[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125317-en":3,"doc-seo-125317-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125317,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine learning for the prediction of rework in green buildings - Paper","Green buildings aim to reduce negative impacts on occupants, communities, and the environment while supporting contractor productivity and profitability. Despite the benefits of sustainable practices, rework remains frequent in green building projects and drives quality loss, disputes, claims, and cost and schedule overruns. This paper develops eight machine learning models to predict rework in green buildings using 65 instances and 16 features, after applying feature scaling and normalization.","CIB Conferences  \n\n| Volume 1 | Article 339 |\n| --- | --- |\n| 2025\u003Cbr>Machine learning for the prediction of rework in green\u003Cbr>AbdulLateef Olanrewaju\u003Cbr>Universiti Tunku Abdul Rahman (UTAR), [olanrewaju20002000@gmail.com](olanrewaju20002000@gmail.com)\u003Cbr>Follow this and additional works at: [https://docs.lib.purdue.edu/cib-conferences](https://docs.lib.purdue.edu/cib-conferences) | buildings |\n\nRecommended Citation  \nOlanrewaju, AbdulLateef (2025) \"Machine learning for the prediction of rework in green buildings,\" CIB Conferences: Vol. 1 Article 339.  \nDOI: [https://doi.org/10.7771/3067-4883.1659](https://doi.org/10.7771/3067-4883.1659)  \nThis document has been made available through Purdue e-Pubs, a service of the Purdue University Libraries. [Please contact epubs@purdue.edu](Please contact epubs@purdue.edu) for additional information.  \nMachine Learning for the Prediction of Rework in Green Buildings  \nAbdulLateef Olanrewaju, [olanrewaju20002000@gmail.com](olanrewaju20002000@gmail.com)[ ](olanrewaju20002000@gmail.com)Universiti Tunku Abdul Rahman, Malaysia  \nAbstract  \nGreen buildings are designed to minimize the negative impact of construction on occupants, communities, and the environment, while enhancing contractor productivity and profitability. However, despite the advantages and potential of sustainable building practices, construction companies frequently encounter rework issues in green building projects.This paper presents research aimed at predicting rework occurrences in green buildings using advanced machine learning techniques. Eight machine learning models were trained on a dataset comprising 65 instances and 16 features. To ensure consistency across the dataset, feature scaling and normalization were performed.The study identifies variations in project characteristics, cost overruns, time overruns, client experience, client types, specifications, and project size as the primary predictors of rework in green buildings. Among the models, Gradient Boosting, AdaBoost, and Random Forest demonstrated the highest predictive accuracy. Specifically, the Gradient Boosting model achieved an accuracy of 97%, with precision, recall, and an F1-score all at 97% . Similarly, the AdaBoost model also achieved an accuracy of 97%, with precision at 97%, recall at 92%, and an F1-score of 97%.These findings have significant theoretical and practical implications, offering valuable insights for advancing sustainable construction management. By bridging a notable gap in the literature, this study highlights the applicability of machine learning to predict rework in green building projects, an area that remains underexplored in sustainable construction research.  \nKeywords: classifiers, claims, productivity, defects, site operatives, Malaysia.  \n1 Introduction  \nThe construction sector contributes up to 10% of GDP and employs over 10% of the workforce in many economies. Despite its significant role, the sector's overall performance remains below expectations, particularly in terms of quality. The finished quality of construction products often lags behind that of other industries, and poor quality frequently costs the sector more than its profit margins. For example, better quality management could save the UK construction industry up to £12 billion annually (Montague, 2018) . The impact of rework is similarly substantial across various regions. In South Africa, rework accounts for 5.12% of construction costs (Simpeh et al., 2015), while in Singapore, nearly a quarter of project schedule extensions are due to rework (Hwang and Yang, 2014) . In Malaysia, Olanrewaju and Lee (2022) reported that rework occurred in more than 80% of building projects, with poor quality affecting up to 60% of these projects. Rework has far-reaching consequences, including reduced productivity, lower profit margins, disputes, claims, cost and time overruns, strained relationships, and diminished client satisfaction (Olanrewaju, 2022; Enshassi et al., 2017).","cbCaigIdqQagMsLs","https://ap.wps.com/l/cbCaigIdqQagMsLs","pdf",989583,1,13,"English","en",105,"# Abstract\n# 1 Introduction\n# 2 Literature review","[{\"question\":\"What problem does the paper address in green building projects?\",\"answer\":\"It addresses frequent rework in green building projects and the resulting quality deterioration, disputes, claims, and cost/schedule overruns.\"},{\"question\":\"How is rework predicted in the study?\",\"answer\":\"Eight machine learning models are trained on a dataset with 65 instances and 16 features, using feature scaling and normalization.\"},{\"question\":\"Which models achieve the best predictive accuracy?\",\"answer\":\"Gradient Boosting, AdaBoost, and Random Forest show the highest accuracy, with Gradient Boosting and AdaBoost reaching about 97% accuracy.\"}]","Machine learning for the prediction of rework in green buildings - Paper | PDF",1785898138,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-for-the-prediction-of-rework-in-green-buildings-paper","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-for-the-prediction-of-rework-in-green-buildings-paper/125317/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper address in green building projects?","Question",{"text":75,"@type":76},"It addresses frequent rework in green building projects and the resulting quality deterioration, disputes, claims, and cost/schedule overruns.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is rework predicted in the study?",{"text":80,"@type":76},"Eight machine learning models are trained on a dataset with 65 instances and 16 features, using feature scaling and normalization.",{"name":82,"@type":73,"acceptedAnswer":83},"Which models achieve the best predictive accuracy?",{"text":84,"@type":76},"Gradient Boosting, AdaBoost, and Random Forest show the highest accuracy, with Gradient Boosting and AdaBoost reaching about 97% accuracy.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]