Mobile app recommendations using deep learning and big data
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10362/59930 |
Resumo: | Dissertation presented as the partial requirement for obtaining a Master's degree in Statistics and Information Management, specialization in Marketing Research e CRM |
id |
RCAP_a1a42a8c2fac56648216cd2afaddd615 |
---|---|
oai_identifier_str |
oai:run.unl.pt:10362/59930 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Mobile app recommendations using deep learning and big dataSparkTensorflowSocial NetworksMachine LearningDissertation presented as the partial requirement for obtaining a Master's degree in Statistics and Information Management, specialization in Marketing Research e CRMRecommender systems were first introduced to solve information overload problems in enterprises. Over the last decades, recommender systems have found applications in several major websites related to e-commerce, music and video streaming, travel and movie sites, social media and mobile app stores. Several methods have been proposed over the years to build recommender systems. The most popular approaches are based on collaborative filtering techniques, which leverage the similarities between consumer tastes. But the current state of the art in recommender systems is deep-learning methods, which can leverage not only item consumption data but also content, context, and user attributes. Mobile app stores generate data with Big Data properties from app consumption data, behavioral, geographic, demographic, social network and user-generated content data, which includes reviews, comments and search queries. In this dissertation, we propose a deep-learning architecture for recommender systems in mobile app stores that leverage most of these data sources. We analyze three issues related to the impact of the data sources, the impact of embedding layer pretraining and the efficiency of using Kernel methods to improve app scoring at a Big Data scale. An experiment is conducted on a Portuguese Android app store. Results suggest that models can be improved by combining structured and unstructured data. The results also suggest that embedding layer pretraining is essential to obtain good results. Some evidence is provided showing that Kernel-based methods might not be efficient when deployed in Big Data contexts.Henriques, Roberto André PereiraRUNPinto, Luís António Galego2019-02-08T16:02:08Z2019-01-182019-01-18T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/59930TID:202167674enginfo: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:RCAAP2024-03-11T04:28:44Zoai:run.unl.pt:10362/59930Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:33:27.358444Repositório 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 |
Mobile app recommendations using deep learning and big data |
title |
Mobile app recommendations using deep learning and big data |
spellingShingle |
Mobile app recommendations using deep learning and big data Pinto, Luís António Galego Spark Tensorflow Social Networks Machine Learning |
title_short |
Mobile app recommendations using deep learning and big data |
title_full |
Mobile app recommendations using deep learning and big data |
title_fullStr |
Mobile app recommendations using deep learning and big data |
title_full_unstemmed |
Mobile app recommendations using deep learning and big data |
title_sort |
Mobile app recommendations using deep learning and big data |
author |
Pinto, Luís António Galego |
author_facet |
Pinto, Luís António Galego |
author_role |
author |
dc.contributor.none.fl_str_mv |
Henriques, Roberto André Pereira RUN |
dc.contributor.author.fl_str_mv |
Pinto, Luís António Galego |
dc.subject.por.fl_str_mv |
Spark Tensorflow Social Networks Machine Learning |
topic |
Spark Tensorflow Social Networks Machine Learning |
description |
Dissertation presented as the partial requirement for obtaining a Master's degree in Statistics and Information Management, specialization in Marketing Research e CRM |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-02-08T16:02:08Z 2019-01-18 2019-01-18T00:00:00Z |
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/10362/59930 TID:202167674 |
url |
http://hdl.handle.net/10362/59930 |
identifier_str_mv |
TID:202167674 |
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_ |
1799137956655529984 |