User behaviour modeling, recommendations, and purchase prediction during shopping festivals

Zeng, M.; Cao, Hancheng; Chen, Min; Li, Yong

doi:10.1007/s12525-018-0311-8

Cited by 53 publications

(33 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Prediction goals. Some models address the challenge of distinguishing between buying and non-buying sessions (B/NB, two possible prediction outcomes) [4], [7], [8], [29]- [35]. Alternatively, other works concentrate on calculating the probability that a customer buys either a specific product (B-Prod) [20], [36]- [38] or a class of products (B-CProd) [39], [40], makes a purchase in the next visit to the online store (Next) [41]- [43], or repurchases in a future session (ReP) [44], [45].…”

Section: Related Workmentioning

confidence: 99%

Log-Based Session Profiling and Online Behavioral Prediction in E–Commerce Websites

2020

View full text Add to dashboard Cite

Improvements to customer experience give companies a competitive advantage, as understanding customers' behaviors allows e-commerce companies to enhance their marketing strategies by means of recommendation techniques and the customization of products and services. This is not a simple task, and it becomes more difficult when working with anonymous sessions since no historical information of the user can be applied. In this paper, analysis and clustering of the clickstreams of past anonymous sessions are used to synthesize a prediction model based on a neural network. The model allows for prediction of a user's profile after a few clicks of an online anonymous session. This information can be used by the e-commerce's decision system to generate online recommendations and better adapt the offered services to the customer's profile. INDEX TERMS Behavior prediction, User profiling, Log analysis, Clustering, Neural networks, Model checking.

show abstract

Section: Related Workmentioning

confidence: 99%

Log-Based Session Profiling and Online Behavioral Prediction in E–Commerce Websites

2020

View full text Add to dashboard Cite

show abstract

“…Dentre os estudos que propõem soluções, foram encontrados trabalhos que utilizam bases de dados de empresas privadas de comércio eletrônico da China. Dentre estes estudos, podemos destacar (Zhao et al, 2016, Zeng et al, 2019, Zaim et al, 2019. Zhao et al (2016) apresentam uma solução para prever compras em uma plataforma de varejo on-line para consumidores da China.…”

Section: Trabalhos Relacionadosunclassified

“…De acordo com os autores, os resultados mostraram que os três grupos de variáveis apresentam um bom desempenho, mas que um modelo que utilize todos os grupos de variáveis juntos alcança um poder preditivo maior. Zeng et al (2019) utilizaram técnicas estatísticas para modelar o comportamento de usuários que fazem compras durante o dia do festival de compras na China. A base de dados foi composta por 31 milhões de logs gerados neste dia do festival.…”

Section: Trabalhos Relacionadosunclassified

Uma solução de mineração de dados para concessão de cupons de descontos em comércio eletrônico: um estudo de caso

Neto

Ramos

Silva

2019

RBCA

View full text Add to dashboard Cite

Este artigo pretende responder seguinte pergunta de pesquisa: ``como construir uma solução eficiente de mineração de dados para um sistema de cupom de desconto?''. Assim, neste artigo é proposto uma solução de mineração de dados para responder a essa pergunta. A solução é constituída por quatro componentes: 1) uso da técnica Random Forest como classificador, 2) tratamento dos valores ausentes, 3) enriquecimento da base de dados através da construção de novas variáveis e 4) uso do método de \textit{Kolmogorov Smirnov} para a escolha do ponto de corte para tomada de decisão. Um estudo experimental foi realizado para validar a eficiência da solução proposta. Os resultados mostraram a adequação do método ao problema e que a estratégia de aquisição de conhecimento proposta aumentou o poder preditivo. Por fim, os resultados mostraram que a estratégia de tratamento de valores ausentes possui influência no poder discriminatório da solução. A contribuição deste estudo é um direcionamento para construção de soluções de mineração de dados em web-shop, dando diretivas sobre qual método de mineração de dados utilizar, qual a melhor estratégia para tratamento de valores ausentes, como melhorar o poder preditivo através da aquisição de conhecimento e ainda como escolher o melhor ponto de corte.

show abstract

“…Small and Medium Enterprises (SMEs) could benefit from these methods to improve their efficiency as well. Beside the spread of COVID-19, different important reasons could be presented to show the appropriateness of machine learning methods for SMEs (Zeng et al 2019 ). For example, considering urban traffic management issues, using online tools for online shopping and online marketing is on the rise (McDonald et al 2019 ).…”

Section: Introductionmentioning

confidence: 99%

A Computational Model to Predict Consumer Behaviour During COVID-19 Pandemic

Safara

2020

Comput Econ

View full text Add to dashboard Cite

The knowledge-based economy has drawn increasing attention recently, particularly in online shopping applications where all the transactions and consumer opinions are logged. Machine learning methods could be used to extract implicit knowledge from the logs. Industries and businesses use the knowledge to better understand the consumer behavior, and opportunities and threats correspondingly. The outbreak of coronavirus (COVID-19) pandemic has a great impact on the different aspects of our daily life, in particular, on our shopping behaviour. To predict electronic consumer behaviour could be of valuable help for managers in government, supply chain and retail industry. Although, before coronavirus pandemic we have experienced online shopping, during the disease the number of online shopping increased dramatically. Due to high speed transmission of COVID-19, we have to observe personal and social health issues such as social distancing and staying at home. These issues have direct effect on consumer behaviour in online shopping. In this paper, a prediction model is proposed to anticipate the consumers behaviour using machine learning methods. Five individual classifiers, and their ensembles with Bagging and Boosting are examined on the dataset collected from an online shopping site. The results indicate the model constructed using decision tree ensembles with Bagging achieved the best prediction of consumer behavior with the accuracy of 95.3%. In addition, correlation analysis is performed to determine the most important features influencing the volume of online purchase during coronavirus pandemic.

show abstract

User behaviour modeling, recommendations, and purchase prediction during shopping festivals

Cited by 53 publications

References 19 publications

Log-Based Session Profiling and Online Behavioral Prediction in E–Commerce Websites

Log-Based Session Profiling and Online Behavioral Prediction in E–Commerce Websites

Uma solução de mineração de dados para concessão de cupons de descontos em comércio eletrônico: um estudo de caso

A Computational Model to Predict Consumer Behaviour During COVID-19 Pandemic

Contact Info

Product

Resources

About