[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125987-en":3,"doc-seo-125987-105":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},125987,687207024478,"Liam","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Boosted Generalized Normal Distributions - Integrating Machine Learning with Operations Knowledge","Applications of machine learning in operations face two core gaps: many methods output only point predictions while operational decisions often require full distributional information, and typical distribution-agnostic models ignore domain-specific insights from operations literature. This work proposes a novel Boosted Generalized Normal Distribution (bGND) that uses gradient boosting with tree learners to estimate generalized normal distribution parameters as functions of covariates. Statistical consistency is proved. Using U.S. emergency-department data, bGND improves distributional forecasts for wait and service times and links gains to higher patient satisfaction and lower mortality.","arXiv :2407 . 19092v2 [ cs .LG] 1 Aug 2024  \nBoosted Generalized Normal Distributions: Integrating Machine Learning with Operations Knowledge  \nRagıp G¨urlek  \nGoizueta Business School, Emory University  \nFrancis de Vricourt  \nEuropean School of Management and Technology Berlin  \nDonald K.K. Lee*  \nGoizueta Business School and Department of Biostatistics & Bioinformatics, Emory University  \nApplications of machine learning (ML) techniques to operational settings often face two challenges: i) ML methods mostly provide point predictions whereas many operational problems require distributional information; and ii) They typically do not incorporate the extensive body of knowledge in the operations literature, particularly the theoretical and empirical findings that characterize specific distributions. We introduce a novel and rigorous methodology, the Boosted Generalized Normal Distribution (bGND), to address these challenges. The Generalized Normal Distribution (GND) encompasses a wide range of parametric distributions commonly encountered in operations, and bGND leverages gradient boosting with tree learners to flexibly estimate the parameters of the GND as functions of covariates. We establish bGND’s statistical consistency, thereby extending this key property to special cases studied in the ML literature that lacked such guarantees. Using data from a large academic emergency department in the United States, we show that the distributional forecasting of patient wait and service times can be meaningfully improved by leveraging findings from the healthcare operations literature. Specifically, bGND performs 6% and 9% better than the distribution-agnostic ML benchmark used to forecast wait and service times respectively. Further analysis suggests that these improvements translate into a 9% increase in patient satisfaction and a 4% reduction in mortality for myocardial infarction patients. Our work underscores the importance of integrating ML with operations knowledge to enhance distributional forecasts.  \nKey words: Distributional Machine Learning, Gradient Boosting, Wait Times, Service Times, Emergency Departments,  \nHealthcare Operations History: 1 August 2024  \n1. Introduction  \nMachine learning (ML) is increasingly being implemented across various areas of operations, including forecasting patient wait times in emergency departments (Arora et al. 2023), developing chemotherapy treatments (Bertsimas et al. 2016), manufacturing process improvements (Senoner et al. 2022), to optimizing last-mile delivery assignments (Liu et al. 2021) . The growing application of these methodologies can be attributed to their ability to learn complex relationships, their remarkable versatility, and the increased availability of operations-related data.  \n* Corresponding author. Supported by National Institutes of Health grant R01-HL164405 .  \nHowever, there are two challenges to applying ML techniques to operational settings. First, the majority of ML methods provide point predictions rather than distributional forecasts. Yet, many fundamental operations problems are framed around probability distributions: The analysis of service systems, for instance, focus on the distributions of wait and service times, while the newsvendor problem requires a specific quantile of the demand distribution. Consider also staffing (He et al. 2012, Ban and Rudin 2019) and elective surgery scheduling (Rath et al. 2017), which rely on distributional estimates of hospital workload and surgery duration.  \nSecond, the distributional ML algorithms do not account for the extensive body of knowledge in operations (Arora et al. 2023, Bertsimas et al. 2022) . This is because nonparametric ML algorithms are distribution-agnostic by design, precluding them from taking advantage of the specific distributional knowledge identified in the theoretical and empirical operations literature. For instance, Kingman (1962) demonstrated that wait times in queuing systems under heavy traffi","cbCaicnNfkeXiEf5","https://ap.wps.com/l/cbCaicnNfkeXiEf5","pdf",548952,1,28,"English","en",105,"# Introduction\n## Challenges in Applying ML to Operational Settings\n## Proposed bGND Methodology\n## Motivating Healthcare Operations Application","[{\"question\":\"What problem does bGND address in operational machine learning?\",\"answer\":\"It addresses two issues: operational tasks often need distributional forecasts rather than point predictions, and standard distribution-agnostic ML methods fail to incorporate operations literature knowledge about specific distributions.\"},{\"question\":\"How does bGND estimate the generalized normal distribution in practice?\",\"answer\":\"bGND uses gradient boosting with tree learners to model the location and scale parameters of the generalized normal distribution as flexible functions of covariates.\"},{\"question\":\"What is the impact shown in the emergency-department application?\",\"answer\":\"On U.S. emergency-department data, bGND improves distributional forecasting of patient wait times and service times, and the analysis suggests improved patient satisfaction and reduced mortality for myocardial infarction patients.\"}]","Boosted Generalized Normal Distributions - Integrating Machine Learning with Operations Knowledge | PDF",1785902401,71,{"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},"boosted-generalized-normal-distributions-integrating-machine-learning-with-operations-knowledge","",{"@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/boosted-generalized-normal-distributions-integrating-machine-learning-with-operations-knowledge/125987/",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","2026-08-18","2026-08-05",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 problem does bGND address in operational machine learning?","Question",{"text":76,"@type":77},"It addresses two issues: operational tasks often need distributional forecasts rather than point predictions, and standard distribution-agnostic ML methods fail to incorporate operations literature knowledge about specific distributions.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does bGND estimate the generalized normal distribution in practice?",{"text":81,"@type":77},"bGND uses gradient boosting with tree learners to model the location and scale parameters of the generalized normal distribution as flexible functions of covariates.",{"name":83,"@type":74,"acceptedAnswer":84},"What is the impact shown in the emergency-department application?",{"text":85,"@type":77},"On U.S. emergency-department data, bGND improves distributional forecasting of patient wait times and service times, and the analysis suggests improved patient satisfaction and reduced mortality for myocardial infarction patients.","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"]