The Effect of Combining Algorithms in Recommendation Systems
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
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/1199 |
Resumo: | Due to the increasing investment of industry and the scientific development, new recommendation systems are constantly emerging, seeking to increase the precision of item`s suggestions to consumers and to cover a greater number of application contexts. However, choosing the optimal algorithm for a given application is not always a trivial task. Recent papers have studied ways to accomplish this choice automatically, through meta-learning strategies. This work investigates the effects of the extension of this meta-learning process from the application context level to the user context. Some experiments were performed from four recommendation models, selecting, from two different criteria, the algorithm that presents better performance in the task of mapping the preferences of each user, verifying the effect of the customized application of the algorithms on the systems overall performance. Positive results were achieved when the algorithm selection was based on approaches with similar complexities. |
id |
UFPE-2_29bb726280d4f873e4155aef5eefde85 |
---|---|
oai_identifier_str |
oai:ojs.poli.br:article/1199 |
network_acronym_str |
UFPE-2 |
network_name_str |
Revista de Engenharia e Pesquisa Aplicada |
repository_id_str |
|
spelling |
The Effect of Combining Algorithms in Recommendation SystemsUma Investigação Sobre o Efeito da Combinação de Algoritmos em Sistemas de RecomendaçãoDue to the increasing investment of industry and the scientific development, new recommendation systems are constantly emerging, seeking to increase the precision of item`s suggestions to consumers and to cover a greater number of application contexts. However, choosing the optimal algorithm for a given application is not always a trivial task. Recent papers have studied ways to accomplish this choice automatically, through meta-learning strategies. This work investigates the effects of the extension of this meta-learning process from the application context level to the user context. Some experiments were performed from four recommendation models, selecting, from two different criteria, the algorithm that presents better performance in the task of mapping the preferences of each user, verifying the effect of the customized application of the algorithms on the systems overall performance. Positive results were achieved when the algorithm selection was based on approaches with similar complexities.Em função do crescente investimento da indústria e do desenvolvimento científico na área, novos sistemas de recomendação surgem permanentemente, buscando incrementar a precisão da indicação de itens aos consumidores e abranger um maior número de contextos de aplicação. Entretanto, a escolha do algoritmo ideal para determinada aplicação nem sempre é uma tarefa trivial. Artigos recentes estudaram formas de realizar esta escolha de forma automática, através de estratégias de meta-aprendizado. Este trabalho busca investigar os efeitos da extensão desse processo de meta-aprendizado do nível de contexto de aplicação para o de usuário. Nesse sentido, foram realizados experimentos a partir de quatro modelos de recomendação, selecionando, a partir de dois critérios distintos, o algoritmo que apresenta melhor desempenho no mapeamento das preferências de cada usuário, verificando o efeito da aplicação personalizada dos algoritmos na performance global do sistema. Resultados positivos foram obtidos quando a seleção de algoritmos era baseada em abordagens de complexidades semelhantes.Escola Politécnica de Pernambuco2020-04-26info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdftext/htmlhttp://revistas.poli.br/index.php/repa/article/view/119910.25286/repa.v5i1.1199Journal of Engineering and Applied Research; Vol 5 No 1 (2020): Edição Especial em Ciência de Dados e Analytics; 58-66Revista de Engenharia e Pesquisa Aplicada; v. 5 n. 1 (2020): Edição Especial em Ciência de Dados e Analytics; 58-662525-425110.25286/repa.v5i1reponame:Revista de Engenharia e Pesquisa Aplicadainstname:Universidade Federal de Pernambuco (UFPE)instacron:UFPEporhttp://revistas.poli.br/index.php/repa/article/view/1199/575http://revistas.poli.br/index.php/repa/article/view/1199/588--Copyright (c) 2020 Marcos Antonio Almeida Souto Junior, Byron Leite Dantas Bezerrahttp://creativecommons.org/licenses/by-nc/4.0info:eu-repo/semantics/openAccessSouto Junior, Marcos Antonio AlmeidaBezerra, Byron Leite Dantas2021-07-13T08:41:09Zoai:ojs.poli.br:article/1199Revistahttp://revistas.poli.br/index.php/repaONGhttp://revistas.poli.br/index.php/repa/oai||repa@poli.br2525-42512525-4251opendoar:2021-07-13T08:41:09Revista de Engenharia e Pesquisa Aplicada - Universidade Federal de Pernambuco (UFPE)false |
dc.title.none.fl_str_mv |
The Effect of Combining Algorithms in Recommendation Systems Uma Investigação Sobre o Efeito da Combinação de Algoritmos em Sistemas de Recomendação |
title |
The Effect of Combining Algorithms in Recommendation Systems |
spellingShingle |
The Effect of Combining Algorithms in Recommendation Systems Souto Junior, Marcos Antonio Almeida |
title_short |
The Effect of Combining Algorithms in Recommendation Systems |
title_full |
The Effect of Combining Algorithms in Recommendation Systems |
title_fullStr |
The Effect of Combining Algorithms in Recommendation Systems |
title_full_unstemmed |
The Effect of Combining Algorithms in Recommendation Systems |
title_sort |
The Effect of Combining Algorithms in Recommendation Systems |
author |
Souto Junior, Marcos Antonio Almeida |
author_facet |
Souto Junior, Marcos Antonio Almeida Bezerra, Byron Leite Dantas |
author_role |
author |
author2 |
Bezerra, Byron Leite Dantas |
author2_role |
author |
dc.contributor.author.fl_str_mv |
Souto Junior, Marcos Antonio Almeida Bezerra, Byron Leite Dantas |
description |
Due to the increasing investment of industry and the scientific development, new recommendation systems are constantly emerging, seeking to increase the precision of item`s suggestions to consumers and to cover a greater number of application contexts. However, choosing the optimal algorithm for a given application is not always a trivial task. Recent papers have studied ways to accomplish this choice automatically, through meta-learning strategies. This work investigates the effects of the extension of this meta-learning process from the application context level to the user context. Some experiments were performed from four recommendation models, selecting, from two different criteria, the algorithm that presents better performance in the task of mapping the preferences of each user, verifying the effect of the customized application of the algorithms on the systems overall performance. Positive results were achieved when the algorithm selection was based on approaches with similar complexities. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-04-26 |
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/1199 10.25286/repa.v5i1.1199 |
url |
http://revistas.poli.br/index.php/repa/article/view/1199 |
identifier_str_mv |
10.25286/repa.v5i1.1199 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
http://revistas.poli.br/index.php/repa/article/view/1199/575 http://revistas.poli.br/index.php/repa/article/view/1199/588 |
dc.rights.driver.fl_str_mv |
Copyright (c) 2020 Marcos Antonio Almeida Souto Junior, Byron Leite Dantas Bezerra http://creativecommons.org/licenses/by-nc/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
Copyright (c) 2020 Marcos Antonio Almeida Souto Junior, Byron Leite Dantas Bezerra 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 |
- - |
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 5 No 1 (2020): Edição Especial em Ciência de Dados e Analytics; 58-66 Revista de Engenharia e Pesquisa Aplicada; v. 5 n. 1 (2020): Edição Especial em Ciência de Dados e Analytics; 58-66 2525-4251 10.25286/repa.v5i1 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_ |
1798035999781027840 |