Machine Learning Model for Construction Time Prediction: A Case of Selected Public Building Projects in Hosanna, Ethiopia

Author:

Debero Demoze Wondimu,Sinesilassiea Ephrem GirmaORCID

Abstract

The duration of a construction project is a vital factor to consider before the commencement of the new project. Nowadays, the common problem in the construction industry is time overrun. The main reason for this is the poor prediction of construction contract durations. Therefore, the objective of this study is to evaluate and validate Bromilow’s time‐cost model and Love et al.’s time‐floor model to estimate early project durations for public building construction projects in the Hadiya Zone. The study also suggested an alternative duration machine learning prediction model by considering possibly influential project influencing factors. A questionnaire survey is designed to collect data, and subsequently, the study was performed using the Python programming language for development and validation purposes with different libraries used. The study developed Bromilow’s time‐cost model using a simple linear regression algorithm and Love et al.’s time‐floor model using a multiple linear regression algorithm and proposed a parametric model using random forest, XGBoost, decision tree, K‐nearest neighbor, and polynomial regression algorithms. This study extends the body of knowledge related to construction time performance, and it contributes valuable insights that inform the implementation of machine learning model for construction time prediction.

Publisher

Wiley

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3