Next-Item Recommendation With Deep Adaptable Co-Embedding Neural Networks

The next-item recommendation has been in the central of interest in real-world applications such as e-commerce. However, it is challenging to infer what a user may purchase next due the complex interactions in the historical sessions and the changing semantics of an item over time. Most existing met...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2021, Vol.28, p.1220-1224
Main Authors: Chen, Daochang, Hu, Wenzheng, Yuan, Bo, Zhang, Rui, Wang, Jianqiang
Format: Article
Language:English
Subjects:
co-embedding
Covariance matrices
dynamic integration
Electronic mail
Embedding
evolving preferences
Markov processes
Neural networks
Recommender systems
Semantics
Sequential behavior
Social networking (online)
Training
Vehicle dynamics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The next-item recommendation has been in the central of interest in real-world applications such as e-commerce. However, it is challenging to infer what a user may purchase next due the complex interactions in the historical sessions and the changing semantics of an item over time. Most existing methods employ separate models to generate the general preference and the sequential patterns for the next-item recommendation without considering the interactions between the two factors or use a simple linear combination of the two factors. In this paper, we propose a deep adaptable co-embedding neural network (ACENet) to address these limitations. ACENet not only adaptably balances the combination of general preference and sequential patterns but also introduces dynamic attention for each factor in hybrid representations. Extensive experiments on two real-world datasets show the superiority of ACENet compared with other state-of-the-art methods.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2021.3084513