DISCONTINUANCE OF BRAZILIAN COMPANIES SECTOR CONSUMPTION CYCLIC: A METHODOLOGY FOR BALANCING OF DATABASE USING DATA MINING TECHNIQUES

Detalhes bibliográficos
Autor(a) principal: Horta, Rui Américo Mathiasi
Data de Publicação: 2014
Outros Autores: Borges, Carlos Cristiano Hasenclever, Jorge, Marcelino José
Tipo de documento: Artigo
Idioma: por
Título da fonte: Revista Ambiente Contábil
Texto Completo: https://periodicos.ufrn.br/ambiente/article/view/4124
Resumo: Discontinuity of companies is an issue that increasingly is being studied in the field of accounting and finance due to the considerable number of parts of the social fabric affected by the failure of a corporate entity. Banks, investors, governments, auditors, managers, suppliers, employees and many others have great interests in the accuracy of prediction of insolvency of a company. In Brazil, studies on the subject are still suffering the effects of being available only in databases with reduced dimensions, mostly due to data quality. But there is little studied issues in predictive modeling of insolvency. The balance or imbalance of data on insolvency is one of those issues in economic environments typical number of companies classified as solvent is much higher than those classified as insolvent. The aim of this study is to propose a new procedure for balancing of database problems in insolvency prediction with (step) feature selection. Was then constructed a strategy of data mining with the double virtue of selecting attributes and solve the problem of the imbalance. The database was derived from financial statements of Brazilian companies in the consumer cyclical economic sector, listed on the BOVESPA between the years 1996 and 2011. The results and validations performed demonstrate the success of the proposed strategy, improving the ability of the prediction model for the classification of companies belonging to the class of insolvent and thus consolidating it as quite competitive with other strategies presented in the specific literature. Given the nature of the empirical exercise, it is clear that the advantage of the new procedure does not depend on the studied sector. Keywords: Discontinuity of companies; Brazilian companies from the consumer discretionary sector, accounting variables, Data mining; Balancing database. 
id UFRN-3_f85cc13eadc508c0a6355eac98c3b131
oai_identifier_str oai:periodicos.ufrn.br:article/4124
network_acronym_str UFRN-3
network_name_str Revista Ambiente Contábil
repository_id_str
spelling DISCONTINUANCE OF BRAZILIAN COMPANIES SECTOR CONSUMPTION CYCLIC: A METHODOLOGY FOR BALANCING OF DATABASE USING DATA MINING TECHNIQUESINTERRUPCIÓN DEL BRASILEÑO SECTOR EMPRESARIAL DE CONSUMO CÍCLICO: UNA METODOLOGÍA PARA EQUILIBRAR LA BASE DE DATOS CON TÉCNICAS DE MINERÍA DE DATOSDESCONTINUIDADE DE EMPRESAS BRASILEIRAS DO SETOR DE CONSUMO CÍCLICO: UM ESTUDO COM DADOS CONTÁBEIS UTILIZANDO TÉCNICAS DE DATA MININGDiscontinuity of companies is an issue that increasingly is being studied in the field of accounting and finance due to the considerable number of parts of the social fabric affected by the failure of a corporate entity. Banks, investors, governments, auditors, managers, suppliers, employees and many others have great interests in the accuracy of prediction of insolvency of a company. In Brazil, studies on the subject are still suffering the effects of being available only in databases with reduced dimensions, mostly due to data quality. But there is little studied issues in predictive modeling of insolvency. The balance or imbalance of data on insolvency is one of those issues in economic environments typical number of companies classified as solvent is much higher than those classified as insolvent. The aim of this study is to propose a new procedure for balancing of database problems in insolvency prediction with (step) feature selection. Was then constructed a strategy of data mining with the double virtue of selecting attributes and solve the problem of the imbalance. The database was derived from financial statements of Brazilian companies in the consumer cyclical economic sector, listed on the BOVESPA between the years 1996 and 2011. The results and validations performed demonstrate the success of the proposed strategy, improving the ability of the prediction model for the classification of companies belonging to the class of insolvent and thus consolidating it as quite competitive with other strategies presented in the specific literature. Given the nature of the empirical exercise, it is clear that the advantage of the new procedure does not depend on the studied sector. Keywords: Discontinuity of companies; Brazilian companies from the consumer discretionary sector, accounting variables, Data mining; Balancing database. La discontinuidad de las empresas es un tema que se está estudiando cada vez más en el campo de la contabilidad y las finanzas, debido al número considerable de partes del tejido social afectado por la falla de una entidad corporativa. Bancos, inversores, gobiernos, auditores, gerentes, proveedores, empleados y muchos otros tienen grandes intereses en la exactitud de la predicción de la insolvencia de una empresa. En Brasil, los estudios sobre el tema siguen sufriendo los efectos de estar disponible sólo en bases de datos de dimensiones reducidas, casi siempre debido a la calidad de los datos. Pero hay pocos temas estudiados en modelos de predicción de la insolvencia. El desequilibrio o insolvencia datos desequilibrio es uno de esos problemas, en entornos económicos típicos del número de empresas clasificadas como disolventes es mucho mayor que los clasificados como insolvente. El objetivo de este estudio es proponer un nuevo procedimiento para el equilibrio de los problemas de base de datos en la predicción de la insolvencia con (paso) de selección de características. A continuación, se construyó una estrategia de minería de datos con la doble virtud de la selección de atributos y resolver el problema de desequilibrio. La base de datos se deriva de los estados financieros de las empresas brasileñas en el sector de la economía de consumo cíclico, que se enumeran en la Bovespa entre los años 1996 y 2011. Los resultados y validaciones demuestran el éxito de la estrategia propuesta, la mejora de la capacidad del modelo de pronóstico para la clasificación de las empresas que pertenecen a la clase de insolvencia y por lo tanto la consolidación como bastante competitivo con otros enfoques sugeridos en la literatura. Dada la naturaleza del ejercicio empírico, está claro que la ventaja del nuevo procedimiento no depende de el sector estudiado. Palabras clave: Negocios discontinuados. La selección de las variables de contabilidad. Equilibrio de base de datos. La minería de datos. Sector Consumidor Discrecional - Brasil.Descontinuidade de empresas é um tema que cada vez mais vem sendo estudado no campo da contabilidade e finanças devido ao considerável número de partes do tecido social afetadas pelo fracasso corporativo de uma entidade. Bancos, investidores, governos, auditores, gerentes, fornecedores, empregados e muitos outros têm grandes interesses na acurácia da previsão de insolvência de uma companhia. No Brasil os estudos sobre o tema ainda sofrem o efeito de estarem disponíveis apenas em bases de dados com dimensões reduzidas, quase sempre devido à qualidade dos dados. Mas há questões pouco estudadas na modelagem de previsão de insolvência. O desequilíbrio ou desbalanceamento dos dados sobre insolvência é uma dessas questões, em ambientes econômicos típicos o número de empresas classificadas como solventes é bem maior do que o daquelas classificadas como insolventes. O objetivo deste estudo é propor um novo procedimento para balanceamento da base de dados em problemas de previsão de insolvência com (etapa de) seleção de atributos. Foi então construída uma estratégia de data mining com a dupla virtude de selecionar atributos e de resolver o problema do desequilíbrio. A base de dados foi originada de demonstrativos contábeis de empresas brasileiras do setor econômico de consumo cíclico, listadas na BOVESPA entre os anos de 1996 e 2011. Os resultados obtidos e as validações realizadas evidenciam o sucesso da estratégia proposta, melhorando a capacidade do modelo de previsão na classificação das empresas pertencentes à classe das insolventes e, assim consolidando-a como bastante competitiva com outras estratégias apresentadas na literatura específica. Dada a natureza do exercício empírico, fica evidente que a vantagem do novo procedimento não depende do setor estudado.Palavras-chave: Descontinuidade de empresas. Seleção de variáveis contábeis. Balanceamento de base de dados. Data mining. Setor de consumo cíclico – Brasil.Portal de Periódicos Eletrônicos da UFRN2014-01-06info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicos.ufrn.br/ambiente/article/view/4124REVISTA AMBIENTE CONTÁBIL - Universidade Federal do Rio Grande do Norte; Vol. 6 No. 1 (2014): Jan./Jun.; 99-121REVISTA AMBIENTE CONTÁBIL - Universidade Federal do Rio Grande do Norte; Vol. 6 Núm. 1 (2014): Jan./Jun.; 99-121REVISTA AMBIENTE CONTÁBIL - Universidade Federal do Rio Grande do Norte - ISSN 2176-9036; v. 6 n. 1 (2014): Jan./Jun.; 99-1212176-9036reponame:Revista Ambiente Contábilinstname:Universidade Federal do Rio Grande do Norte (UFRN)instacron:UFRNporhttps://periodicos.ufrn.br/ambiente/article/view/4124/3993Copyright (c) 2016 REVISTA AMBIENTE CONTÁBIL - Universidade Federal do Rio Grande do Norte - ISSN 2176-9036info:eu-repo/semantics/openAccessHorta, Rui Américo MathiasiBorges, Carlos Cristiano HasencleverJorge, Marcelino José2019-10-09T22:35:15Zoai:periodicos.ufrn.br:article/4124Revistahttps://periodicos.ufrn.br/ambientePUBhttps://periodicos.ufrn.br/ambiente/oai||prof.mauriciocsilva@gmail.com2176-90362176-9036opendoar:2019-10-09T22:35:15Revista Ambiente Contábil - Universidade Federal do Rio Grande do Norte (UFRN)false
dc.title.none.fl_str_mv DISCONTINUANCE OF BRAZILIAN COMPANIES SECTOR CONSUMPTION CYCLIC: A METHODOLOGY FOR BALANCING OF DATABASE USING DATA MINING TECHNIQUES
INTERRUPCIÓN DEL BRASILEÑO SECTOR EMPRESARIAL DE CONSUMO CÍCLICO: UNA METODOLOGÍA PARA EQUILIBRAR LA BASE DE DATOS CON TÉCNICAS DE MINERÍA DE DATOS
DESCONTINUIDADE DE EMPRESAS BRASILEIRAS DO SETOR DE CONSUMO CÍCLICO: UM ESTUDO COM DADOS CONTÁBEIS UTILIZANDO TÉCNICAS DE DATA MINING
title DISCONTINUANCE OF BRAZILIAN COMPANIES SECTOR CONSUMPTION CYCLIC: A METHODOLOGY FOR BALANCING OF DATABASE USING DATA MINING TECHNIQUES
spellingShingle DISCONTINUANCE OF BRAZILIAN COMPANIES SECTOR CONSUMPTION CYCLIC: A METHODOLOGY FOR BALANCING OF DATABASE USING DATA MINING TECHNIQUES
Horta, Rui Américo Mathiasi
title_short DISCONTINUANCE OF BRAZILIAN COMPANIES SECTOR CONSUMPTION CYCLIC: A METHODOLOGY FOR BALANCING OF DATABASE USING DATA MINING TECHNIQUES
title_full DISCONTINUANCE OF BRAZILIAN COMPANIES SECTOR CONSUMPTION CYCLIC: A METHODOLOGY FOR BALANCING OF DATABASE USING DATA MINING TECHNIQUES
title_fullStr DISCONTINUANCE OF BRAZILIAN COMPANIES SECTOR CONSUMPTION CYCLIC: A METHODOLOGY FOR BALANCING OF DATABASE USING DATA MINING TECHNIQUES
title_full_unstemmed DISCONTINUANCE OF BRAZILIAN COMPANIES SECTOR CONSUMPTION CYCLIC: A METHODOLOGY FOR BALANCING OF DATABASE USING DATA MINING TECHNIQUES
title_sort DISCONTINUANCE OF BRAZILIAN COMPANIES SECTOR CONSUMPTION CYCLIC: A METHODOLOGY FOR BALANCING OF DATABASE USING DATA MINING TECHNIQUES
author Horta, Rui Américo Mathiasi
author_facet Horta, Rui Américo Mathiasi
Borges, Carlos Cristiano Hasenclever
Jorge, Marcelino José
author_role author
author2 Borges, Carlos Cristiano Hasenclever
Jorge, Marcelino José
author2_role author
author
dc.contributor.author.fl_str_mv Horta, Rui Américo Mathiasi
Borges, Carlos Cristiano Hasenclever
Jorge, Marcelino José
description Discontinuity of companies is an issue that increasingly is being studied in the field of accounting and finance due to the considerable number of parts of the social fabric affected by the failure of a corporate entity. Banks, investors, governments, auditors, managers, suppliers, employees and many others have great interests in the accuracy of prediction of insolvency of a company. In Brazil, studies on the subject are still suffering the effects of being available only in databases with reduced dimensions, mostly due to data quality. But there is little studied issues in predictive modeling of insolvency. The balance or imbalance of data on insolvency is one of those issues in economic environments typical number of companies classified as solvent is much higher than those classified as insolvent. The aim of this study is to propose a new procedure for balancing of database problems in insolvency prediction with (step) feature selection. Was then constructed a strategy of data mining with the double virtue of selecting attributes and solve the problem of the imbalance. The database was derived from financial statements of Brazilian companies in the consumer cyclical economic sector, listed on the BOVESPA between the years 1996 and 2011. The results and validations performed demonstrate the success of the proposed strategy, improving the ability of the prediction model for the classification of companies belonging to the class of insolvent and thus consolidating it as quite competitive with other strategies presented in the specific literature. Given the nature of the empirical exercise, it is clear that the advantage of the new procedure does not depend on the studied sector. Keywords: Discontinuity of companies; Brazilian companies from the consumer discretionary sector, accounting variables, Data mining; Balancing database. 
publishDate 2014
dc.date.none.fl_str_mv 2014-01-06
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://periodicos.ufrn.br/ambiente/article/view/4124
url https://periodicos.ufrn.br/ambiente/article/view/4124
dc.language.iso.fl_str_mv por
language por
dc.relation.none.fl_str_mv https://periodicos.ufrn.br/ambiente/article/view/4124/3993
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.publisher.none.fl_str_mv Portal de Periódicos Eletrônicos da UFRN
publisher.none.fl_str_mv Portal de Periódicos Eletrônicos da UFRN
dc.source.none.fl_str_mv REVISTA AMBIENTE CONTÁBIL - Universidade Federal do Rio Grande do Norte; Vol. 6 No. 1 (2014): Jan./Jun.; 99-121
REVISTA AMBIENTE CONTÁBIL - Universidade Federal do Rio Grande do Norte; Vol. 6 Núm. 1 (2014): Jan./Jun.; 99-121
REVISTA AMBIENTE CONTÁBIL - Universidade Federal do Rio Grande do Norte - ISSN 2176-9036; v. 6 n. 1 (2014): Jan./Jun.; 99-121
2176-9036
reponame:Revista Ambiente Contábil
instname:Universidade Federal do Rio Grande do Norte (UFRN)
instacron:UFRN
instname_str Universidade Federal do Rio Grande do Norte (UFRN)
instacron_str UFRN
institution UFRN
reponame_str Revista Ambiente Contábil
collection Revista Ambiente Contábil
repository.name.fl_str_mv Revista Ambiente Contábil - Universidade Federal do Rio Grande do Norte (UFRN)
repository.mail.fl_str_mv ||prof.mauriciocsilva@gmail.com
_version_ 1799770186714185728