at the work package level.\n\n\nDesign/methodology/approach\nMore than 250 construction work packages collected over a two-year period are used to identify the main contributing factors affecting labor resource requirements. Also, a novel machine learning algorithm – Recurrent Neural Network (RNN) – is adopted to develop a forecasting model that can predict the utilization of labor resources over time.\n\n\nFindings\nThis paper presents a robust machine learning approach for predicting labor resources’ utilization rates in construction projects based on the identified contributing factors. The machine learning approach is found to result in a reliable time series forecasting model that uses the RNN algorithm. The proposed model indicates the capability of machine learning algorithms in facilitating the traditional challenges in construction industry.\n\n\nOriginality/value\nThe findings point to the suitability of state-of-the-art machine learning techniques for developing predictive models to forecast the utilization rate of labor resources in construction projects, as well as for supporting project managers by providing forecasting tool for labor estimations at the work package level before detailed activity schedules have been generated. Accordingly, the proposed approach facilitates resource allocation and enables prioritization of available resources to enhance the overall performance of projects.\n","PeriodicalId":45580,"journal":{"name":"Construction Innovation-England","volume":" ","pages":""},"PeriodicalIF":3.1000,"publicationDate":"2023-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Construction Innovation-England","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1108/ci-11-2021-0211","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose Existing labor estimation models typically consider only certain construction project types or specific influencing factors. These models are focused on quantifying the total labor hours required, while the utilization rate of the labor during the project is not usually accounted for. This study aims to develop a novel machine learning model to predict the time series of labor resource utilization rate at the work package level. Design/methodology/approach More than 250 construction work packages collected over a two-year period are used to identify the main contributing factors affecting labor resource requirements. Also, a novel machine learning algorithm – Recurrent Neural Network (RNN) – is adopted to develop a forecasting model that can predict the utilization of labor resources over time. Findings This paper presents a robust machine learning approach for predicting labor resources’ utilization rates in construction projects based on the identified contributing factors. The machine learning approach is found to result in a reliable time series forecasting model that uses the RNN algorithm. The proposed model indicates the capability of machine learning algorithms in facilitating the traditional challenges in construction industry. Originality/value The findings point to the suitability of state-of-the-art machine learning techniques for developing predictive models to forecast the utilization rate of labor resources in construction projects, as well as for supporting project managers by providing forecasting tool for labor estimations at the work package level before detailed activity schedules have been generated. Accordingly, the proposed approach facilitates resource allocation and enables prioritization of available resources to enhance the overall performance of projects.
利用机器学习估算建筑项目中的劳动力资源需求
目的现有的人工估算模型通常只考虑特定的建设项目类型或特定的影响因素。这些模型专注于量化所需的总劳动时间,而项目期间的劳动利用率通常不被考虑在内。本研究旨在建立一种新的机器学习模型来预测工作包层面的劳动力资源利用率时间序列。设计/方法/方法在两年的时间里收集了250多个建筑工作包,用于确定影响劳动力资源需求的主要因素。同时,采用一种新颖的机器学习算法——递归神经网络(RNN),建立了一种预测模型,可以预测劳动力资源随时间的利用情况。本文提出了一种鲁棒的机器学习方法,用于基于确定的影响因素预测建筑项目中劳动力资源的利用率。发现机器学习方法可以产生使用RNN算法的可靠时间序列预测模型。所提出的模型表明了机器学习算法在促进建筑行业传统挑战方面的能力。独创性/价值研究结果指出了最先进的机器学习技术的适用性,用于开发预测模型来预测建筑项目中劳动力资源的利用率,以及在详细的活动计划生成之前,通过为工作包级别的劳动力估计提供预测工具来支持项目经理。因此,拟议的方法有助于资源分配,并能够确定现有资源的优先次序,以提高项目的总体绩效。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Construction Innovation-England
Construction Innovation-England CONSTRUCTION & BUILDING TECHNOLOGY-
CiteScore
7.10
自引率
12.10%
发文量
71
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信