Publicação

Click-through rate prediction : a comparative study of ensemble techniques in real-time bidding

Ver documento

Detalhes bibliográficos
Resumo:Real-Time Bidding is an automated mechanism to buy and sell ads in real time that uses data collected from internet users, to accurately deliver the right audience to the best-matched advertisers. It goes beyond contextual advertising by motivating the bidding focused on user data and also, it is different from the sponsored search auction where the bid price is associated with keywords. There is extensive literature regarding the classification and prediction of performance metrics such as click-through-rate, impression rate and bidding price. However, there is limited research on the application of advanced machine learning techniques, such as ensemble methods, on predicting click-through rate of real-time bidding campaigns. This paper presents an in-depth analysis of predicting click-through rate in real-time bidding campaigns by comparing the classification results from six traditional classification models (Linear Discriminant Analysis, Logistic Regression, Regularised Regression, Decision trees, k-nearest neighbors and Support Vector Machines) with two popular ensemble learning techniques (Voting and BootStrap Aggregation). The goal of our research is to determine whether ensemble methods can accurately predict click-through rate and compared to standard classifiers. Results showed that ensemble techniques outperformed simple classifiers performance. Moreover, also, highlights the excellent performance of linear algorithms (Linear Discriminant Analysis and Regularized Regression).
Autores principais:Blanc, Maria do Canto e Castro Faria
Assunto:Programmatic Real-Time bidding Click-through-rate Classification Ensemble methods
Ano:2019
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Universidade Nova de Lisboa
Idioma:inglês
Origem:Repositório Institucional da UNL
_version_ 1863891298810855424
author Blanc, Maria do Canto e Castro Faria
author_facet Blanc, Maria do Canto e Castro Faria
author_role author
contributor_name_str_mv Henriques, Roberto André Pereira
Melo, André Pestana Sampaio e
RUN
country_str PT
creators_json_str [{\"Person.name\":\"Blanc, Maria do Canto e Castro Faria\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Henriques, Roberto André Pereira
Melo, André Pestana Sampaio e
RUN
datacite.creators.creator.creatorName.fl_str_mv Blanc, Maria do Canto e Castro Faria
datacite.date.Accepted.fl_str_mv 2019-04-03T00:00:00Z
datacite.date.available.fl_str_mv 2019-05-31T18:26:47Z
datacite.date.embargoed.fl_str_mv 2019-05-31T18:26:47Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Programmatic
Real-Time bidding
Click-through-rate
Classification
Ensemble methods
datacite.titles.title.fl_str_mv Click-through rate prediction : a comparative study of ensemble techniques in real-time bidding
dc.contributor.none.fl_str_mv Henriques, Roberto André Pereira
Melo, André Pestana Sampaio e
RUN
dc.creator.none.fl_str_mv Blanc, Maria do Canto e Castro Faria
dc.date.Accepted.fl_str_mv 2019-04-03T00:00:00Z
dc.date.available.fl_str_mv 2019-05-31T18:26:47Z
dc.date.embargoed.fl_str_mv 2019-05-31T18:26:47Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10362/71313
dc.language.none.fl_str_mv eng
dc.rights.cclincense.fl_str_mv http://creativecommons.org/licenses/by/4.0/
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Programmatic
Real-Time bidding
Click-through-rate
Classification
Ensemble methods
dc.title.fl_str_mv Click-through rate prediction : a comparative study of ensemble techniques in real-time bidding
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_bdcc
description Real-Time Bidding is an automated mechanism to buy and sell ads in real time that uses data collected from internet users, to accurately deliver the right audience to the best-matched advertisers. It goes beyond contextual advertising by motivating the bidding focused on user data and also, it is different from the sponsored search auction where the bid price is associated with keywords. There is extensive literature regarding the classification and prediction of performance metrics such as click-through-rate, impression rate and bidding price. However, there is limited research on the application of advanced machine learning techniques, such as ensemble methods, on predicting click-through rate of real-time bidding campaigns. This paper presents an in-depth analysis of predicting click-through rate in real-time bidding campaigns by comparing the classification results from six traditional classification models (Linear Discriminant Analysis, Logistic Regression, Regularised Regression, Decision trees, k-nearest neighbors and Support Vector Machines) with two popular ensemble learning techniques (Voting and BootStrap Aggregation). The goal of our research is to determine whether ensemble methods can accurately predict click-through rate and compared to standard classifiers. Results showed that ensemble techniques outperformed simple classifiers performance. Moreover, also, highlights the excellent performance of linear algorithms (Linear Discriminant Analysis and Regularized Regression).
dirty 0
eu_rights_str_mv openAccess
format masterThesis
fulltext.url.fl_str_mv https://run.unl.pt/bitstreams/bf8f93e5-5330-4e95-b050-44feb0613e80/download
id run_4d65d052d9f33031bf9bda819cccc2b6
identifier.url.fl_str_mv http://hdl.handle.net/10362/71313
instacron_str unl
institution Universidade Nova de Lisboa
instname_str Universidade Nova de Lisboa
language eng
network_acronym_str run
network_name_str Repositório Institucional da UNL
oai_identifier_str oai:run.unl.pt:10362/71313
organization_str_mv urn:organizationAcronym:unl
person_str_mv Blanc, Maria do Canto e Castro Faria
publishDate 2019
reponame_str Repositório Institucional da UNL
repository_id_str urn:repositoryAcronym:run
service_str_mv urn:repositoryAcronym:run
spelling engpt_PTReal-Time Bidding is an automated mechanism to buy and sell ads in real time that uses data collected from internet users, to accurately deliver the right audience to the best-matched advertisers. It goes beyond contextual advertising by motivating the bidding focused on user data and also, it is different from the sponsored search auction where the bid price is associated with keywords. There is extensive literature regarding the classification and prediction of performance metrics such as click-through-rate, impression rate and bidding price. However, there is limited research on the application of advanced machine learning techniques, such as ensemble methods, on predicting click-through rate of real-time bidding campaigns. This paper presents an in-depth analysis of predicting click-through rate in real-time bidding campaigns by comparing the classification results from six traditional classification models (Linear Discriminant Analysis, Logistic Regression, Regularised Regression, Decision trees, k-nearest neighbors and Support Vector Machines) with two popular ensemble learning techniques (Voting and BootStrap Aggregation). The goal of our research is to determine whether ensemble methods can accurately predict click-through rate and compared to standard classifiers. Results showed that ensemble techniques outperformed simple classifiers performance. Moreover, also, highlights the excellent performance of linear algorithms (Linear Discriminant Analysis and Regularized Regression).application/pdfpt_PTClick-through rate prediction : a comparative study of ensemble techniques in real-time biddingBlanc, Maria do Canto e Castro FariaHenriques, Roberto André PereiraMelo, André Pestana Sampaio eHostingInstitutionOrganizationalRUNe-mailmailto:run@unl.ptrun@unl.ptURNurn:tid:2022506362019-05-31T18:26:47Z2019-04-032019-04-03T00:00:00ZHandlehttp://hdl.handle.net/10362/71313http://purl.org/coar/access_right/c_abf2open accessProgrammaticReal-Time biddingClick-through-rateClassificationEnsemble methods655445 bytesliteraturehttp://purl.org/coar/resource_type/c_bdccmaster thesis2019-04-03http://creativecommons.org/licenses/by/4.0/http://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://run.unl.pt/bitstreams/bf8f93e5-5330-4e95-b050-44feb0613e80/download
spellingShingle Click-through rate prediction : a comparative study of ensemble techniques in real-time bidding
Blanc, Maria do Canto e Castro Faria
Programmatic
Real-Time bidding
Click-through-rate
Classification
Ensemble methods
subject.fl_str_mv Programmatic
Real-Time bidding
Click-through-rate
Classification
Ensemble methods
title Click-through rate prediction : a comparative study of ensemble techniques in real-time bidding
title_full Click-through rate prediction : a comparative study of ensemble techniques in real-time bidding
title_fullStr Click-through rate prediction : a comparative study of ensemble techniques in real-time bidding
title_full_unstemmed Click-through rate prediction : a comparative study of ensemble techniques in real-time bidding
title_short Click-through rate prediction : a comparative study of ensemble techniques in real-time bidding
title_sort Click-through rate prediction : a comparative study of ensemble techniques in real-time bidding
topic Programmatic
Real-Time bidding
Click-through-rate
Classification
Ensemble methods
topic_facet Programmatic
Real-Time bidding
Click-through-rate
Classification
Ensemble methods
url http://hdl.handle.net/10362/71313
visible 1