What type of study is this?

This is a Quantitative Study study.

Periodic Graph Neural Networks for Click-Through Rate Prediction in Online Advertising

View Full Paper

Ask AI

Bookmark

Authors

This paper demonstrates improved click-through rate prediction using periodic patterns in user-ad interactions, suggesting new avenues for modeling.

PGNN significantly enhances click-through rate prediction by integrating periodic patterns in user behavior.
Experiments show PGNN outperforms the strongest baseline models by achieving a 0.01 to 0.02 increase in AUC and Logloss.
The model employs periodic graph representations to capture dynamic user-ad interactions effectively.
Findings highlight the importance of considering periodic behavior in advancing advertising model performance.

Zhai et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

This paper demonstrates improved click-through rate prediction using periodic patterns in user-ad interactions, suggesting new avenues for modeling.