[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124320-en":3,"doc-seo-124320-105":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},124320,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine Learning Techniques to Forecast Fatal Accidents on Construction Sites in Brazil","Global estimates indicate the construction industry experiences some of the highest occupational accident rates. In response, the sector increasingly applies emerging technologies to improve safety conditions and decision-making, with machine learning (ML) used to analyze data and predict events. This paper develops an ML prediction model for fatal accidents using historical construction data from Brazil, covering 2,305 accidents (fatal and non-fatal) from 2018–2023 and evaluating seven classifiers. Gradient boosting achieved the best results with accuracy 0.885, precision 0.88, recall 0.833, and F1-score 0.881. The model supports safety management by highlighting influential attributes and enabling scenario-based prevention.","CIB Conferences  \nManuscript 1863  \nMachine Learning Techniques to Forecast Fatal Accidents on Construction Sites in Brazil  \nFilipe dos Santos Freitas Mirian Caroline Farias Santos Roseneia Rodrigues Santos Melo Paulo Henrique Ferreira Dayana Bastos Costa  \nFollow this and additional works at: [https://docs.lib.purdue.edu/cib-conferences](https://docs.lib.purdue.edu/cib-conferences)  \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 Techniques to Forecast Fatal Accidents on Construction Sites in Brazil  \nFilipe dos Santos Freitas, [filipedsfreitas@live.com](filipedsfreitas@live.com)[ ](filipedsfreitas@live.com)Federal University of Bahia, Brazil  \nMirian Caroline Farias Santos, [mirian.caroline@ufba.br](mirian.caroline@ufba.br)[ ](mirian.caroline@ufba.br)Federal University of Bahia, Brazil  \nRoseneia Rodrigues Santos de Melo, [roseneia.engcivil@gmail.com](roseneia.engcivil@gmail.com)[ ](roseneia.engcivil@gmail.com)Federal University of Bahia, Brazil  \nPaulo Henrique Ferreira, [paulohenri@ufba.br](paulohenri@ufba.br)[ ](paulohenri@ufba.br)Federal University of Bahia, Brazil  \nDayana Bastos Costa, [dayanabcosta@ufba.br](dayanabcosta@ufba.br)[ ](dayanabcosta@ufba.br)Federal University of Bahia, Brazil  \nAbstract  \nGlobal estimates indicate that the construction industry has one of the highest rates of occupational accidents. Given this scenario, the sector has adopted emergent technologies to improve safety conditions and decision-making. Thus, machine learning (ML) emerges as a promising tool to streamline data analysis besides being used to predict events based on datasets. In construction, the use of the ML model to predict site accidents remains emerging without studies using historical data from emerging South and Latin American countries. Therefore, this paper aims to develop a prediction model using machine learning for fatal accidents using historical data from construction. The dataset contains 2,305 accidents, including fatal and non-fatal, from 2018 to 2023, distributed in 17 binary and categorical variables. After the pre-processing, seven predictive models were generated with different classifiers to determine which models fit the dataset better. Among the classifiers, the gradientboosting model exhibited the best performance, achieving an accuracy of 0.885, 0.88 precision, 0.833 recall, and 0.881 F1-Score. As a contribution, this study brings insights regarding the use of predictive models in construction safety management, calling attention to the attributes that have the most influence on a fatal accident. In addition, the model can assist managers in identifying scenarios that are more prone to accidents and propose effective preventive measures.  \nKeywords  \nSafety management, Machine learning models, Prediction.  \n1 Introduction  \nConstruction is a sector with a high incidence of fatal accidents, especially in Brazil, where recent data has reported alarming rates (Smartlab 2024) . In this context, emerging technologies such as machine learning (ML) have been adopted to enhance analyses and predict accidents.  \nOccupational accidents result from a combination of factors rather than a single isolated cause, given the dynamic and non-linear nature of complex sociotechnical systems (Hollnagel 2014) . This indicates  \nthat such accidents often arise from a complex interaction between human, environmental, organizational, and technical elements (Yin et al. 2023) . In light of this, there is an urgent need to analyse these factors, using historical data, to propose proactive measures for improving safety on construction sites. The Brazilian government provides an official form that companies must use to report all work-related accidents. However, despite the collection of this data, the analyses conducted are typically at a strategic level, which d","cbCairjvo691kaza","https://ap.wps.com/l/cbCairjvo691kaza","pdf",1005466,1,11,"English","en",105,"# 1 Introduction\n# 2 Background","[{\"question\":\"What problem does the paper address in construction safety?\",\"answer\":\"The paper targets the high incidence of fatal occupational accidents in construction, noting that current analyses often remain at strategic levels and do not sufficiently support tactical and operational decision-making.\"},{\"question\":\"What dataset and timeframe are used for building the fatal-accident prediction model?\",\"answer\":\"The dataset contains 2,305 construction accidents, including fatal and non-fatal cases, recorded from 2018 to 2023 and described using 17 binary and categorical variables.\"},{\"question\":\"Which machine learning model performed best and what were its results?\",\"answer\":\"Among seven evaluated classifiers, the gradient boosting model delivered the strongest performance, reaching an accuracy of 0.885, precision of 0.88, recall of 0.833, and an F1-score of 0.881.\"}]","Machine Learning Techniques to Forecast Fatal Accidents on Construction Sites in Brazil | PDF",1785821596,28,{"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-techniques-to-forecast-fatal-accidents-on-construction-sites-in-brazil","",{"@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-techniques-to-forecast-fatal-accidents-on-construction-sites-in-brazil/124320/",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","2026-08-04",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 construction safety?","Question",{"text":75,"@type":76},"The paper targets the high incidence of fatal occupational accidents in construction, noting that current analyses often remain at strategic levels and do not sufficiently support tactical and operational decision-making.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What dataset and timeframe are used for building the fatal-accident prediction model?",{"text":80,"@type":76},"The dataset contains 2,305 construction accidents, including fatal and non-fatal cases, recorded from 2018 to 2023 and described using 17 binary and categorical variables.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning model performed best and what were its results?",{"text":84,"@type":76},"Among seven evaluated classifiers, the gradient boosting model delivered the strongest performance, reaching an accuracy of 0.885, precision of 0.88, recall of 0.833, and an F1-score of 0.881.","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"]