[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118890-en":3,"doc-seo-118890-105":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},118890,16904993612988,"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 - Supplemental Materials","Supplemental materials present an evidence-focused approach to forecasting domestic homicide using police data and super learning. The text explains London’s limitations in publicly reporting domestic homicide cases and derives estimated domestic homicide counts from aggregate homicide statistics. It reviews existing domestic homicide forecasting tools, emphasizing that screening questionnaires often predict non-lethal repeat victimization rather than lethal outcomes due to distinct phenomenology. The materials then describe two near-fatal forecasting instruments—Danger Assessment and Lethality Assessment Programme—highlighting gender calibration, performance metrics, and lack of replications, before moving to dataset and methodological details.","SUPPLEMENTAL MATERIALS  \nUsing 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)  \n2 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)  \n3 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).  \nSupplemental Introductory Materials  \nEstimating Domestic Homicides in London  \nThe London Metropolitan Policing Services (“MPS”) does not report cases of domestic homicides via its publicly available datasets.1 However, MPS did report that they experienced an average of 132.5 homicides per year during the four-year period between 2018 and 2022. Domestic homicides encompass 19.03% of all homicide cases across the United Kingdom.2–5 When applying these macro-level statistics to the MPS annual homicide cases, we estimates that 25 of these 132.5 homicides are domestic.  \nExisting Domestic Homicide Forecasting Tools  \nDomestic homicide forecasts are often conducted via screening tools.6. These screening tools do not use machine learning; they are typically questionnaires administered to a victim of domestic abuse, and they assign the victim a risk category (e.g., high, medium, or low) . In a state-of-the-art literature review, Graham and colleagues identified 18 different screening tools that were administered in eight countries applied by various professional groups (law enforcement, social workers, academics, researchers, etc.) .7 Most screening tools did not forecast domestic homicide; they predicted whether an individual would suffer from a future, non-lethal domestic abuse incident.8 However, these tools cannot be used in this study because factors that predict domestic abuse may differ from those that predict domestic homicide.9 All abuse is damaging, but there are variations between different types of assaults, threats, and violence that perpetrators inflict on their victims. Severity scores can be used as indexes that enable a more nuanced classification of offenders. This can then be used to create typologies of domestic abuse pathologies, such as coercion, pathological behavior, sadism, or  \nhomicidal behavior. 10,11 Critically, research shows that there are phenomenological differences  \nbetween domestic homicide and non-lethal domestic abuse in terms of the \"emotions that trigger it, the circumstances that led up to it, and the state of mind that characterizes it.\" 12 Therefore, predicting non-lethal repeat victimization is not necessarily similar to predicting lethal domestic abuse.  \nStill, we identified two instruments that attempted to forecast near-fatal domestic abuse, or domestic abuse incidents in which the victim was nearly killed—the Danger Assessment and Lethality Assessment Programme—which are described below.  \nThe Danger Assessment. The first tool that forecasts near-fatal domestic abuse is the Danger Assessment. Developed by Campbell, 13 this questionnaire was published in Advances in Nursing Science and is intended to be administered in a medical setting. It consists of 20 weighted ques","cbCaitWDMF6UWzEL","https://ap.wps.com/l/cbCaitWDMF6UWzEL","pdf",341492,1,23,"English","en",105,"# Supplemental Introductory Materials\n## Estimating Domestic Homicides in London\n## Existing Domestic Homicide Forecasting Tools\n## The Danger Assessment\n## Lethality Assessment Programme\n# Supplemental Methods and Results\n## Dataset Description","[{\"question\":\"Why can’t London’s Metropolitan Police datasets directly report domestic homicide cases?\",\"answer\":\"The materials state that the London Metropolitan Policing Services do not report domestic homicide cases through publicly available datasets, requiring estimation from broader homicide statistics.\"},{\"question\":\"What is the key limitation of many existing domestic homicide forecasting tools?\",\"answer\":\"Most tools are screening questionnaires that do not use machine learning and often predict future non-lethal abuse incidents, not lethal domestic homicide, because predictors and underlying phenomenology can differ.\"},{\"question\":\"How do the Danger Assessment and Lethality Assessment Programme differ in design and intended use?\",\"answer\":\"The Danger Assessment is a 20-question, weighted medical-setting questionnaire calibrated for female victims, while the Lethality Assessment Programme modifies it into 11 desensitized questions for law enforcement use; both are described as screening female rather than male victims.\"}]","Using Machine Learning to Forecast Domestic Homicide via Police Data and Super Learning - Supplemental Materials | PDF",1785720798,58,{"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-supplemental-materials","",{"@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-supplemental-materials/118890/",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},"Why can’t London’s Metropolitan Police datasets directly report domestic homicide cases?","Question",{"text":75,"@type":76},"The materials state that the London Metropolitan Policing Services do not report domestic homicide cases through publicly available datasets, requiring estimation from broader homicide statistics.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the key limitation of many existing domestic homicide forecasting tools?",{"text":80,"@type":76},"Most tools are screening questionnaires that do not use machine learning and often predict future non-lethal abuse incidents, not lethal domestic homicide, because predictors and underlying phenomenology can differ.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the Danger Assessment and Lethality Assessment Programme differ in design and intended use?",{"text":84,"@type":76},"The Danger Assessment is a 20-question, weighted medical-setting questionnaire calibrated for female victims, while the Lethality Assessment Programme modifies it into 11 desensitized questions for law enforcement use; both are described as screening female rather than male victims.","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"]