Comparative Analysis of Logistics of Stationary Retail and Online Commerce

Yerniyazova, Zh.N.; Talapbayeva, Gulnar; Makasheva, G.K.; Galidenov, M.E.

doi:10.32014/2020.2518-1483.97

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(4) Reference model: For e-commerce retail projects, Caffe provides some reference models [9]. However, the high-speed computing claimed by Caffe in the early design stage is simply to use GPU to accelerate computing [10].…”

Section: Deep Learning Caffementioning

confidence: 99%

Deep Learning in E-commerce Retail

2022

View full text Add to dashboard Cite

With the continuous development of the e-commerce economy, consumers have gradually stepped from the dilemma of lack of information to the dilemma of excess information. In addition, under the influence of the epidemic, this year has set off a wave of live broadcasts in e-commerce, making more and more many people join the industry. In order to solve the shortcomings of existing research in the field of e-commerce retail, this paper discusses the functional equations of deep neural networks, the deep learning Caffe framework and the characteristics of e-commerce retail, and aims at the sample data of deep learning in the field of e-commerce retail and parameter settings are briefly introduced. And the design of the deep learning neural network e-commerce retail product recommendation system is discussed. Finally, the product click-through rate (CTR), transaction rate and favorable rate in the application of the deep learning neural network e-commerce retail product recommendation system designed in this paper are used in Adaboost. , RNN model for experimental comparison. The experimental data show that the click-through rate (CTR), transaction rate and favorable rate of products in the deep learning neural network application designed in this paper reach an average of 93%, while the Adaboost and RNN models reach 83% and 87% respectively. Therefore, it is verified that the model designed in this paper has good training effect and practical value in the field of e-commerce retail.

show abstract

Section: Deep Learning Caffementioning

confidence: 99%

Deep Learning in E-commerce Retail

2022

View full text Add to dashboard Cite

show abstract

Comparative Analysis of Logistics of Stationary Retail and Online Commerce

Cited by 1 publication

References 0 publications

Deep Learning in E-commerce Retail

Deep Learning in E-commerce Retail

Contact Info

Product

Resources

About