Predicting Online Purchase Conversion for Retargeting

Yeo, Jinyoung; Kim, Sung‐Chul; Koh, Eunyee; Hwang, Seung-won; Lipka, Nedim

doi:10.1145/3018661.3018715

Cited by 25 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Sessions last from a few minutes to a few hours, and the number of clicked products varies from one to hundreds depending on user activity. This dataset has been used widely for consumer intention prediction and user behaviour modelling (Yeo et al 2017;Wu et al 2015;Brodén et al 2018;Bogina and Kuflik 2017;Mokryn et al 2019).…”

Section: Dataset Descriptionmentioning

confidence: 99%

Towards early purchase intention prediction in online session based retailing systems

2020

View full text Add to dashboard Cite

Purchase prediction has an important role for decision-makers in e-commerce to improve consumer experience, provide personalised recommendations and increase revenue. Many works investigated purchase prediction for session logs by analysing users’ behaviour to predict purchase intention after a session has ended. In most cases, e-shoppers prefer to be anonymous while browsing the websites and after a session has ended, identifying users and offering discounts can be challenging. Therefore, after a session ends, predicting purchase intention may not be useful for the e-commerce strategists. In this work, we propose and develop an early purchase prediction framework using advanced machine learning models to investigate how early purchase intention in an ongoing session can be predicted. Since users could be anonymous, this could help to give real-time offers and discounts before the session ends. We use dynamically created session features after each interaction in a session, and propose a utility scoring method to evaluate how early machine learning models can predict the probability of purchase intention. The proposed framework is validated with a real-world dataset. Computational experiments show machine learning models can identify purchase intention early with good performance in terms of Area Under Curve (AUC) score which shows success rate of machine learning models on early purchase prediction.

show abstract

Section: Dataset Descriptionmentioning

confidence: 99%

Towards early purchase intention prediction in online session based retailing systems

2020

View full text Add to dashboard Cite

show abstract

“…Ao acessar um vídeo conteúdo no YouTube, algoritmos de leilões [Sizov and Piller 2016, Wang et al 2014, Yeo et al 2017, Chen et al 2015, Mei et al 2017 Sitaraman 2013] são executados para selecionar vídeo propagandas a serem pareadas com o vídeo conteúdo. Este pareamento implica em exibir a vídeo propaganda selecionada para o usuário, geralmente antes do vídeo conteúdo (embora possa também ser exibida durante ou depois do stream do vídeo).…”

Section: Referencial Teórico E Trabalhos Relacionadosunclassified

“…Entretanto, antes de ter acesso ao conteúdo requisitado, ele pode ser exposto a uma vídeo propaganda e precisará assistí-la por um tempo mínimo 5 antes de ter acesso ao vídeo requisitado 6 . Existe uma grande gama de trabalhos prévios que abordam o tema de propagandas online [Sizov and Piller 2016, Wang et al 2014, Yeo et al 2017, Chen et al 2015, Mei et al 2017. Em particular no contexto de vídeo, o trabalho de Arantes et al [Arantes et al 2016, Arantes et al 2017, Arantes et al 2018] explorou características de tráfego da web [Arantes et al 2016], monetização [Arantes et al 2017], além de estudos com usuários [Arantes et al 2018].…”

Section: Referencial Teórico E Trabalhos Relacionadosunclassified

Analisando o Uso de uma Grande Rede de Streaming de Vídeos na Divulgação de Conteúdo Político

Giori

Figueiredo

Soares

et al. 2019

Anais Do XXXVII Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos (SBRC 2019)

View full text Add to dashboard Cite

Atualmente, o YouTube como plataforma de vídeos tem uma presença ubíqua na disseminação de conteúdo online. Desta forma, é esperado tanto que marqueteiros quanto criadores de conteúdo façam uso do YouTube para disseminação de produtos e ideias. Neste artigo, analisamos o tráfego de vídeos políticos e vídeo propagandas no YouTube durante as eleições de 2018. Nossa análise é realizada através de personas de rede sintéticas desenvolvidas de modo a simular o comportamento humano. Durante o período de aproximadamente 40 dias, simulamos eleitores de diferentes estados (através de VPNs), gênero (através de configurações de conta), além de alinhamento político (através de acessos à canais classificados como sendo de esquerda, centro e direita). Durante o experimento, as diferentes personas estavam susceptíveis as vídeo propagandas que são pareadas com os vídeos acessados de forma automatizada. Com base nos dados coletados, apresentamos um estudo focando em três aspectos: (1) características de popularidade do conteúdo dos canais; (2) na diferença de exposição de propagandas entre diferentes personas; (3) uma análise de partidos que mais fizeram uso da plataforma.

show abstract

“…Web usage mining has been used for a variety of purposes, including customer behavior studies (Hjort et al, ; Vijayalakshmi et al, ), request prioritization and service differentiation (Totok & Karamcheti, ), recommendation (Jiang et al, ), prediction (Liu et al, ; Yeo et al, ), and e‐commerce market analysis (Zhao et al, ). Among all, the work in (Totok & Karamcheti, ) is closest to the work in this paper.…”

Section: Related Workmentioning

confidence: 99%

“…One of the web mining directions is web usage mining, which focuses on techniques for identification of user navigation behavior within a website. Web usage mining has many applications such as website design (Srivastava, Cooley, Deshpande, & Tan, 2000), user classification (Totok & Karamcheti, 2010), production recommendation (Jiang, Zhu, Zhang, & Yuan, 2015), purchase prediction (Liu et al, 2016;Yeo, Kim, Koh, Hwang, & Lipka, 2017), market analysis and advertisement (Zhao et al, 2013), and so forth. This paper focuses on web usage mining for revenue maximization.…”

mentioning

confidence: 99%

Mining association rules for admission control and service differentiation in e‐commerce applications

Xue

Jarvis²

2018

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Workload demands in e-commerce applications are very dynamic in nature, therefore it is essential for internet service providers to manage server resources effectively to maximize total revenue in server overloading situations. In this paper, a data mining technique is applied to a typical e-commerce application model for identification of composite association rules that capture user navigation patterns. Two algorithms are then developed based on the derived rules for admission control, service differentiation, and priority scheduling. Our approach takes the following aspects into consideration: (a) only final purchase requests result in company revenue; (b) any other request can potentially lead to final purchase, depending upon the likelihood of the navigation sequence that starts from current request and leads to final purchase; (c) service differentiation and priority assignment are based on aggregated confidence and average support of the composite association rules. As identification of composite association rules and computation of confidence and support of the rules can be pre-computed offline, the proposed approach incurs minimum performance overheads. The evaluation results suggest that the proposed approach is effective in terms of request management for revenue maximization.

show abstract

Predicting Online Purchase Conversion for Retargeting

Cited by 25 publications

References 26 publications

Towards early purchase intention prediction in online session based retailing systems

Towards early purchase intention prediction in online session based retailing systems

Analisando o Uso de uma Grande Rede de Streaming de Vídeos na Divulgação de Conteúdo Político

Mining association rules for admission control and service differentiation in e‐commerce applications

Contact Info

Product

Resources

About