Predicting customer abandonment in recurrent neural networks using short-term memory

Customer retention, a critical business priority, has become a growing concern, especially in the telecommunications industry. This study addresses the need to anticipate and understand customer churn through the application of Deep Learning models. The central focus of the research was the developm...

Descripción completa

Detalles Bibliográficos
Autores: Beltozar-Clemente, Saul, Iparraguirre-Villanueva, Orlando, Pucuhuayla-Revatta, Félix, Zapata-Paulini, Joselyn, Cabanillas-Carbonell, Michael
Tipo de recurso: artículo
Fecha de publicación:2023
País:Perú
Institución:Universidad Autónoma del Perú
Repositorio:AUTONOMA-Institucional
Idioma:inglés
OAI Identifier:oai:repositorio.autonoma.edu.pe:20.500.13067/3175
Acceso en línea:https://hdl.handle.net/20.500.13067/3175
https://doi.org/10.1016/j.joitmc.2024.100237
Access Level:acceso abierto
Palabra clave:Deep learning
LSTM
Churn prediction
Customer churn
Telecommunication
https://purl.org/pe-repo/ocde/ford#2.02.04
id PE_a605f00a6a4d1fc6004d20993301b132
oai_identifier_str oai:repositorio.autonoma.edu.pe:20.500.13067/3175
network_acronym_str PE
network_name_str Perú
repository_id_str
spelling 2024-05-23T14:28:20Z2024-05-23T14:28:20Z2023https://hdl.handle.net/20.500.13067/3175Journal of Open Innovation: Technology, Market, and Complexityhttps://doi.org/10.1016/j.joitmc.2024.100237Customer retention, a critical business priority, has become a growing concern, especially in the telecommunications industry. This study addresses the need to anticipate and understand customer churn through the application of Deep Learning models. The central focus of the research was the development and evaluation of a short-term memory model (LSTM) specifically designed to predict customer leakage. The choice of LSTM as the mainstay of the research is based on its proven ability to model long-term dependencies in sequences, its resilience to recurrent challenges in neural networks, and its success in various sequence prediction tasks. The model implementation, configured sequentially with Keras, comprised of an initial LSTM layer of 64 units, followed by a 20% removal layer to mitigate overfitting. The second LSTM layer, with 32 units, was supplemented with another elimination layer. Model training was conducted using a dataset consisting of 20 attributes and 4250 records. The model evaluation was based on crucial measures such as precision, accuracy, sensitivity and F1 count, revealing exceptional results with 95% performance on all metrics. This study, therefore, highlights the effectiveness of the LSTM model in predicting customer churn, providing companies with a valuable tool to improve retention and mitigate associated losses.application/pdfengElsevierinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/4.0/Deep learningLSTMChurn predictionCustomer churnTelecommunicationhttps://purl.org/pe-repo/ocde/ford#2.02.04Predicting customer abandonment in recurrent neural networks using short-term memoryinfo:eu-repo/semantics/article10119reponame:AUTONOMA-Institucionalinstname:Universidad Autónoma del Perúinstacron:AUTONOMABeltozar-Clemente, SaulIparraguirre-Villanueva, OrlandoPucuhuayla-Revatta, FélixZapata-Paulini, JoselynCabanillas-Carbonell, MichaelORIGINAL14.pdf14.pdfArtículoapplication/pdf1954267http://repositorio.autonoma.edu.pe/bitstream/20.500.13067/3175/1/14.pdfc71e5b920e387910e044a7dab1938a44MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-885http://repositorio.autonoma.edu.pe/bitstream/20.500.13067/3175/2/license.txt9243398ff393db1861c890baeaeee5f9MD52TEXT14.pdf.txt14.pdf.txtExtracted texttext/plain54614http://repositorio.autonoma.edu.pe/bitstream/20.500.13067/3175/3/14.pdf.txt65df918100fd3d17b76063f1807da458MD53THUMBNAIL14.pdf.jpg14.pdf.jpgGenerated Thumbnailimage/jpeg7517http://repositorio.autonoma.edu.pe/bitstream/20.500.13067/3175/4/14.pdf.jpg3ca8f374503e98631a6a9694fbcc70e7MD5420.500.13067/3175oai:repositorio.autonoma.edu.pe:20.500.13067/31752025-01-06 16:15:53.121Repositorio de la Universidad Autonoma del Perúrepositorio@autonoma.peVG9kb3MgbG9zIGRlcmVjaG9zIHJlc2VydmFkb3MgcG9yOg0KVU5JVkVSU0lEQUQgQVVUw5NOT01BIERFTCBQRVLDmg0KQ1JFQVRJVkUgQ09NTU9OUw==
dc.title.es_PE.fl_str_mv Predicting customer abandonment in recurrent neural networks using short-term memory
title Predicting customer abandonment in recurrent neural networks using short-term memory
spellingShingle Predicting customer abandonment in recurrent neural networks using short-term memory
Beltozar-Clemente, Saul
Deep learning
LSTM
Churn prediction
Customer churn
Telecommunication
https://purl.org/pe-repo/ocde/ford#2.02.04
title_short Predicting customer abandonment in recurrent neural networks using short-term memory
title_full Predicting customer abandonment in recurrent neural networks using short-term memory
title_fullStr Predicting customer abandonment in recurrent neural networks using short-term memory
title_full_unstemmed Predicting customer abandonment in recurrent neural networks using short-term memory
title_sort Predicting customer abandonment in recurrent neural networks using short-term memory
dc.creator.none.fl_str_mv Beltozar-Clemente, Saul
Iparraguirre-Villanueva, Orlando
Pucuhuayla-Revatta, Félix
Zapata-Paulini, Joselyn
Cabanillas-Carbonell, Michael
author Beltozar-Clemente, Saul
author_facet Beltozar-Clemente, Saul
Iparraguirre-Villanueva, Orlando
Pucuhuayla-Revatta, Félix
Zapata-Paulini, Joselyn
Cabanillas-Carbonell, Michael
author_role author
author2 Iparraguirre-Villanueva, Orlando
Pucuhuayla-Revatta, Félix
Zapata-Paulini, Joselyn
Cabanillas-Carbonell, Michael
author2_role author
author
author
author
dc.subject.es_PE.fl_str_mv Deep learning
LSTM
Churn prediction
Customer churn
Telecommunication
topic Deep learning
LSTM
Churn prediction
Customer churn
Telecommunication
https://purl.org/pe-repo/ocde/ford#2.02.04
dc.subject.ocde.es_PE.fl_str_mv https://purl.org/pe-repo/ocde/ford#2.02.04
description Customer retention, a critical business priority, has become a growing concern, especially in the telecommunications industry. This study addresses the need to anticipate and understand customer churn through the application of Deep Learning models. The central focus of the research was the development and evaluation of a short-term memory model (LSTM) specifically designed to predict customer leakage. The choice of LSTM as the mainstay of the research is based on its proven ability to model long-term dependencies in sequences, its resilience to recurrent challenges in neural networks, and its success in various sequence prediction tasks. The model implementation, configured sequentially with Keras, comprised of an initial LSTM layer of 64 units, followed by a 20% removal layer to mitigate overfitting. The second LSTM layer, with 32 units, was supplemented with another elimination layer. Model training was conducted using a dataset consisting of 20 attributes and 4250 records. The model evaluation was based on crucial measures such as precision, accuracy, sensitivity and F1 count, revealing exceptional results with 95% performance on all metrics. This study, therefore, highlights the effectiveness of the LSTM model in predicting customer churn, providing companies with a valuable tool to improve retention and mitigate associated losses.
publishDate 2023
dc.date.accessioned.none.fl_str_mv 2024-05-23T14:28:20Z
dc.date.available.none.fl_str_mv 2024-05-23T14:28:20Z
dc.date.issued.fl_str_mv 2023
dc.type.es_PE.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.uri.none.fl_str_mv https://hdl.handle.net/20.500.13067/3175
dc.identifier.journal.es_PE.fl_str_mv Journal of Open Innovation: Technology, Market, and Complexity
dc.identifier.doi.es_PE.fl_str_mv https://doi.org/10.1016/j.joitmc.2024.100237
url https://hdl.handle.net/20.500.13067/3175
https://doi.org/10.1016/j.joitmc.2024.100237
identifier_str_mv Journal of Open Innovation: Technology, Market, and Complexity
dc.language.iso.es_PE.fl_str_mv eng
language eng
dc.rights.es_PE.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.uri.es_PE.fl_str_mv https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/4.0/
dc.format.es_PE.fl_str_mv application/pdf
dc.publisher.es_PE.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:AUTONOMA-Institucional
instname:Universidad Autónoma del Perú
instacron:AUTONOMA
instname_str Universidad Autónoma del Perú
instacron_str AUTONOMA
institution AUTONOMA
reponame_str AUTONOMA-Institucional
collection AUTONOMA-Institucional
dc.source.volume.es_PE.fl_str_mv 10
dc.source.issue.es_PE.fl_str_mv 1
dc.source.beginpage.es_PE.fl_str_mv 1
dc.source.endpage.es_PE.fl_str_mv 9
bitstream.url.fl_str_mv http://repositorio.autonoma.edu.pe/bitstream/20.500.13067/3175/1/14.pdf
http://repositorio.autonoma.edu.pe/bitstream/20.500.13067/3175/2/license.txt
http://repositorio.autonoma.edu.pe/bitstream/20.500.13067/3175/3/14.pdf.txt
http://repositorio.autonoma.edu.pe/bitstream/20.500.13067/3175/4/14.pdf.jpg
bitstream.checksum.fl_str_mv c71e5b920e387910e044a7dab1938a44
9243398ff393db1861c890baeaeee5f9
65df918100fd3d17b76063f1807da458
3ca8f374503e98631a6a9694fbcc70e7
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio de la Universidad Autonoma del Perú
repository.mail.fl_str_mv repositorio@autonoma.pe
_version_ 1863014293777154048
score 15,301629

Similares en LA Referencia