[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118886-en":3,"doc-seo-118886-105":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},118886,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Using Machine Learning to Forecast Domestic Homicide via Police Data and Super Learning","The work examines whether machine learning applied to police records can forecast domestic homicides with higher effectiveness than existing approaches. Prior instruments often target nonfatal re-victimization and/or show limited predictive validity. A super learner ensemble—built from roughly a dozen machine learning models—is used to increase recall and AUC while relying solely on police data to reflect confidentiality constraints. Using London Metropolitan Police Service data, the model achieves strong performance, including 77.64% homicide detection and an AUC of 71.04%.","Using Machine Learning to Forecast Domestic Homicide via Police Data and Super Learning  \nJacob Verrey 1*, Barak Ariel2, Vincent Harinam3, Luke Dillon4  \n1 Cantab. Institute of Criminology, University of Cambridge, Sidgwick Ave, Cambridge CB3 9DA, +44 1223 335360; [jjv31@cam.ac.uk](jjv31@cam.ac.uk)  \n3 Professor of Experimental Criminology, Institute of Criminology, University of Cambridge, Sidgwick Ave, Cambridge CB3 9DA, +44 1223 335360, [ba285@cam.ac.uk](ba285@cam.ac.uk) ; and Associate Professor of Criminology, Institute of Criminology, The Hebrew University of Jerusalem Mt. Scopus, Jerusalem, Israel, 9190501, [barak.ariel@mail.huji.ac.il](barak.ariel@mail.huji.ac.il)  \n2 PhD, Institute of Criminology, University of Cambridge, Sidgwick Ave, Cambridge CB3 9DA,+44 1223 335360, [vh315@cam.ac.uk](vh315@cam.ac.uk)  \n4 Cantab. Institute of Criminology, University of Cambridge, Sidgwick Ave, Cambridge CB3 9DA, +44 1223 335360; Metropolitan Police Service, [ltod2@cam.ac.uk](ltod2@cam.ac.uk)  \n___  \n* [Corresponding author.](Corresponding author. Email: jjv31@cam.ac.uk)[ Email:](Corresponding author. Email: jjv31@cam.ac.uk)[ jjv31@cam.ac.uk](Corresponding author. Email: jjv31@cam.ac.uk) (J. Verrey).  \nUsing Machine Learning to Forecast Domestic Homicide via Police Data and Super Learning  \nNotice  \nThis version of the article has been accepted for publication after peer-review, but it is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at [https://doi.org/10.1038/s41598-023-50274-2](https://doi.org/10.1038/s41598-023-50274-2)”.  \nAbstract  \nWe explore the feasibility of using machine learning on a police dataset to forecast domestic homicides. Existing forecasting instruments based on ordinary statistical instruments focus on nonfatal revictimization, produce outputs with limited predictive validity, or both. We implement a\"super learner,\" a machine learning paradigm that incorporates roughly a dozen machine learning models to increase the recall and AUC of forecasting using any one model. We purposely incorporate police records only, rather than multiple data sources, to illustrate the practice utility of the super learner, as additional datasets are often unavailable due to confidentiality considerations. Using London Metropolitan Police Service data, our model outperforms all extant domestic homicide forecasting tools: the super learner detects 77.64% of homicides, with a precision score of 18.61% and a 71.04% Area Under the Curve (AUC), which, collectively and severely, are assessed as “excellent.” Implications for theory, research, and practice are discussed.  \nIntroduction  \nDomestic abuse is a substantial problem in the United Kingdom and across the globe. In the UK alone, it affected 2.4 million adults for the year ending in March 2022,1 cost the British government £68 billion annually,2 and inflicted psychological damage on children, families, and communities that is difficult to quantify.3–5 Perhaps the most insidious form of domestic abuse is domestic homicide, or a form of domestic abuse that results in death. Indeed, a Home Office report estimates that a single case of domestic homicide costs the UK £2.2 million on average,2 with domestic homicides accounting for nearly a fifth of all police-reported homicides. 1,6–8  \nIt is no surprise that police in the United Kingdom consider the prevention of domestic homicide atop priority. The London Metropolitan Police Service (MPS) is the UK’s largest police force that is estimated to respond to 25 cases of domestic homicide per year (see supplemental materials for estimate computation) .9,10 With each case costing £2.2 million,2 these domestic homicide cases translate to an annual loss of £55 million, and they also inflict profound psychological damage on those affected by the homicide.3–5  \nUnsurprisingly, the MPS has a demonstrated interest in preventing domestic homicide, and they have","cbCaieQRpaKu4Ezx","https://ap.wps.com/l/cbCaieQRpaKu4Ezx","pdf",381251,1,23,"English","en",105,"# Abstract\n# Introduction\n## Domestic abuse and the need for prevention\n## Forecasting in UK policing\n## Machine learning approach and research question\n## Study aims and comparison of tools","[{\"question\":\"What problem does the paper address?\",\"answer\":\"The paper addresses forecasting domestic homicides as part of domestic abuse prevention, noting that police currently use a procedure considered weak.\"},{\"question\":\"What machine learning method is implemented?\",\"answer\":\"It implements a “super learner,” an ensemble approach combining roughly a dozen machine learning models to improve forecasting recall and AUC.\"},{\"question\":\"How does the proposed model perform compared with existing tools?\",\"answer\":\"Using London Metropolitan Police Service data, the super learner outperforms extant domestic homicide forecasting tools, achieving 77.64% detection, 18.61% precision, and 71.04% AUC, rated as “excellent.”\"}]","Using Machine Learning to Forecast Domestic Homicide via Police Data and Super Learning | PDF",1785720789,58,{"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},"using-machine-learning-to-forecast-domestic-homicide-via-police-data-and-super-learning","",{"@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/using-machine-learning-to-forecast-domestic-homicide-via-police-data-and-super-learning/118886/",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},"What problem does the paper address?","Question",{"text":75,"@type":76},"The paper addresses forecasting domestic homicides as part of domestic abuse prevention, noting that police currently use a procedure considered weak.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What machine learning method is implemented?",{"text":80,"@type":76},"It implements a “super learner,” an ensemble approach combining roughly a dozen machine learning models to improve forecasting recall and AUC.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed model perform compared with existing tools?",{"text":84,"@type":76},"Using London Metropolitan Police Service data, the super learner outperforms extant domestic homicide forecasting tools, achieving 77.64% detection, 18.61% precision, and 71.04% AUC, rated as “excellent.”","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"]