Machine Learning Algorithms – Application on Big Data to Predict Retention Actions Needs
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10362/103843 |
Resumo: | The use of Machine Learning techniques is increasingly commonplace in multiple practical applications. Nowadays, the results of the application of these techniques are already routinely influencing our life and day-to-day tasks. Suggestions of videos to visualize; which route to take to a destination; facial recognition in biometric and security systems; all are practical examples of the advances made in this area. Many Machine Learning models are black box, given the complexity of the problems addressed and their algorithmic nature and, sometimes, do not offer a perception of their decision-making processes or are not directly interpretable when it comes to the reasons that originate their forecasts and results. The use of Explanatory Methods highlights patterns in the data, allowing a more assertive interpretation of results. Thus, this dissertation intends to develop a prototype that combines Machine Learning techniques with Explanatory Methods in order to improve the evaluation and validation of indicators, making the process of obtaining results by the algorithm and how it is affected more consistent and assertive. From a commercial point of view, based on the results of the models applied to the data, the consequent definition or reengineering of strategies obtains better operational results and the continuous improvement of indicators. With this prototype I intend to demonstrate that, from a practical point of view, obtaining representative indicators of customer permanence/loyalty in an organization, applying Machine Learning techniques on real data, and using explanatory methods, once the influence and weight of the characteristics are interpreted from the data on the model/s, it will be possible to redefine and fine-tune operational strategies. Specifically, as a practical case of this dissertation, it is expected that corporate systems such as Customer Relationship Management systems can benefit from the results of this dissertation through the application of Machine Learning techniques and the interpretation of Explanatory Methods. |
id |
RCAP_4ae6ef88c21db2bc01d869adbd842924 |
---|---|
oai_identifier_str |
oai:run.unl.pt:10362/103843 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Machine Learning Algorithms – Application on Big Data to Predict Retention Actions NeedsMachine LearningCustomer Relationship ManagementExplanation methodologyProbabilistic indicatorsDomínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e InformáticaThe use of Machine Learning techniques is increasingly commonplace in multiple practical applications. Nowadays, the results of the application of these techniques are already routinely influencing our life and day-to-day tasks. Suggestions of videos to visualize; which route to take to a destination; facial recognition in biometric and security systems; all are practical examples of the advances made in this area. Many Machine Learning models are black box, given the complexity of the problems addressed and their algorithmic nature and, sometimes, do not offer a perception of their decision-making processes or are not directly interpretable when it comes to the reasons that originate their forecasts and results. The use of Explanatory Methods highlights patterns in the data, allowing a more assertive interpretation of results. Thus, this dissertation intends to develop a prototype that combines Machine Learning techniques with Explanatory Methods in order to improve the evaluation and validation of indicators, making the process of obtaining results by the algorithm and how it is affected more consistent and assertive. From a commercial point of view, based on the results of the models applied to the data, the consequent definition or reengineering of strategies obtains better operational results and the continuous improvement of indicators. With this prototype I intend to demonstrate that, from a practical point of view, obtaining representative indicators of customer permanence/loyalty in an organization, applying Machine Learning techniques on real data, and using explanatory methods, once the influence and weight of the characteristics are interpreted from the data on the model/s, it will be possible to redefine and fine-tune operational strategies. Specifically, as a practical case of this dissertation, it is expected that corporate systems such as Customer Relationship Management systems can benefit from the results of this dissertation through the application of Machine Learning techniques and the interpretation of Explanatory Methods.Pereira, NunoSilva, JoaquimRUNVicente, Catarina Gonçalves Simões Nicolau2020-09-10T15:05:47Z2020-0720202020-07-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/103843enginfo: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:RCAAP2024-03-11T04:49:29Zoai:run.unl.pt:10362/103843Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:40:04.980187Repositório 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 |
Machine Learning Algorithms – Application on Big Data to Predict Retention Actions Needs |
title |
Machine Learning Algorithms – Application on Big Data to Predict Retention Actions Needs |
spellingShingle |
Machine Learning Algorithms – Application on Big Data to Predict Retention Actions Needs Vicente, Catarina Gonçalves Simões Nicolau Machine Learning Customer Relationship Management Explanation methodology Probabilistic indicators Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
title_short |
Machine Learning Algorithms – Application on Big Data to Predict Retention Actions Needs |
title_full |
Machine Learning Algorithms – Application on Big Data to Predict Retention Actions Needs |
title_fullStr |
Machine Learning Algorithms – Application on Big Data to Predict Retention Actions Needs |
title_full_unstemmed |
Machine Learning Algorithms – Application on Big Data to Predict Retention Actions Needs |
title_sort |
Machine Learning Algorithms – Application on Big Data to Predict Retention Actions Needs |
author |
Vicente, Catarina Gonçalves Simões Nicolau |
author_facet |
Vicente, Catarina Gonçalves Simões Nicolau |
author_role |
author |
dc.contributor.none.fl_str_mv |
Pereira, Nuno Silva, Joaquim RUN |
dc.contributor.author.fl_str_mv |
Vicente, Catarina Gonçalves Simões Nicolau |
dc.subject.por.fl_str_mv |
Machine Learning Customer Relationship Management Explanation methodology Probabilistic indicators Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
topic |
Machine Learning Customer Relationship Management Explanation methodology Probabilistic indicators Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
description |
The use of Machine Learning techniques is increasingly commonplace in multiple practical applications. Nowadays, the results of the application of these techniques are already routinely influencing our life and day-to-day tasks. Suggestions of videos to visualize; which route to take to a destination; facial recognition in biometric and security systems; all are practical examples of the advances made in this area. Many Machine Learning models are black box, given the complexity of the problems addressed and their algorithmic nature and, sometimes, do not offer a perception of their decision-making processes or are not directly interpretable when it comes to the reasons that originate their forecasts and results. The use of Explanatory Methods highlights patterns in the data, allowing a more assertive interpretation of results. Thus, this dissertation intends to develop a prototype that combines Machine Learning techniques with Explanatory Methods in order to improve the evaluation and validation of indicators, making the process of obtaining results by the algorithm and how it is affected more consistent and assertive. From a commercial point of view, based on the results of the models applied to the data, the consequent definition or reengineering of strategies obtains better operational results and the continuous improvement of indicators. With this prototype I intend to demonstrate that, from a practical point of view, obtaining representative indicators of customer permanence/loyalty in an organization, applying Machine Learning techniques on real data, and using explanatory methods, once the influence and weight of the characteristics are interpreted from the data on the model/s, it will be possible to redefine and fine-tune operational strategies. Specifically, as a practical case of this dissertation, it is expected that corporate systems such as Customer Relationship Management systems can benefit from the results of this dissertation through the application of Machine Learning techniques and the interpretation of Explanatory Methods. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-09-10T15:05:47Z 2020-07 2020 2020-07-01T00:00:00Z |
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/10362/103843 |
url |
http://hdl.handle.net/10362/103843 |
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_ |
1799138016565919744 |