Fraud: and anomaly detection in healthcare: an unsupervised machine learning approach

Detalhes bibliográficos
Autor(a) principal: Dangers, Lennart
Data de Publicação: 2022
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/132860
Resumo: Internship Report presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics
id RCAP_d214b34351185c6304cd323d9adb632e
oai_identifier_str oai:run.unl.pt:10362/132860
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Fraud: and anomaly detection in healthcare: an unsupervised machine learning approachFraud detectionAnomaly detectionHealthcare dataUnsupervised learningClusteringMachine learningIsolation forestNetwork analysisCancellation PredictionInternship Report presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business AnalyticsFraud and abuse in healthcare are critical and cause significant damage. However, the auditing of healthcare encounters is cumbersome, and the detection of fraud and abuse is challenging and binds capacity. Data-driven fraud and anomaly detection models can help to overcome these issues. This work proposes several unsupervised learning methods to understand patterns and detect abnormal healthcare encounters which might be fraudulent or abusive. The ensemble of models is split into sub-processes and applied on a healthcare data set belonging to Future Healthcare group, a Portuguese group acting in health insurance. One major part of the ensemble is the implementation of the Isolation Forest algorithm, which achieves good results in precision and recall and detect new potential fraudulent abnormal behaviour. Due to unlabelled data and the application of unsupervised learning methods, the proposed model detects new fraudulent patterns instead of learning from existing patterns. Besides the model to predict whether new incoming medical encounters are fraudulent or abusive, this work illustrates a visual method to detect suspicious networks among medical providers. In addition, this work contains an approach to predict whether a customer will cancel the insurance based on anomalous behaviour. This internship report aims to contribute to science and be public, even though some parts could not be explained in detail due to confidentiality.António, Nuno Miguel da ConceiçãoRUNDangers, Lennart2022-02-14T17:15:19Z2022-01-192022-01-19T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/132860TID:202948196enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:11:32Zoai:run.unl.pt:10362/132860Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:47:37.230678Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Fraud: and anomaly detection in healthcare: an unsupervised machine learning approach
title Fraud: and anomaly detection in healthcare: an unsupervised machine learning approach
spellingShingle Fraud: and anomaly detection in healthcare: an unsupervised machine learning approach
Dangers, Lennart
Fraud detection
Anomaly detection
Healthcare data
Unsupervised learning
Clustering
Machine learning
Isolation forest
Network analysis
Cancellation Prediction
title_short Fraud: and anomaly detection in healthcare: an unsupervised machine learning approach
title_full Fraud: and anomaly detection in healthcare: an unsupervised machine learning approach
title_fullStr Fraud: and anomaly detection in healthcare: an unsupervised machine learning approach
title_full_unstemmed Fraud: and anomaly detection in healthcare: an unsupervised machine learning approach
title_sort Fraud: and anomaly detection in healthcare: an unsupervised machine learning approach
author Dangers, Lennart
author_facet Dangers, Lennart
author_role author
dc.contributor.none.fl_str_mv António, Nuno Miguel da Conceição
RUN
dc.contributor.author.fl_str_mv Dangers, Lennart
dc.subject.por.fl_str_mv Fraud detection
Anomaly detection
Healthcare data
Unsupervised learning
Clustering
Machine learning
Isolation forest
Network analysis
Cancellation Prediction
topic Fraud detection
Anomaly detection
Healthcare data
Unsupervised learning
Clustering
Machine learning
Isolation forest
Network analysis
Cancellation Prediction
description Internship Report presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics
publishDate 2022
dc.date.none.fl_str_mv 2022-02-14T17:15:19Z
2022-01-19
2022-01-19T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/132860
TID:202948196
url http://hdl.handle.net/10362/132860
identifier_str_mv TID:202948196
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138078782128128

Registros relacionados