[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124985-en":3,"doc-seo-124985-105":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},124985,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Predicting Short Time-to-Crime Guns - a Machine Learning Analysis of California Transaction Records (2010-2021)","Gun-related crime remains an urgent public health and safety challenge across the United States. A central question is how firearms are diverted from legal retail into offenders’ hands. Using nearly 8 million California legal firearm transaction records (2010–2020) linked to over 380,000 recovered crime gun records (2010–2021), the study applies supervised machine learning to predict which guns are used in crimes soon after purchase. Models use random forest with stratified under-sampling and SHAP-based interpretation, achieving strong discrimination (test AUC 0.85).","UC Davis  \nUC Davis Previously Published Works  \nTitle  \nPredicting Short Time-to-Crime Guns: a Machine Learning Analysis of California Transaction Records (2010-2021) .  \nPermalink  \n[https://escholarship.org/uc/item/7dp1j2pb](https://escholarship.org/uc/item/7dp1j2pb)  \nJournal  \nJournal of Urban Health, 101(5)  \nAuthors  \nLaqueur, Hannah  \nSmirniotis, Colette McCort, Christopher  \nPublication Date  \n2024-10-01  \nDOI  \n10.1007/s11524-024-00909-0  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nJournal of Urban Health (2024) 101:955–967 [https://doi.org/10.1007/s11524-024-00909-0](https://doi.org/10.1007/s11524-024-00909-0)  \nORIGINAL ARTICLE  \nPredicting Short Time-to-Crime Guns: a Machine Learning Analysis of California Transaction Records (2010–2021)  \nHannah S. Laqueur  · Colette Smirniotis ·  \nChristopher McCort  \nAccepted: 20 June 2024 / Published online: 5 September 2024 © The Author(s) 2024  \nAbstract Gun-related crime continues to bean urgent public health and safety problem in cities across the US. A key question is: how are firearms diverted from the legal retail market into the hands of gun offenders? With close to 8 million legal firearm transaction records in California (2010–2020) linked to over 380,000 records of recovered crime guns (2010–2021), we employ supervised machine learning to predict which firearms are used in crimes shortly after purchase. Specifically, using random forest(RF)with stratified under-sampling, we predict any crime gun recovery within a year (0.2% of transactions) and violent crime gun recovery within a year (0.03% of transactions) . We also identify the purchaser, firearm, and dealer characteristics most predictive ofthis short timeto-crime gun recovery using SHapley Additive exPlanations and mean decrease in accuracy variable importance measures. Overall, our models show good discrimination, and we are able to identify firearms at extreme risk for diversion into criminal hands. The test set AUCis 0.85 for both models. For the model predict-  \nSupplementary Information The online version contains supplementary material available at [https://doi.org/10.1007/](https://doi.org/10.1007/)[ ](https://doi.org/10.1007/)[s11524-024-00909-0](s11524-024-00909-0.)[.](s11524-024-00909-0.)  \nH. S. Laqueur (B) · C. Smirniotis · C. McCort  \nViolence Prevention Research Program, Department of Emergency Medicine, University of California, Davis, USA [e-mail: hslaqueur@ucdavis.edu](e-mail: hslaqueur@ucdavis.edu)  \nH. S. Laqueur · C. Smirniotis · C. McCort  \nCalifornia Firearm Violence Research Center, Davis, USA  \ning any recovery, a default threshold of 0.50 results ina sensitivity of 0.63 and a specificity of 0.88 . Among transactions identified as extremely risky, e.g., transactions with a score of 0.98 and above, 74%(35/47 in the test data) are recovered within a year. The most important predictive features include purchaserage and caliber size. This study suggests the potential utility of transaction records combined with machine learning to identify firearms at the highest risk for diversion and criminal use soon after purchase.  \nKeywords Firearm transactions · Crime guns · Short time-to-crime · Random forest · Risk prediction · Variable importance  \nIntroduction  \nGun-related crime continues to be an urgent public health and safety problem in the United States. The firearm homicide rate increased by close to 35% in 2020 from the year prior [1] and rose another 8% in 2021, reaching a 29-year high [2] . In that year,firearms were used in 81% of the more than 20,000 homicides, the highest proportion reported in over 50 years [1]. This rise in homicides coincided with recordhigh firearm sales, which researchers have linked to increased gun violence [3, 4] . It also coincided with a significant increase in firearms recovered in crimes shortly after legal purchase [5] . The rapid diversion of a firearm from sale to criminal use, i.e., a shor","cbCaiahcEjQdrwHA","https://ap.wps.com/l/cbCaiahcEjQdrwHA","pdf",581904,1,14,"English","en",105,"# Abstract\n# Introduction\n## Research gap and data constraints\n## Previous findings on risk factors\n## Study approach and aims","[{\"question\":\"What problem does the study address?\",\"answer\":\"The study examines how firearms diverted from legal retail are used in crimes shortly after purchase, i.e., short time-to-crime.\"},{\"question\":\"What data are used to build the machine learning models?\",\"answer\":\"It links nearly 8 million legal firearm transaction records in California (2010–2020) with more than 380,000 records of recovered crime guns (2010–2021).\"},{\"question\":\"How well do the models perform and what key predictors emerge?\",\"answer\":\"The test set AUC is 0.85 for both models, and important predictive features include purchaser age and firearm caliber size. Extremely risky transactions have a high recovery rate within a year.\"}]","Predicting Short Time-to-Crime Guns - a Machine Learning Analysis of California Transaction Records (2010-2021) | PDF",1785895856,35,{"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},"predicting-short-time-to-crime-guns-a-machine-learning-analysis-of-california-transaction-records-2010-2021","",{"@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/predicting-short-time-to-crime-guns-a-machine-learning-analysis-of-california-transaction-records-2010-2021/124985/",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","2026-08-05",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 study address?","Question",{"text":75,"@type":76},"The study examines how firearms diverted from legal retail are used in crimes shortly after purchase, i.e., short time-to-crime.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data are used to build the machine learning models?",{"text":80,"@type":76},"It links nearly 8 million legal firearm transaction records in California (2010–2020) with more than 380,000 records of recovered crime guns (2010–2021).",{"name":82,"@type":73,"acceptedAnswer":83},"How well do the models perform and what key predictors emerge?",{"text":84,"@type":76},"The test set AUC is 0.85 for both models, and important predictive features include purchaser age and firearm caliber size. Extremely risky transactions have a high recovery rate within a year.","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"]