[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127309-en":3,"doc-seo-127309-105":31,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},127309,2336475104957,"Seraphina","https://ap-avatar.wpscdn.com/avatar/22000c4c6bd8a5076e1?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786593998035447633",8,"Research & Report","Automated machine learning pipeline for robust project cost and duration forecasting","Projects often encounter cost and schedule overruns, making reliable Estimates at Completion (EACs) essential for corrective actions during execution. Existing supervised ML regression methods for EACs use features from Earned Value Management (EVM) and Earned Schedule Management (ESM) but can be compromised by underfitting and overfitting, reducing robustness. This paper proposes a fully automated ML pipeline with data balancing and augmentation, feature engineering, and rigorous training and evaluation. Tested on 50 real construction projects across 30 ML techniques, it produces more accurate, precise, and timely EAC forecasts than EVM and ESM.","POLITECNICO DI TORINO  \nRepository ISTITUZIONALE  \nAutomated machine learning pipeline for robust project cost and duration forecasting  \nOriginal  \nAutomated machine learning pipeline for robust project cost and duration forecasting / Ottaviani, F. M. ; BallesterosPerez, P. ; Narbaev, T.. -In: AUTOMATION IN CONSTRUCTION. -ISSN 0926-5805. -ELETTRONICO. -178:(2025) .[10.1016/j.autcon.2025.106426]  \nAvailability:  \nThis version is available at: 11583/3002311 since: 2025-08-03T20:59:58Z  \nPublisher:  \nElsevier B.V.  \nPublished  \nDOI:10.1016/j.autcon.2025.106426  \nTerms of use:  \nThis article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository  \nPublisher copyright  \n(Article begins on next page)  \n04 October 2025  \nAutomation in Construction 178 (2025) 106426  \n\n| \u003Cbr>\u003Cbr>Contents lists available at ScienceDirect Automation in Construction\u003Cbr>journal [homepage:](homepage: www.elsevier.com/locate/autcon)[ www.elsevier.com/locate/autcon](homepage: www.elsevier.com/locate/autcon) |  |\n| --- | --- |\n\n\n| Automated machine learning pipeline for robust project cost and duration forecasting\u003Cbr>Filippo Maria Ottaviani a ,∗, Pablo Ballesteros-Pérez b, Timur Narbaev a\u003Cbr>a Department of Management and Production Engineering, Politecnico di Torino, Corso Duca degli Abruzzi, 24, Turin, 10129, Italy b Escuela Técnica Superior de Ingeniería Industrial, Universitat Politècnica de València, Camino de Vera, s/n, València, 46022, Spain |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| Keywords:\u003Cbr>Project management Machine Learning Regression\u003Cbr>Monitoring and control Earned Value Management Estimate at completion |  | Projects often face issues that trigger project controls, where Estimates at Completion (EACs) play a crucial role in determining the scope of corrective actions. Recent studies have applied supervised Machine Learning (ML) regression techniques to develop EAC models, utilizing features derived from Earned Value Management (EVM) and Earned Schedule Management (ESM) methodologies. However, these studies overlook several underfitting and overfitting issues that could compromise model robustness, leading to biased results. This paper introduces an ML pipeline designed to address these issues through automated procedures for data balancing and augmentation, feature engineering, and model training and evaluation. The pipeline was tested with 30 ML techniques on a dataset of 50 real-world construction projects. Results show that the EAC models developed through the pipeline achieve superior accuracy, precision, and timeliness to EVM and ESM ones. These findings validate the pipeline and offer practitioners an automated framework for developing robust, ML-based EAC models. |\n\n1. Introduction  \nOn average, over 90% of construction projects experience cost or schedule overruns because of planning and execution issues [1, 2]. Planning issues are due to inaccurate estimates [3], unrealistic schedules [4], and scope gaps [5]. Execution issues stem from unforeseen internal or external risks that impact project activities and resources [6].  \nEstimates at Completion (EACs) play a key role in project control. They are forecasts of the revised project cost and duration, calculated during the execution phase. Comparing EACs to the project baseline helps determine whether and to what extent corrective actions are needed [7,8]. These actions are aimed at recovering cost and schedule variances to ensure that the project meets the contractual budget and duration constraints.  \nThe state-of-the-art approach to calculating EACs integrates Earned Value Analysis (EVA) with supervised Machine Learning (ML) regression techniques [9]. EVA methodologies, including Earned Value Management (EVM) [10] and Earned Schedule Management (ESM) [11], rely on three metrics: the budgeted cost of work scheduled, the budgeted cost of work performed, and the actual cost of work p","cbCaiiXAbVjSXnCu","https://ap.wps.com/l/cbCaiiXAbVjSXnCu","pdf",973913,2,1,16,"English","en",105,"# Introduction\n## Project cost and schedule overruns\n## Estimates at Completion (EACs) in project control\n## EVA, EVM, and ESM foundations\n## Underfitting and overfitting challenges\n## Study goal and proposed automated ML pipeline","[{\"question\":\"What role do Estimates at Completion (EACs) play in project control?\",\"answer\":\"EACs forecast revised project cost and duration during execution. Comparing them to the project baseline helps determine whether and how corrective actions are needed to meet contractual constraints.\"},{\"question\":\"How does the proposed pipeline address underfitting and overfitting?\",\"answer\":\"It includes automated data balancing and augmentation, nested cross-validation to prevent overfitting during training and evaluation, and indirect regression via intermediate variables to improve generalization.\"},{\"question\":\"How was the pipeline evaluated and what were the results compared with EVM and ESM?\",\"answer\":\"The study tested 30 ML techniques on a dataset of 50 real construction projects. The resulting EAC models achieved superior accuracy, precision, and timeliness versus standard EVM and ESM models.\"}]","Automated machine learning pipeline for robust project cost and duration forecasting | PDF",1785938232,40,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"automated-machine-learning-pipeline-for-robust-project-cost-and-duration-forecasting","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/automated-machine-learning-pipeline-for-robust-project-cost-and-duration-forecasting/127309/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What role do Estimates at Completion (EACs) play in project control?","Question",{"text":76,"@type":77},"EACs forecast revised project cost and duration during execution. Comparing them to the project baseline helps determine whether and how corrective actions are needed to meet contractual constraints.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed pipeline address underfitting and overfitting?",{"text":81,"@type":77},"It includes automated data balancing and augmentation, nested cross-validation to prevent overfitting during training and evaluation, and indirect regression via intermediate variables to improve generalization.",{"name":83,"@type":74,"acceptedAnswer":84},"How was the pipeline evaluated and what were the results compared with EVM and ESM?",{"text":85,"@type":77},"The study tested 30 ML techniques on a dataset of 50 real construction projects. The resulting EAC models achieved superior accuracy, precision, and timeliness versus standard EVM and ESM models.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":30,"slug":119},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]