[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122939-en":3,"doc-seo-122939-105":30,"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":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},122939,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","Causal impact evaluation of occupational safety policies on firms’ default using machine learning uplift modelling - Research report","Occupational safety and health (OSH) policies are evaluated for their direct and indirect influence on corporate outcomes, focusing on whether public incentives reduce firms’ default risk. The study analyzes an Italy-based aid scheme for small and medium enterprises that invest in OSH, estimating individual treatment effects with thirteen competing models. LightGBM yields the best AUUC and Qini performance (0.064 and 0.407), and follow-up statistical analysis indicates stronger benefits for firms facing performance problems immediately prior to intervention, where increased liquidity may avert default.","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nCausal impact evaluation of occupational safety policies on firms’ default using machine learning uplift modelling  \nBerardino Barile1,2*, Marco Forti 3, Alessia Marrocco 3 & Angelo Castaldo3  \nIt is often undermined that occupational safety policies do not only displace a direct effect on work well-being, but also an indirect effect on firms’ economic performances. In such context, econometric models dominated the scenes of causality until recently while Machine Learning models were  \nseen with skepticism. With the rise of complex datasets, an ever-increasing need for automated algorithms capable to handle complex non-linear relationships between variables has brought to uncover the power of Machine Learning for causality. In this paper, we carry out an evaluation of a public aid-scheme implemented in Italy and oriented to support investment of small and medium enterprises (SMEs) in occupational safety and health (OSH) for assessing the impact on the survival of corporations. A comparison of thirteen models is performed and the Individual Treatment Effect (ITE) estimated and validated based on the AUUC and Qini score for which best values of 0.064 and 0.407, respectively, are obtained based on the Light Gradient Boosting Machine (LightGBM). An additional in-depth statistical analysis also revealed that the best beneficiaries of the policy intervention are those firms that experience performance issues in the period just before the interventions and for which the increased liquidity brought by the policy may have prevented default.  \nPublic policies on occupational safety and health (OSH) aim primarily at improving working conditions. Usually, this objective is set at constitutional level and through other regulatory sources, both at the European and national level. The European Agency for Safety and Health at Work underlines the need for a mixed approach in addressing the challenge of improving health and safety conditions in the workplace by relying on both legal regulation and its enforcement (sticks), as well as economic incentives (carrots) . Nevertheless, in Europe the use of carrots is much less widespread than sticks, and the former, even where implemented, is not provided asa structural policy tool.  \nIn Italy, since 2010, the Italian National Institute for Insurance against Accidents at Work (INAIL) has launched a State-aid scheme (ISI calls) to support firms’ (especially SMEs) investments to improve Occupational Safety and Health (OSH) performance. Under a theoretical perspective, OSH policies do not only displace a direct effect on work well-being, but also an indirect effect on firms’ economic performance1–6. Following Uegaki et al.7, we can identify four labels to denote four proxies of the measure of productivity that links health to firm performance and, hence, in our perspective, to survival: (1) sick leave; (2) compensated sick leave; (3) limited or modified operational activities; and (4) working-presenteeism. At the operational level, this means that when workplace accidents occur there is a decrease in production (imputable to days loss, and equipment damages) and/or a deterioration in product quality; moreover, in the case in which workers are still at work even though not fully healed, they could operate with a lower productivity. In both cases, the result is a loss of part of the profitsand productivity that would have been potentially obtained, considering the optimal scenario of production at full capacity and without defects6.  \nUnderstanding the economic perspective is particularly important in the context of OSH: on the policymakers side, unsafe or unhealthy working conditions lead to negative externalities with respect to the costs that workers and firms bear. Indeed, injuries and professional illness related to working population are accompanied by significant socio-economic burdens7, usually in the form of costs (mon","cbCaidWupknzwem1","https://ap.wps.com/l/cbCaidWupknzwem1","pdf",2204377,1,22,"English","en",105,"# Introduction\n## Policy rationale and indirect firm impacts\n# Data and evaluation setup\n## Italy OSH aid scheme and SMEs\n## Uplift modelling and causal ML approach\n# Results\n## Model comparison and best AUUC/Qini performance\n## Who benefits most from the intervention\n# Discussion\n## Economic perspective on OSH investments and survival","[{\"question\":\"What does the study evaluate regarding occupational safety policies?\",\"answer\":\"It evaluates how an OSH public aid scheme affects firms’ default by estimating individual treatment effects and examining the causal impact beyond direct work well-being.\"},{\"question\":\"Which modelling approach and model performed best in the comparison?\",\"answer\":\"The study uses uplift modelling within causal machine learning and compares thirteen models; LightGBM achieves the best AUUC and Qini values of 0.064 and 0.407.\"},{\"question\":\"Which firms are identified as the best beneficiaries of the policy?\",\"answer\":\"Beneficiaries are firms experiencing performance issues in the period just before the intervention, where the policy-driven increase in liquidity may have prevented default.\"}]","Causal impact evaluation of occupational safety policies on firms’ default using machine learning uplift modelling - Research report | PDF",1785813794,55,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"causal-impact-evaluation-of-occupational-safety-policies-on-firms-default-using-machine-learning-uplift-modelling-research-report","",{"@graph":36,"@context":86},[37,54,69],{"@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/causal-impact-evaluation-of-occupational-safety-policies-on-firms-default-using-machine-learning-uplift-modelling-research-report/122939/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",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 does the study evaluate regarding occupational safety policies?","Question",{"text":76,"@type":77},"It evaluates how an OSH public aid scheme affects firms’ default by estimating individual treatment effects and examining the causal impact beyond direct work well-being.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which modelling approach and model performed best in the comparison?",{"text":81,"@type":77},"The study uses uplift modelling within causal machine learning and compares thirteen models; LightGBM achieves the best AUUC and Qini values of 0.064 and 0.407.",{"name":83,"@type":74,"acceptedAnswer":84},"Which firms are identified as the best beneficiaries of the policy?",{"text":85,"@type":77},"Beneficiaries are firms experiencing performance issues in the period just before the intervention, where the policy-driven increase in liquidity may have prevented default.","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":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]