Publication

A deep learning-based decision support system for mobile performance marketing

View document

Bibliographic Details
Summary:In Mobile Performance Marketing (MPM), monetary compensation only occurs when an advertisement results in a conversion (e.g., sale of a product or service). In this work, we propose an intelligent decision support system (IDSS) to automatically select mobile marketing campaigns for users. The IDSS is based on a computationally efficient mobile user conversion prediction model that assumes a novel Percentage Categorical Pruning (PCP) categorical preprocessing and an online deep multilayer perceptron (MLP) reuse model (MLPr). Using private (nonpublicly available) business MPM data provided by a marketing company, the MLPr model outperformed an offline multilayer perceptron and a logistic regression, obtaining a high quality class discrimination when applied to sampled (85% to 92%) and complete (90% to 94%) data. In addition, the MLPr compared favorably with other machine learning (ML) models (e.g., Random Forest, XGBoost), as well as with other deep neural networks (e.g., diamond shaped). Moreover, we designed two strategies (A - best campaign selection; and B - random selection among the top candidate campaigns) to build the IDSS, in which the predictive deep learning model is used to perform a real-time selection of advertisement campaigns for mobile users. Using recently collected big data (with millions of redirect events) from a worldwide MPM company, we performed a realistic IDSS evaluation that considered three criteria: response time, potential profit and advertiser diversity. Overall, competitive results were achieved by the IDSS B strategy when compared with the current marketing company ad assignment method.
Main Authors:Matos, Luis Miguel
Other Authors:Cortez, Paulo; Mendes, Rui; Moreau, Antoine
Subject:Big data Categorical transformation Classification Conversion Rate (CVR) Deep multilayer perceptron Intelligent decision support system (IDSS)
Year:2022
Country:Portugal
Document type:article
Access type:open access
Associated institution:Universidade do Minho
Language:English
Origin:RepositóriUM - Universidade do Minho
_version_ 1867439309895761920
author Matos, Luis Miguel
author2 Cortez, Paulo
Mendes, Rui
Moreau, Antoine
author2_role author
author
author
author_facet Matos, Luis Miguel
Cortez, Paulo
Mendes, Rui
Moreau, Antoine
author_role author
contributor_name_str_mv RepositóriUM - Universidade do Minho
country_str PT
creators_json_txt [{\"Person.name\":\"Matos, Luis Miguel\"},{\"Person.name\":\"Cortez, Paulo\"},{\"Person.name\":\"Mendes, Rui\"},{\"Person.name\":\"Moreau, Antoine\"}]
datacite.contributors.contributor.contributorName.fl_str_mv RepositóriUM - Universidade do Minho
datacite.creators.creator.creatorName.fl_str_mv Matos, Luis Miguel
Cortez, Paulo
Mendes, Rui
Moreau, Antoine
datacite.date.Accepted.fl_str_mv 2022-08-01T00:00:00Z
datacite.date.available.fl_str_mv 2023-12-28T14:19:15Z
datacite.date.embargoed.fl_str_mv 2023-12-28T14:19:15Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Big data
Categorical transformation
Classification
Conversion Rate (CVR)
Deep multilayer perceptron
Intelligent decision support system (IDSS)
datacite.titles.title.fl_str_mv A deep learning-based decision support system for mobile performance marketing
dc.contributor.none.fl_str_mv RepositóriUM - Universidade do Minho
dc.creator.none.fl_str_mv Matos, Luis Miguel
Cortez, Paulo
Mendes, Rui
Moreau, Antoine
dc.date.Accepted.fl_str_mv 2022-08-01T00:00:00Z
dc.date.available.fl_str_mv 2023-12-28T14:19:15Z
dc.date.embargoed.fl_str_mv 2023-12-28T14:19:15Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv https://hdl.handle.net/1822/87697
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv World Scientific Publishing
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Big data
Categorical transformation
Classification
Conversion Rate (CVR)
Deep multilayer perceptron
Intelligent decision support system (IDSS)
dc.title.fl_str_mv A deep learning-based decision support system for mobile performance marketing
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description In Mobile Performance Marketing (MPM), monetary compensation only occurs when an advertisement results in a conversion (e.g., sale of a product or service). In this work, we propose an intelligent decision support system (IDSS) to automatically select mobile marketing campaigns for users. The IDSS is based on a computationally efficient mobile user conversion prediction model that assumes a novel Percentage Categorical Pruning (PCP) categorical preprocessing and an online deep multilayer perceptron (MLP) reuse model (MLPr). Using private (nonpublicly available) business MPM data provided by a marketing company, the MLPr model outperformed an offline multilayer perceptron and a logistic regression, obtaining a high quality class discrimination when applied to sampled (85% to 92%) and complete (90% to 94%) data. In addition, the MLPr compared favorably with other machine learning (ML) models (e.g., Random Forest, XGBoost), as well as with other deep neural networks (e.g., diamond shaped). Moreover, we designed two strategies (A - best campaign selection; and B - random selection among the top candidate campaigns) to build the IDSS, in which the predictive deep learning model is used to perform a real-time selection of advertisement campaigns for mobile users. Using recently collected big data (with millions of redirect events) from a worldwide MPM company, we performed a realistic IDSS evaluation that considered three criteria: response time, potential profit and advertiser diversity. Overall, competitive results were achieved by the IDSS B strategy when compared with the current marketing company ad assignment method.
dirty 0
eu_rights_str_mv openAccess
format article
fulltext.url.fl_str_mv https://repositorium.uminho.pt/bitstreams/4d392694-b794-431b-946c-b35c0f095078/download
id rum_fbb3d0697de52e3df190aa9a3fc8cd4a
identifier.url.fl_str_mv https://hdl.handle.net/1822/87697
instacron_str repositorium
institution Universidade do Minho
instname_str Universidade do Minho
language eng
network_acronym_str rum
network_name_str RepositóriUM - Universidade do Minho
oai_identifier_str oai:repositorium.uminho.pt:1822/87697
organization_str_mv urn:organizationAcronym:repositorium
person_str_mv Matos, Luis Miguel
Cortez, Paulo
Mendes, Rui
Moreau, Antoine
publishDate 2022
publisher.none.fl_str_mv World Scientific Publishing
reponame_str RepositóriUM - Universidade do Minho
repository_id_str urn:repositoryAcronym:rum
service_str_mv urn:repositoryAcronym:rum
spelling engWorld Scientific PublishingporIn Mobile Performance Marketing (MPM), monetary compensation only occurs when an advertisement results in a conversion (e.g., sale of a product or service). In this work, we propose an intelligent decision support system (IDSS) to automatically select mobile marketing campaigns for users. The IDSS is based on a computationally efficient mobile user conversion prediction model that assumes a novel Percentage Categorical Pruning (PCP) categorical preprocessing and an online deep multilayer perceptron (MLP) reuse model (MLPr). Using private (nonpublicly available) business MPM data provided by a marketing company, the MLPr model outperformed an offline multilayer perceptron and a logistic regression, obtaining a high quality class discrimination when applied to sampled (85% to 92%) and complete (90% to 94%) data. In addition, the MLPr compared favorably with other machine learning (ML) models (e.g., Random Forest, XGBoost), as well as with other deep neural networks (e.g., diamond shaped). Moreover, we designed two strategies (A - best campaign selection; and B - random selection among the top candidate campaigns) to build the IDSS, in which the predictive deep learning model is used to perform a real-time selection of advertisement campaigns for mobile users. Using recently collected big data (with millions of redirect events) from a worldwide MPM company, we performed a realistic IDSS evaluation that considered three criteria: response time, potential profit and advertiser diversity. Overall, competitive results were achieved by the IDSS B strategy when compared with the current marketing company ad assignment method.application/pdfporA deep learning-based decision support system for mobile performance marketingMatos, Luis MiguelCortez, PauloMendes, RuiMoreau, AntoineHostingInstitutionOrganizationalRepositóriUM - Universidade do Minhoe-mailmailto:repositorium@usdb.uminho.ptrepositorium@usdb.uminho.ptISSNIsPartOf0219-6220EISSNIsPartOf1793-6845DOIIsPartOf10.1142/S021962202250047X2023-12-28T14:19:15Z2022-082023-12-27T18:07:15Z2022-08-01T00:00:00ZHandlehttps://hdl.handle.net/1822/87697http://purl.org/coar/access_right/c_abf2open accessBig dataCategorical transformationClassificationConversion Rate (CVR)Deep multilayer perceptronIntelligent decision support system (IDSS)231947 bytesliteraturehttp://purl.org/coar/resource_type/c_6501journal articlehttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://repositorium.uminho.pt/bitstreams/4d392694-b794-431b-946c-b35c0f095078/download
spellingShingle A deep learning-based decision support system for mobile performance marketing
Matos, Luis Miguel
Big data
Categorical transformation
Classification
Conversion Rate (CVR)
Deep multilayer perceptron
Intelligent decision support system (IDSS)
status SINGLETON
subject.fl_str_mv Big data
Categorical transformation
Classification
Conversion Rate (CVR)
Deep multilayer perceptron
Intelligent decision support system (IDSS)
title A deep learning-based decision support system for mobile performance marketing
title_full A deep learning-based decision support system for mobile performance marketing
title_fullStr A deep learning-based decision support system for mobile performance marketing
title_full_unstemmed A deep learning-based decision support system for mobile performance marketing
title_short A deep learning-based decision support system for mobile performance marketing
title_sort A deep learning-based decision support system for mobile performance marketing
topic Big data
Categorical transformation
Classification
Conversion Rate (CVR)
Deep multilayer perceptron
Intelligent decision support system (IDSS)
topic_facet Big data
Categorical transformation
Classification
Conversion Rate (CVR)
Deep multilayer perceptron
Intelligent decision support system (IDSS)
url https://hdl.handle.net/1822/87697
visible 1