Visual Analytics Tailored to Support E-Commerce Marketplace Advertising: The ECommVis Platform

Detalhes bibliográficos
Ano de defesa: 2025
Autor(a) principal: Gino, Henrique Luiz Shibata
Orientador(a): Não Informado pela instituição
Banca de defesa: Não Informado pela instituição
Tipo de documento: Dissertação
Tipo de acesso: Acesso aberto
Idioma: eng
Instituição de defesa: Biblioteca Digitais de Teses e Dissertações da USP
Programa de Pós-Graduação: Não Informado pela instituição
Departamento: Não Informado pela instituição
País: Não Informado pela instituição
Palavras-chave em Português:
Advertising performance
Análise visual
Marketplaces online
Online marketplace
Performance de anúncios
Visual analytics
Link de acesso: https://www.teses.usp.br/teses/disponiveis/55/55134/tde-18112025-120315/
Resumo: E-commerce platforms rely increasingly on digital advertising to drive merchant sales, yet existing analytics tools often fail to provide contextual insights that connect advertising performance with actionable business strategies. This is especially true in online marketplaces, where many sellers struggle to assess if their advertising performance from sponsored sales truly aligns with their selling strategy. Based on that, this study introduces ECommVis, a visual analytics system designed to address the gap between complex advertising metrics and merchant decision-making in e-commerce marketplaces. ECommVis integrates five complementary visualization components that provide temporal, spatial, and comparative perspectives on advertising performance: Orders Over Time (OS) tracks historical organic versus ad-driven sales through adjustable time frames; Geospatial Interactions (GS) visualizes spatial performance patterns using hexagonal grid mapping; Merchant Metrics (MC) displays advertising KPIs via interactive stacked charts correlating budget with engagement; Interactions by Weekday and Shift (HM) identifies optimal advertising windows across daily shifts and weekday patterns; and Time Period Comparison (TP) benchmarks campaigns across time frames using correlation, trend, and search term analyses. ECommViss usefulness and effectiveness is demonstrated through two usage scenarios developed with real food delivery platform data, and a user study with 11 platform experts.
id USP_33a362e8b3259d5fc319429ecd756970
oai_identifier_str oai:teses.usp.br:tde-18112025-120315
network_acronym_str USP
network_name_str Biblioteca Digital de Teses e Dissertações da USP
repository_id_str
spelling Visual Analytics Tailored to Support E-Commerce Marketplace Advertising: The ECommVis PlatformAnálise Visual Adaptada para Apoiar Publicidade em Marketplaces de E- commerce: A Plataforma ECommVisAdvertising performanceAnálise visualMarketplaces onlineOnline marketplacePerformance de anúnciosVisual analyticsE-commerce platforms rely increasingly on digital advertising to drive merchant sales, yet existing analytics tools often fail to provide contextual insights that connect advertising performance with actionable business strategies. This is especially true in online marketplaces, where many sellers struggle to assess if their advertising performance from sponsored sales truly aligns with their selling strategy. Based on that, this study introduces ECommVis, a visual analytics system designed to address the gap between complex advertising metrics and merchant decision-making in e-commerce marketplaces. ECommVis integrates five complementary visualization components that provide temporal, spatial, and comparative perspectives on advertising performance: Orders Over Time (OS) tracks historical organic versus ad-driven sales through adjustable time frames; Geospatial Interactions (GS) visualizes spatial performance patterns using hexagonal grid mapping; Merchant Metrics (MC) displays advertising KPIs via interactive stacked charts correlating budget with engagement; Interactions by Weekday and Shift (HM) identifies optimal advertising windows across daily shifts and weekday patterns; and Time Period Comparison (TP) benchmarks campaigns across time frames using correlation, trend, and search term analyses. ECommViss usefulness and effectiveness is demonstrated through two usage scenarios developed with real food delivery platform data, and a user study with 11 platform experts.Plataformas de e-commerce dependem cada vez mais de anúncios para impulsionar as vendas dos lojistas. No entanto, as ferramentas de análise existentes muitas vezes não fornecem insights contextuais que conectem o desempenho da publicidade com estratégias de negócios acionáveis. Isso é notado em marketplaces online, onde muitos vendedores têm dificuldade em avaliar se o desempenho de seus anúncios a partir de vendas patrocinadas realmente se alinha com sua estratégia de vendas. Baseado nisso, esta Dissertação de Mestrado introduz ECommVis, um sistema de análise visual desenvolvido para endereçar essa lacuna entre métricas de anúncio complexas e tomada de decisões em marketplaces de e-commerce. O ECommVis integra cinco componentes de visualização complementares que oferecem perspectivas temporais, espaciais e comparativas sobre o desempenho de anúncios: Orders Over Time (OS) rastreia vendas históricas orgânicas versus vendas impulsionadas por anúncios através de períodos ajustáveis; Geospatial Interactions (GS) visualiza padrões de desempenho espacial usando mapeamento em grade hexagonal; Merchant Metrics (MC) exibe Key Performance Indicators (KPIs) de publicidade via gráficos interativos que correlacionam orçamento com engajamento; Interactions by Weekday and Shift (HM) identifica janelas de publicidade ótimas em turnos diários e padrões de dias da semana; e Time Period Comparison (TP) compara campanhas em diferentes períodos usando análises de correlação, tendência e termos de busca. A utilidade e eficácia do ECommVis são demonstradas por meio de dois cenários de uso desenvolvidos com dados reais de uma plataforma de entrega de alimentos, e um estudo de usuário com 11 especialistas da plataforma.Biblioteca Digitais de Teses e Dissertações da USPLinhares, Claudio Douglas GouveiaTraina, Agma Juci MachadoGino, Henrique Luiz Shibata2025-07-30info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttps://www.teses.usp.br/teses/disponiveis/55/55134/tde-18112025-120315/reponame:Biblioteca Digital de Teses e Dissertações da USPinstname:Universidade de São Paulo (USP)instacron:USPLiberar o conteúdo para acesso público.info:eu-repo/semantics/openAccesseng2025-11-18T14:21:02Zoai:teses.usp.br:tde-18112025-120315Biblioteca Digital de Teses e Dissertaçõeshttp://www.teses.usp.br/PUBhttp://www.teses.usp.br/cgi-bin/mtd2br.plvirginia@if.usp.br|| atendimento@aguia.usp.br||virginia@if.usp.bropendoar:27212025-11-18T14:21:02Biblioteca Digital de Teses e Dissertações da USP - Universidade de São Paulo (USP)false
dc.title.none.fl_str_mv Visual Analytics Tailored to Support E-Commerce Marketplace Advertising: The ECommVis Platform
Análise Visual Adaptada para Apoiar Publicidade em Marketplaces de E- commerce: A Plataforma ECommVis
title Visual Analytics Tailored to Support E-Commerce Marketplace Advertising: The ECommVis Platform
spellingShingle Visual Analytics Tailored to Support E-Commerce Marketplace Advertising: The ECommVis Platform
Gino, Henrique Luiz Shibata
Advertising performance
Análise visual
Marketplaces online
Online marketplace
Performance de anúncios
Visual analytics
title_short Visual Analytics Tailored to Support E-Commerce Marketplace Advertising: The ECommVis Platform
title_full Visual Analytics Tailored to Support E-Commerce Marketplace Advertising: The ECommVis Platform
title_fullStr Visual Analytics Tailored to Support E-Commerce Marketplace Advertising: The ECommVis Platform
title_full_unstemmed Visual Analytics Tailored to Support E-Commerce Marketplace Advertising: The ECommVis Platform
title_sort Visual Analytics Tailored to Support E-Commerce Marketplace Advertising: The ECommVis Platform
author Gino, Henrique Luiz Shibata
author_facet Gino, Henrique Luiz Shibata
author_role author
dc.contributor.none.fl_str_mv Linhares, Claudio Douglas Gouveia
Traina, Agma Juci Machado
dc.contributor.author.fl_str_mv Gino, Henrique Luiz Shibata
dc.subject.por.fl_str_mv Advertising performance
Análise visual
Marketplaces online
Online marketplace
Performance de anúncios
Visual analytics
topic Advertising performance
Análise visual
Marketplaces online
Online marketplace
Performance de anúncios
Visual analytics
description E-commerce platforms rely increasingly on digital advertising to drive merchant sales, yet existing analytics tools often fail to provide contextual insights that connect advertising performance with actionable business strategies. This is especially true in online marketplaces, where many sellers struggle to assess if their advertising performance from sponsored sales truly aligns with their selling strategy. Based on that, this study introduces ECommVis, a visual analytics system designed to address the gap between complex advertising metrics and merchant decision-making in e-commerce marketplaces. ECommVis integrates five complementary visualization components that provide temporal, spatial, and comparative perspectives on advertising performance: Orders Over Time (OS) tracks historical organic versus ad-driven sales through adjustable time frames; Geospatial Interactions (GS) visualizes spatial performance patterns using hexagonal grid mapping; Merchant Metrics (MC) displays advertising KPIs via interactive stacked charts correlating budget with engagement; Interactions by Weekday and Shift (HM) identifies optimal advertising windows across daily shifts and weekday patterns; and Time Period Comparison (TP) benchmarks campaigns across time frames using correlation, trend, and search term analyses. ECommViss usefulness and effectiveness is demonstrated through two usage scenarios developed with real food delivery platform data, and a user study with 11 platform experts.
publishDate 2025
dc.date.none.fl_str_mv 2025-07-30
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 https://www.teses.usp.br/teses/disponiveis/55/55134/tde-18112025-120315/
url https://www.teses.usp.br/teses/disponiveis/55/55134/tde-18112025-120315/
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv
dc.rights.driver.fl_str_mv Liberar o conteúdo para acesso público.
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Liberar o conteúdo para acesso público.
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.coverage.none.fl_str_mv
dc.publisher.none.fl_str_mv Biblioteca Digitais de Teses e Dissertações da USP
publisher.none.fl_str_mv Biblioteca Digitais de Teses e Dissertações da USP
dc.source.none.fl_str_mv
reponame:Biblioteca Digital de Teses e Dissertações da USP
instname:Universidade de São Paulo (USP)
instacron:USP
instname_str Universidade de São Paulo (USP)
instacron_str USP
institution USP
reponame_str Biblioteca Digital de Teses e Dissertações da USP
collection Biblioteca Digital de Teses e Dissertações da USP
repository.name.fl_str_mv Biblioteca Digital de Teses e Dissertações da USP - Universidade de São Paulo (USP)
repository.mail.fl_str_mv virginia@if.usp.br|| atendimento@aguia.usp.br||virginia@if.usp.br
_version_ 1865492193159938048

Registros relacionados