Time-aligned Exposure-enhanced Model for Click-Through Rate Prediction

TL;DR

This paper introduces TEM4CTR, a novel CTR prediction framework that aligns user behavior sequences temporally and leverages auxiliary feedback to improve prediction accuracy, addressing key challenges in sequence modeling.

Contribution

The paper proposes TEM4CTR, a framework that achieves temporal alignment and enhances feedback utilization through a representation projection mechanism for better CTR prediction.

Findings

TEM4CTR outperforms existing models on public datasets.

Temporal alignment improves multi-feedback modeling accuracy.

Representation projection mitigates negative effects of irrelevant feedback.

Abstract

Click-Through Rate (CTR) prediction, crucial in applications like recommender systems and online advertising, involves ranking items based on the likelihood of user clicks. User behavior sequence modeling has marked progress in CTR prediction, which extracts users' latent interests from their historical behavior sequences to facilitate accurate CTR prediction. Recent research explores using implicit feedback sequences, like unclicked records, to extract diverse user interests. However, these methods encounter key challenges: 1) temporal misalignment due to disparate sequence time ranges and 2) the lack of fine-grained interaction among feedback sequences. To address these challenges, we propose a novel framework called TEM4CTR, which ensures temporal alignment among sequences while leveraging auxiliary feedback information to enhance click behavior at the item level through a representation projection mechanism. Moreover, this projection-based information transfer module can effectively alleviate the negative impact of irrelevant or even potentially detrimental components of the auxiliary feedback information on the learning process of click behavior. Comprehensive experiments on public and industrial datasets confirm the superiority and effectiveness of TEM4CTR, showcasing the significance of temporal alignment in multi-feedback modeling.