Analytical approach to churn identification and prevention
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Revista de Engenharia e Pesquisa Aplicada |
Texto Completo: | http://revistas.poli.br/index.php/repa/article/view/2461 |
Resumo: | Churn is a term that refers to customers who leave a company, this problem is constant in the business world. Thus, it becomes necessary to use data analysis and processing techniques to understand and solve the Churn process in a company. The company analyzed in this research was Justa, which is a Brazilian Fintech company, which provided the database for the evaluation and implementation of this study. The available base contains two parts: The customer information itself and their transactions, in which pre-processing steps were carried out for better data analysis. After the pre-processing steps, Machine Learning techniques and algorithms such as: K-means, KNN and Logistic Regression are applied in order to seek to solve the Churn problem in the company. The results obtained here show that, for the estimated scope, the project is able to say whether a customer is churn, based on their transactions, but due to the high turnover of customers, the groups of customers analyzed are not accentuated and have few behavioral patterns. For a more elaborate analysis of customer profiles, it is necessary to obtain more detailed customer information, such as monthly income, occupancy, among others. |
id |
UFPE-2_261b3e50a55d019372b4e7a37e144a99 |
---|---|
oai_identifier_str |
oai:ojs.poli.br:article/2461 |
network_acronym_str |
UFPE-2 |
network_name_str |
Revista de Engenharia e Pesquisa Aplicada |
repository_id_str |
|
spelling |
Analytical approach to churn identification and preventionAbordagem analítica para predição e prevenção do ChurnChurn is a term that refers to customers who leave a company, this problem is constant in the business world. Thus, it becomes necessary to use data analysis and processing techniques to understand and solve the Churn process in a company. The company analyzed in this research was Justa, which is a Brazilian Fintech company, which provided the database for the evaluation and implementation of this study. The available base contains two parts: The customer information itself and their transactions, in which pre-processing steps were carried out for better data analysis. After the pre-processing steps, Machine Learning techniques and algorithms such as: K-means, KNN and Logistic Regression are applied in order to seek to solve the Churn problem in the company. The results obtained here show that, for the estimated scope, the project is able to say whether a customer is churn, based on their transactions, but due to the high turnover of customers, the groups of customers analyzed are not accentuated and have few behavioral patterns. For a more elaborate analysis of customer profiles, it is necessary to obtain more detailed customer information, such as monthly income, occupancy, among others.O Churn, é um termo que se refere a clientes que abandonam uma empresa, este problema é constante no mundo empresarial. Dessa forma se torna necessário o uso de técnicas de análise e tratamento dos dados, para entender e solucionar o processo de Churn numa empresa. A empresa analisada nesta pesquisa foi a Justa, que é uma Fintech brasileira, que proporcionou a base de dados para avaliação e implementação deste estudo. A base disponibilizada contém duas partes: As informações dos clientes em si e as transações deles, nestas foram realizadas etapas de pré-processamento para melhor análise dos dados. Após as etapas de pré-processamento são aplicados técnicas e algoritmos de Machine Learning como: K-means, KNN e Logistic Regression a fim de buscar solucionar o problema de Churn na empresa. Os resultados aqui obtidos mostram que, para o escopo estimado, o projeto consegue dizer se um cliente é churn, com base nas suas transações, mas devido a grande rotatividade de clientes os grupos de clientes analisados não são acentuados e possuem poucos padrões comportamentais. Para uma análise mais elaborada dos perfis de cliente, é necessário obter informações mais detalhadas do cliente, como renda mensal, ocupação, entre outros.Escola Politécnica de Pernambuco2022-11-30info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdftext/htmlhttp://revistas.poli.br/index.php/repa/article/view/246110.25286/repa.v7i3.2461Journal of Engineering and Applied Research; Vol 7 No 3 (2022): Edição Especial em Ciência de Dados e Analytics; 64-72Revista de Engenharia e Pesquisa Aplicada; v. 7 n. 3 (2022): Edição Especial em Ciência de Dados e Analytics; 64-722525-425110.25286/repa.v7i3reponame:Revista de Engenharia e Pesquisa Aplicadainstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPEporhttp://revistas.poli.br/index.php/repa/article/view/2461/851http://revistas.poli.br/index.php/repa/article/view/2461/852Brazil; XXI Century;Brasil; Século XXI;Copyright (c) 2022 Lucas Matheus da Silva Oliveira, Lucas Azevedo Rêgo Lima, George Victor de Souza Alveshttp://creativecommons.org/licenses/by-nc/4.0info:eu-repo/semantics/openAccessAlves, George Victor de SouzaLima, Lucas Azevedo RêgoOliveira, Lucas Matheus da Silva2022-11-30T23:03:18Zoai:ojs.poli.br:article/2461Revistahttp://revistas.poli.br/index.php/repaONGhttp://revistas.poli.br/index.php/repa/oai||repa@poli.br2525-42512525-4251opendoar:2022-11-30T23:03:18Revista de Engenharia e Pesquisa Aplicada - Universidade Federal de Pernambuco (UFPE)false |
dc.title.none.fl_str_mv |
Analytical approach to churn identification and prevention Abordagem analítica para predição e prevenção do Churn |
title |
Analytical approach to churn identification and prevention |
spellingShingle |
Analytical approach to churn identification and prevention Alves, George Victor de Souza |
title_short |
Analytical approach to churn identification and prevention |
title_full |
Analytical approach to churn identification and prevention |
title_fullStr |
Analytical approach to churn identification and prevention |
title_full_unstemmed |
Analytical approach to churn identification and prevention |
title_sort |
Analytical approach to churn identification and prevention |
author |
Alves, George Victor de Souza |
author_facet |
Alves, George Victor de Souza Lima, Lucas Azevedo Rêgo Oliveira, Lucas Matheus da Silva |
author_role |
author |
author2 |
Lima, Lucas Azevedo Rêgo Oliveira, Lucas Matheus da Silva |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Alves, George Victor de Souza Lima, Lucas Azevedo Rêgo Oliveira, Lucas Matheus da Silva |
description |
Churn is a term that refers to customers who leave a company, this problem is constant in the business world. Thus, it becomes necessary to use data analysis and processing techniques to understand and solve the Churn process in a company. The company analyzed in this research was Justa, which is a Brazilian Fintech company, which provided the database for the evaluation and implementation of this study. The available base contains two parts: The customer information itself and their transactions, in which pre-processing steps were carried out for better data analysis. After the pre-processing steps, Machine Learning techniques and algorithms such as: K-means, KNN and Logistic Regression are applied in order to seek to solve the Churn problem in the company. The results obtained here show that, for the estimated scope, the project is able to say whether a customer is churn, based on their transactions, but due to the high turnover of customers, the groups of customers analyzed are not accentuated and have few behavioral patterns. For a more elaborate analysis of customer profiles, it is necessary to obtain more detailed customer information, such as monthly income, occupancy, among others. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-11-30 |
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 |
http://revistas.poli.br/index.php/repa/article/view/2461 10.25286/repa.v7i3.2461 |
url |
http://revistas.poli.br/index.php/repa/article/view/2461 |
identifier_str_mv |
10.25286/repa.v7i3.2461 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
http://revistas.poli.br/index.php/repa/article/view/2461/851 http://revistas.poli.br/index.php/repa/article/view/2461/852 |
dc.rights.driver.fl_str_mv |
http://creativecommons.org/licenses/by-nc/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf text/html |
dc.coverage.none.fl_str_mv |
Brazil; XXI Century; Brasil; Século XXI; |
dc.publisher.none.fl_str_mv |
Escola Politécnica de Pernambuco |
publisher.none.fl_str_mv |
Escola Politécnica de Pernambuco |
dc.source.none.fl_str_mv |
Journal of Engineering and Applied Research; Vol 7 No 3 (2022): Edição Especial em Ciência de Dados e Analytics; 64-72 Revista de Engenharia e Pesquisa Aplicada; v. 7 n. 3 (2022): Edição Especial em Ciência de Dados e Analytics; 64-72 2525-4251 10.25286/repa.v7i3 reponame:Revista de Engenharia e Pesquisa Aplicada instname:Universidade Federal de Pernambuco (UFPE) instacron:UFPE |
instname_str |
Universidade Federal de Pernambuco (UFPE) |
instacron_str |
UFPE |
institution |
UFPE |
reponame_str |
Revista de Engenharia e Pesquisa Aplicada |
collection |
Revista de Engenharia e Pesquisa Aplicada |
repository.name.fl_str_mv |
Revista de Engenharia e Pesquisa Aplicada - Universidade Federal de Pernambuco (UFPE) |
repository.mail.fl_str_mv |
||repa@poli.br |
_version_ |
1798036000483573760 |