[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119725-en":3,"doc-seo-119725-105":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},119725,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Machine Learning in the Prediction of Human Wellbeing - Working Paper Series","Subjective wellbeing survey data increasingly inform social-science research and policy, yet modeling capability remains limited. This working paper applies tree-based machine learning to more than one million respondents from Germany, the UK, and the United States using data from 2010–2018. Machine learning delivers higher predictive accuracy than ordinary least squares, and expanding explanatory variables substantially increases out-of-sample performance. Key predictors include material conditions, health, personality traits, and meaningful social relations, aligning with established literature.","Working Paper Series  \nMachine Learning in the Prediction of Human Wellbeing  \nEkaterina Oparina∗ Alexandre Tkatchenko  \n○r  \nCaspar Kaiser∗  \nAndrew E. Clark Conchita D’Ambrosio  \n○r Niccol`o Gentile∗ Jan-Emmanuel De Neve  \nApril 6, 2023  \nAbstract  \nSubjective wellbeing data are increasingly used across the social sciences. Yet, our ability to model wellbeing is severely limited. In response, we here use tree-based Machine Learning (ML) algorithms to provide a better understanding of respondents’ self-reported wellbeing. We analyse representative samples of more than one million respondents from Germany, the UK, and the United States, using the data between 2010 and 2018 . In terms of predictive power, our ML approaches perform better than traditional ordinary least squares (OLS) regressions. We moreover find that drastically expanding the set of explanatory variables doubles the predictive power of both OLS and the ML approaches on unseen data. The variables identified as important by our ML algorithms – i. e. material conditions, health, personality traits, and meaningful social relations – are similar to those that have already been identified in the literature. In that sense, our data-driven ML results validate the findings from conventional approaches.  \nKeywords: Subjective wellbeing, prediction methods, machine learning.  \n∗ These authors are joint first authors. The displayed order of these authors is random and determined by  \nthe AEA tool, [confirmation code](confirmation code oJsh ZMZJwhH. Correspondence to casparkaiser@gmail.com. Author affilia)[ oJsh](confirmation code oJsh ZMZJwhH. Correspondence to casparkaiser@gmail.com. Author affilia)[ ](confirmation code oJsh ZMZJwhH. Correspondence to casparkaiser@gmail.com. Author affilia)[ZMZJwhH](confirmation code oJsh ZMZJwhH. Correspondence to casparkaiser@gmail.com. Author affilia)[. Correspondence to casparkaiser@gmail.com. Author affilia](confirmation code oJsh ZMZJwhH. Correspondence to casparkaiser@gmail.com. Author affilia)  \ntions: Ekaterina Oparina: LSE; Niccol`o Gentile, Conchita D’Ambrosio and Alexandre Tkatchenko: University of Luxembourg; Caspar Kaiser and Jan-Emmanuel De Neve: University of Oxford; Andrew E. Clark: PSE-CNRS. We thank Filippo Volpin for excellent research assistance and Sid Bhushan for early discussions on the topic. We are grateful to Martin Huber, Daniel Kahneman, Christian Krekel, Andrew Oswald, Nattavudh Powdthavee, Sorawoot Srisuma and seminar participants at the LSE Wellbeing Seminar and Loughborough University, as well as the STATEC Wellbeing 2022 Conference, the 2022 IAAEU Workshop on Health and the Labour Market, and the Oxford Wellbeing & Policy Conference for comments and suggestions. This work was supported by the ERC [grant agreement n. 856455], the ESRC [grant number ES/T014431/1]; and the Institute for Advanced Studies, University of Luxembourg [grant DSEWELL] . We thank The Gallup Organization for providing access to their data for this research project.  \n1  \nStatement of Relevance  \nThere is a vast literature on the determinants of subjective wellbeing. International organisationsand statistical offices are now collecting such survey data at scale. However, standard regression models explain surprisingly little of the variation in respondents’wellbeing, limiting our ability to predict it. We utilise tree-based Machine Learning (ML) algorithms to improve predictions. First, we find that these ML algorithms indeed yield better predictive performance than standard methods, and establish an upper bound on the predictability of evaluative wellbeing with survey data. Second, we use ML to identify the key drivers of evaluative wellbeing. We show that the variables emphasised in the earlier intuition- and theory-based literature also appear in ML analyses. Third, we illustrate how ML can be an impartial arbiter in questions about functional forms, including the existence of satiation points in the effects of income and the U-sha","cbCaivmVT7hA9aVs","https://ap.wps.com/l/cbCaivmVT7hA9aVs","pdf",4729291,1,38,"English","en",105,"# Abstract\n# Statement of Relevance\n# Introduction","[{\"question\":\"How does the paper model subjective wellbeing?\",\"answer\":\"It uses tree-based machine learning algorithms to model respondents’ self-reported subjective wellbeing based on survey data.\"},{\"question\":\"Which approaches perform better according to the paper?\",\"answer\":\"The paper finds that machine learning approaches outperform traditional ordinary least squares (OLS) regressions in predictive power.\"},{\"question\":\"What drives evaluative wellbeing in the paper’s findings?\",\"answer\":\"The variables identified as important include material conditions, health, personality traits, and meaningful social relations.\"}]","Machine Learning in the Prediction of Human Wellbeing - Working Paper Series | PDF",1785725973,96,{"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-in-the-prediction-of-human-wellbeing-working-paper-series","",{"@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-in-the-prediction-of-human-wellbeing-working-paper-series/119725/",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","2026-08-03",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},"How does the paper model subjective wellbeing?","Question",{"text":75,"@type":76},"It uses tree-based machine learning algorithms to model respondents’ self-reported subjective wellbeing based on survey data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which approaches perform better according to the paper?",{"text":80,"@type":76},"The paper finds that machine learning approaches outperform traditional ordinary least squares (OLS) regressions in predictive power.",{"name":82,"@type":73,"acceptedAnswer":83},"What drives evaluative wellbeing in the paper’s findings?",{"text":84,"@type":76},"The variables identified as important include material conditions, health, personality traits, and meaningful social relations.","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"]