Modeling Users' Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search

TL;DR

This paper introduces RACP, a neural model that captures both intra-page context and inter-page interest evolution for improved click-through rate prediction in e-commerce search, outperforming existing methods.

Contribution

It proposes a novel context-aware user behavior modeling approach using page-wise feedback sequences and a recurrent attention mechanism, enhancing CTR prediction accuracy.

Findings

RACP outperforms baseline models on public datasets.

The model effectively captures intra-page and inter-page user interests.

Experimental results demonstrate significant improvements in prediction accuracy.

Abstract

Modeling user's historical feedback is essential for Click-Through Rate Prediction in personalized search and recommendation. Existing methods usually only model users' positive feedback information such as click sequences which neglects the context information of the feedback. In this paper, we propose a new perspective for context-aware users' behavior modeling by including the whole page-wisely exposed products and the corresponding feedback as contextualized page-wise feedback sequence. The intra-page context information and inter-page interest evolution can be captured to learn more specific user preference. We design a novel neural ranking model RACP(i.e., Recurrent Attention over Contextualized Page sequence), which utilizes page-context aware attention to model the intra-page context. A recurrent attention process is used to model the cross-page interest convergence evolution as denoising the interest in the previous pages. Experiments on public and real-world industrial datasets verify our model's effectiveness.