[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121618-en":3,"doc-seo-121618-105":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},121618,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Unsupervised Machine Learning for Explainable Medicare Fraud Detection - paper","Unsupervised machine learning is used to identify providers who overbill Medicare and potentially commit fraud within inpatient hospitalization claims. The approach is fully unsupervised, requiring no labeled training data, and outputs explainable, user-facing reasoning about why providers are flagged. Large-scale Medicare claims patterns are validated using Department of Justice anti-fraud lawsuit information and case studies, supporting both quantitative and qualitative findings for suspicious billing behavior.","arXiv :2211 .02927v2 [ cs .CY] 9 Nov 2022  \nUnsupervised Machine Learning for Explainable Medicare Fraud Detection*  \nClick here for the latest version of the paper  \nShubhranshu Shekhar  \nCarnegie Mellon University, [shubhras@andrew.cmu.edu](shubhras@andrew.cmu.edu)  \nJetson Leder-Luis  \nBoston University and NBER, [jetson@bu.edu](jetson@bu.edu)  \nLeman Akoglu  \nCarnegie Mellon University, [lakoglu@andrew.cmu.edu](lakoglu@andrew.cmu.edu)  \nThe US federal government spends more than a trillion dollars per year on health care, largely provided by private third parties and reimbursed by the government. A major concern in this system is overbilling, waste and fraud by providers, who face incentives to misreport on their claims in order to receive higher payments. In this paper, we develop novel machine learning tools to identify providers that overbill Medicare, the US federal health insurance program for elderly adults and the disabled. Using large-scale Medicare claims data, we identify patterns consistent with fraud or overbilling among inpatient hospitalizations. Our proposed approach for Medicare fraud detection is fully unsupervised, not relying on any labeled training data, and is explainable to end users, providing reasoning and interpretable insights into the potentially suspicious behavior of the 􀀍agged providers. Data from the Department of Justice on providers facing anti-fraud lawsuitsand several case studies validate our approach and 􀀌ndings both quantitatively and qualitatively.  \nKey words : Medicare, fraud and abuse, machine learning, anomaly detection, explanation  \n1 . Introduction  \nFraud in health care is hard to detect. Insurers face information asymmetries, where physicians and patients both know more about the health care delivered than the insurer responsible for paying for that care. Providers face incentives to maximize their reimbursements from health insurance companies, and insurers must largely rely on documentation from providers themselves. This asymmetric information leads to circumstances where unscrupulous providers can choose to commit fraud.  \n* Research reported in this publication was supported by the National Institute on Aging of the National Institutes of Health under Award Number P30AG012810 . The content is solely the responsibility of the authors and does not necessarily represent the o􀀎cial views of the National Institutes of Health.  \nThese issues are compounded in the federal health care programs, where the government is the insurer. The US federal government spends Trillions of dollars 1 on health insurance, where fraud detection becomes challenging due to the sheer volume of claims being processed. Estimated US health care spending in 2019 is $3 .81 Trillion2 , almost as high as the world's 4th largest GDP of Germany. National health care spending in the US is expected to grow at an average annual rate of 5 .4%3 , from 2019 to 2028, outpacing GDP at 4 .3% .  \nThe largest of these programs is Medicare, the federal health insurance program for people of age 65 and older and the disabled. With more than $800 Billion being spent on Medicare in 2019, even small shares of waste and abuse lead to large losses. Federal Bureau of Investigations (FBI) estimates that fraud accounts for 3{10% of all billings ($24{80 billion), and the US Government Accountability O􀀎ce (GAO) estimates Medicare fraud in 2019 at $46 .2 Billion.4 This problem has gained the attention of Medicare administrators faced with the challenge of detecting and deterring waste and fraud to ensure the program stays 􀀌nancially solvent (U.S. Department of Health and Human Services 2022) .  \nThe nature of health care fraud provides insights into how it can be detected. Healthcare providers face incentives to manipulate billing to increase pro􀀌ts. Yet, in general, patients see multiple providers, and there are many providers in the system that do not commit fraud. Therefore, fraud detection does not rely on the veri􀀌cation of a","cbCaianZMF899AcM","https://ap.wps.com/l/cbCaianZMF899AcM","pdf",1010661,1,35,"English","en",105,"# Introduction\n## Problem of healthcare fraud detection\n## Medicare overbilling and scale of claims\n## Provider-level pattern detection\n# Proposed approach overview","[{\"question\":\"Why is Medicare fraud difficult to detect?\",\"answer\":\"Healthcare fraud is hard to detect due to information asymmetries: providers and patients know more about delivered care than the insurer processing claims, and the government must handle fraud detection at massive scale.\"},{\"question\":\"What makes the proposed Medicare fraud detection approach unsupervised?\",\"answer\":\"The method discovers suspicious provider patterns without relying on any labeled training data, using only the universe of Medicare claims to detect anomalies.\"},{\"question\":\"How does the approach provide explainability for flagged providers?\",\"answer\":\"The system includes explanations that translate flagged providers’ suspiciousness into interpretable insights, enabling end users such as auditors to guide further investigation.\"}]","Unsupervised Machine Learning for Explainable Medicare Fraud Detection - paper | PDF",1785805681,88,{"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},"unsupervised-machine-learning-for-explainable-medicare-fraud-detection-paper","",{"@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/unsupervised-machine-learning-for-explainable-medicare-fraud-detection-paper/121618/",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","2026-08-04",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 is Medicare fraud difficult to detect?","Question",{"text":75,"@type":76},"Healthcare fraud is hard to detect due to information asymmetries: providers and patients know more about delivered care than the insurer processing claims, and the government must handle fraud detection at massive scale.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What makes the proposed Medicare fraud detection approach unsupervised?",{"text":80,"@type":76},"The method discovers suspicious provider patterns without relying on any labeled training data, using only the universe of Medicare claims to detect anomalies.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the approach provide explainability for flagged providers?",{"text":84,"@type":76},"The system includes explanations that translate flagged providers’ suspiciousness into interpretable insights, enabling end users such as auditors to guide further investigation.","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"]