Product Recommender System Using Hypergraph Neural Networks

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

Saghafi Fateme; Mirzaei Sayeh; Fahim Ali

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Seminar Paper

Paper Information

Seminar: INTERNATIONAL CONFERENCE ON WEB RESEARCH
Year:2023 | Issue:9

Download Full-Text

View:

Download:

Information Seminar Paper

Title

Product Recommender System Using Hypergraph Neural Networks

Author(s)

Saghafi Fateme | Mirzaei Sayeh | Fahim Ali

Keywords

Product recommendation system

short-term item correlation

dynamic user intent

user-item interaction

sequence of interactions

Abstract

Improving the performance of recommender systems in the field of product purchase has been one of the important challenges of e-commerce in recent years. The correct recognition of the user's preference and the accurate recommendation of items that meet his needs will certainly lead to progress in the development of online shopping and selling of items. Since the meaning of each item is different for users and the purpose of buying that item changes over time, it is difficult to understand what the user's thinking is now and what kind of product they are looking for. In this work, an approach based on hypergraph neural networks is presented to create a powerful representation for items and users, which can be used to create a correct representation for the user's intent and finally, according to his dynamic intent, offer him/her the right product. The idea of this approach is to use the short-term correlation of items with each other to give them meaning, which is very similar to the logic of buying items by people in the real world. To evaluate the approach, the results of the implementation of the model presented in this article and similar models in recent years are compared on a dataset called Amazon review, and the improvement of the results of the evaluation metrics compared to those models is observed.

Cites

No record.

References

No record.

Cite

APA: Copy

Saghafi, Fateme, Mirzaei, Sayeh, & Fahim, Ali. (). . . SID. https://sid.ir/paper/1046825/en

Vancouver: Copy

Saghafi Fateme, Mirzaei Sayeh, Fahim Ali. . . Available from: https://sid.ir/paper/1046825/en

IEEE: Copy

Fateme Saghafi, Sayeh Mirzaei, and Ali Fahim, “,” presented at the . , [Online]. Available: https://sid.ir/paper/1046825/en

Related Journal Papers