Evolving Interest with Feature Co-action Network for CTR Prediction

Recently, many deep learning-based models have been successfully applied to click-through rate prediction. However, most previous models focus only on feature-level interactions between a single user behavior and the target item or only treat the user’s historical behavior as a sequence to uncover t...

Full description

Saved in:
Bibliographic Details
Published inData Science and Engineering Vol. 8; no. 4; pp. 344 - 356
Main Authors Yuan, Zhiyang, Zheng, Wenguang, Yang, Peilin, Hao, Qingbo, Xiao, Yingyuan
Format Journal Article
LanguageEnglish
Published Singapore Springer Nature Singapore 01.12.2023
Springer
Springer Nature B.V
SpringerOpen
Subjects
Algorithm Analysis and Problem Complexity
Artificial Intelligence
Behavior sequence
Chemistry and Earth Sciences
Computational linguistics
Computer Science
CTR prediction
Data Mining and Knowledge Discovery
Database Management
Deep learning
Evolution
Feature interaction
Language processing
Mineral industry
Mining industry
Natural language interfaces
Physics
Research Paper
Self-attention
Statistics for Engineering
Systems and Data Security
China
CTR prediction
Behavior sequence
Feature interaction
Self-attention
Online AccessGet full text

Cover

More Information
Summary:Recently, many deep learning-based models have been successfully applied to click-through rate prediction. However, most previous models focus only on feature-level interactions between a single user behavior and the target item or only treat the user’s historical behavior as a sequence to uncover the hidden interests behind it when mining user interests. This can lead to user interest that evolves over time dynamically being ignored or the interest shown by a single user’s behavior not being exploited. Based on the above problems, we propose evolving interest with feature co-action network (EIFCN). Specifically, we first design user dynamic interest network to treat the user’s historical behavior as a sequence of information, and tap into the user’s hidden interests over time. In this part, we use a multi-head self-attention mechanism to initially process the data and then pass it into the deep learning network. Then a feature co-action network is designed to mine the user’s single behavior and the displayed feature-level interactions of the target item. Experimental results show that the EIFCN model performs better than other models.
ISSN:2364-1185
2364-1541
DOI:10.1007/s41019-023-00217-8