Prediction of indicators through machine learning and anomaly detection : a case study in the supplementary health system in Brazil
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/235243 |
Resumo: | The research aimed to investigate the stages of a MachineLearning model process creation inordertopredict the indicator over the number of medical appointments per day done in the areaof supplementary health inthe region ofPorto Alegre /RS - Brazil and to propose a metric for anomalies detection. Literature reviewand applied case study wasusedas a methodology inthis paper,besides wasused the statistical software calledR, in order toprepare the data and create the model. Thestages ofthecase study was: database extraction, division of the base in training andtesting, creation of functions and feature engineering,variables selection and correlationanalysis, choiceof the algorithms with cross-validationand tuning, training of models, application of the models in the test data, selection of the best model and proposal of the metric for anomalies detection. At the end of these stages, it was possible to select the best modelin terms ofMAE (MeanAbsolute Error), the Random Forest, which was the algorithm withbetter performance when compared to Linear Regression and Neural Network. It also makes possible to identified nine anomaly points and thirty-eight warning points using the standard deviation metric. It was concluded, through the proposed methodology and the results obtained, that the steps of feature engineering and variables selection were essential for the creation and selection of the model, in addition, the proposed metric achieved the objective of generates alerts in the indicator, showing cases with possible problems or opportunities. |
id |
UFRGS-2_260b250768de4fd801149faf668d3dbc |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/235243 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Borges, Mirele MarquesMuller, Claudio Jose2022-02-16T04:31:29Z20212236-269Xhttp://hdl.handle.net/10183/235243001134950The research aimed to investigate the stages of a MachineLearning model process creation inordertopredict the indicator over the number of medical appointments per day done in the areaof supplementary health inthe region ofPorto Alegre /RS - Brazil and to propose a metric for anomalies detection. Literature reviewand applied case study wasusedas a methodology inthis paper,besides wasused the statistical software calledR, in order toprepare the data and create the model. Thestages ofthecase study was: database extraction, division of the base in training andtesting, creation of functions and feature engineering,variables selection and correlationanalysis, choiceof the algorithms with cross-validationand tuning, training of models, application of the models in the test data, selection of the best model and proposal of the metric for anomalies detection. At the end of these stages, it was possible to select the best modelin terms ofMAE (MeanAbsolute Error), the Random Forest, which was the algorithm withbetter performance when compared to Linear Regression and Neural Network. It also makes possible to identified nine anomaly points and thirty-eight warning points using the standard deviation metric. It was concluded, through the proposed methodology and the results obtained, that the steps of feature engineering and variables selection were essential for the creation and selection of the model, in addition, the proposed metric achieved the objective of generates alerts in the indicator, showing cases with possible problems or opportunities.application/pdfengIndependent journal of management & production [recurso eletrônico]. [Avaré]. Vol. 12, no. 8 (Nov./Dec. 2021), p. 2480-2497Aprendizado de máquinaGestão em saúdeIndicadoresMachine learningIndicatorsAnomaly detectionFeature engineeringSupplementary health systemPrediction of indicators through machine learning and anomaly detection : a case study in the supplementary health system in Brazilinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/otherinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT001134950.pdf.txt001134950.pdf.txtExtracted Texttext/plain42917http://www.lume.ufrgs.br/bitstream/10183/235243/2/001134950.pdf.txtf2f4254dc387b5575e8ab9992f04914dMD52ORIGINAL001134950.pdfTexto completoapplication/pdf362357http://www.lume.ufrgs.br/bitstream/10183/235243/1/001134950.pdfe48b709e3fca48e42fdd2530783e431dMD5110183/2352432022-02-22 05:15:29.342164oai:www.lume.ufrgs.br:10183/235243Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2022-02-22T08:15:29Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Prediction of indicators through machine learning and anomaly detection : a case study in the supplementary health system in Brazil |
title |
Prediction of indicators through machine learning and anomaly detection : a case study in the supplementary health system in Brazil |
spellingShingle |
Prediction of indicators through machine learning and anomaly detection : a case study in the supplementary health system in Brazil Borges, Mirele Marques Aprendizado de máquina Gestão em saúde Indicadores Machine learning Indicators Anomaly detection Feature engineering Supplementary health system |
title_short |
Prediction of indicators through machine learning and anomaly detection : a case study in the supplementary health system in Brazil |
title_full |
Prediction of indicators through machine learning and anomaly detection : a case study in the supplementary health system in Brazil |
title_fullStr |
Prediction of indicators through machine learning and anomaly detection : a case study in the supplementary health system in Brazil |
title_full_unstemmed |
Prediction of indicators through machine learning and anomaly detection : a case study in the supplementary health system in Brazil |
title_sort |
Prediction of indicators through machine learning and anomaly detection : a case study in the supplementary health system in Brazil |
author |
Borges, Mirele Marques |
author_facet |
Borges, Mirele Marques Muller, Claudio Jose |
author_role |
author |
author2 |
Muller, Claudio Jose |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Borges, Mirele Marques Muller, Claudio Jose |
dc.subject.por.fl_str_mv |
Aprendizado de máquina Gestão em saúde Indicadores |
topic |
Aprendizado de máquina Gestão em saúde Indicadores Machine learning Indicators Anomaly detection Feature engineering Supplementary health system |
dc.subject.eng.fl_str_mv |
Machine learning Indicators Anomaly detection Feature engineering Supplementary health system |
description |
The research aimed to investigate the stages of a MachineLearning model process creation inordertopredict the indicator over the number of medical appointments per day done in the areaof supplementary health inthe region ofPorto Alegre /RS - Brazil and to propose a metric for anomalies detection. Literature reviewand applied case study wasusedas a methodology inthis paper,besides wasused the statistical software calledR, in order toprepare the data and create the model. Thestages ofthecase study was: database extraction, division of the base in training andtesting, creation of functions and feature engineering,variables selection and correlationanalysis, choiceof the algorithms with cross-validationand tuning, training of models, application of the models in the test data, selection of the best model and proposal of the metric for anomalies detection. At the end of these stages, it was possible to select the best modelin terms ofMAE (MeanAbsolute Error), the Random Forest, which was the algorithm withbetter performance when compared to Linear Regression and Neural Network. It also makes possible to identified nine anomaly points and thirty-eight warning points using the standard deviation metric. It was concluded, through the proposed methodology and the results obtained, that the steps of feature engineering and variables selection were essential for the creation and selection of the model, in addition, the proposed metric achieved the objective of generates alerts in the indicator, showing cases with possible problems or opportunities. |
publishDate |
2021 |
dc.date.issued.fl_str_mv |
2021 |
dc.date.accessioned.fl_str_mv |
2022-02-16T04:31:29Z |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/other |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/235243 |
dc.identifier.issn.pt_BR.fl_str_mv |
2236-269X |
dc.identifier.nrb.pt_BR.fl_str_mv |
001134950 |
identifier_str_mv |
2236-269X 001134950 |
url |
http://hdl.handle.net/10183/235243 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Independent journal of management & production [recurso eletrônico]. [Avaré]. Vol. 12, no. 8 (Nov./Dec. 2021), p. 2480-2497 |
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 Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/235243/2/001134950.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/235243/1/001134950.pdf |
bitstream.checksum.fl_str_mv |
f2f4254dc387b5575e8ab9992f04914d e48b709e3fca48e42fdd2530783e431d |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801225050763821056 |