[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122132-en":3,"doc-seo-122132-105":30,"detail-sidebar-cat-0-en-105":83},{"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},122132,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Combining System Dynamics and Machine Learning for Predicting Safety Performance in Construction Projects","This master’s thesis combines system dynamics and machine learning to enable early warning for construction projects with high accident risk. A system dynamics model was built to simulate construction projects and generate datasets, using two accident-rate scenarios for serious and fatal accidents. The planning phase portion of the model includes 53 interacting indicators and is validated with extreme condition and sensitivity tests. Machine learning then predicts safety performance from planning-only features across five models, addressing class balance and imbalance challenges.","Master’s thesis  \nNT NU  \nNorwegian University of Science and Technology Faculty of Engineering  \nDepartment of Mechan ica l and Industrial Engineering  \nIngrid Renolen Borkenhagen Jenni Sveen Olsen  \nCombining System Dynamics and Machine Learning for Predicting Safety Performance in Construction Projects  \nMaster’s thesis in Engineering and ICT Supervisor: Nils Olsson  \nCo-supervisor: Antoine Rauzy June 2023  \nIngrid Renolen Borkenhagen Jenni Sveen Olsen  \nCombining System Dynamics and Machine Learning for Predicting Safety Performance in Construction Projects  \nMaster’s thesis in Engineering and ICT Supervisor: Nils Olsson  \nCo-supervisor: Antoine Rauzy June 2023  \nNorwegian University of Science and Technology Faculty of Engineering  \nDepartment of Mechanical and Industrial Engineering  \nPreface  \nThis research is written as the master’s thesis of our Engineering and ICT degree at the Norwegian University of Science and Technology (NTNU) . The thesis is written in the spring of 2023 within the subject code TPK4920 Project and Quality Management, Master’s Thesis. Further it counts for 30 credits.  \nOver the last years, we have both taken a selection of project management and machine learning courses. They have provided interesting and valuable knowledge that we wanted to utilize for our master’s thesis. The project Artificial Intelligence in Projects was therefore a fitting choice as we could combine these two knowledge areas. Additionally, there is a rapid development within the machine learning field which we find very engaging as developers.  \nThe selection of the project resulted in being a part of the sustainable value creation by digital predictions of safety performance in the construction industry (DiSCo) research project. Previously we have had limited knowledge on safety management in construction projects. This research has equipped us with new insights within this field, which we see great importance in. We have also identified a great potential for utilization of new, and better technology to further enhance safety performance in the construction industry. We hope that this thesis contributes with new knowledge and inspiration for further investigation of this domain.  \nAcknowledgement  \nWe would like to thank all contributing parties to this thesis. Their invaluable support and guidance have been significant in our journey.  \nFirst and foremost, we would like to thank our supervisor Nils Olsson for great guidance during this semester. He has contributed with valuable insights and feedback, and we are truly greatful for his mentorship.  \nFurther, we would like to thank our co-supervisor Antoine Rauzy and collaborating student Josefine Stiff Aamlid. Antoine’s technical expertise and enthusiasm towards this research have greatly enriched our work. We would also like to thank Josefine for solid collaboration in the development of the system dynamics model.  \nAdditionally, we would like to thank the rest of the DiSCo team for new perspectives and valuable discussions through our regular meetings. Their expertise has broadened our understanding and enriched the quality of our research.  \nAt last, we would like to thank our friends, boyfriends and family for all the support. Our friends have contributed to some fantastic years in Trondheim, which also gives greater motivation for our studies. Thank you to our boyfriends and families for great support, encouragement and belief in our abilities.  \nIngrid Renolen Borkenhagen, June 2023  \nJenni Sveen Olsen, June 2023  \nAbstract  \nThis thesis aimed to combine system dynamics and machine learning to give an early warning of construction projects with a high accident risk. The construction industry is highly accident prone and there is ongoing research on it’s safety performance. Previous studies have focused on safety factors, system dynamics models as well as various machine learning predictions. For this thesis, a system dynamics model was developed in order to simulate c","cbCaid5yKX09b6sl","https://ap.wps.com/l/cbCaid5yKX09b6sl","pdf",10669896,1,122,"English","en",105,"# Preface\n# Acknowledgement\n# Abstract","[{\"question\":\"What were the main findings from the machine learning results?\",\"answer\":\"The thesis demonstrates combining system dynamics and machine learning when real project data is unavailable, and it suggests potential for separating projects with higher risk of serious accidents; models showed lower accuracy for serious accidents but higher recall, while identifying fatal accidents remained difficult due to imbalance.\"}]","Combining System Dynamics and Machine Learning for Predicting Safety Performance in Construction Projects | PDF",1785808969,307,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"combining-system-dynamics-and-machine-learning-for-predicting-safety-performance-in-construction-projects","",{"@graph":36,"@context":77},[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/combining-system-dynamics-and-machine-learning-for-predicting-safety-performance-in-construction-projects/122132/",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],{"name":72,"@type":73,"acceptedAnswer":74},"What were the main findings from the machine learning results?","Question",{"text":75,"@type":76},"The thesis demonstrates combining system dynamics and machine learning when real project data is unavailable, and it suggests potential for separating projects with higher risk of serious accidents; models showed lower accuracy for serious accidents but higher recall, while identifying fatal accidents remained difficult due to imbalance.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]