Leveraging attribute latent features for addressing new item cold-start issue

作者：

Highlights：

• Integrates CF, CB, and neural network technologies.

• Shows the advantage of using linear and non-linear latent features.

• Uses attribute information to solve the item cold-start issue.

• Enables the promotion of new products online.

摘要

•Integrates CF, CB, and neural network technologies.•Shows the advantage of using linear and non-linear latent features.•Uses attribute information to solve the item cold-start issue.•Enables the promotion of new products online.

论文关键词：E-commerce,Recommender system,Item cold-start problem,Matrix factorization,Neural networks

论文评审过程：Received 13 November 2021, Revised 20 June 2022, Accepted 8 July 2022, Available online 15 July 2022, Version of Record 15 July 2022.

论文官网地址：https://doi.org/10.1016/j.elerap.2022.101177