Time Matters: A Novel Real-Time Long- and Short-term User Interest Model for Click-Through Rate Prediction

TL;DR

This paper introduces a time-aware user interest modeling approach for CTR prediction that captures the dynamic evolution of user interests over time, improving prediction accuracy by considering periodic and time-point interest patterns.

Contribution

It proposes a novel method that models long- and short-term user interests based on temporal patterns, addressing limitations of previous methods that ignore interest-time correlation.

Findings

Outperforms state-of-the-art CTR prediction methods on public datasets

Effectively captures periodic and time-point interest patterns

Demonstrates industrial applicability with improved accuracy

Abstract

Click-Through Rate (CTR) prediction is a core task in online personalization platform. A key step for CTR prediction is to learn accurate user representation to capture their interests. Generally, the interest expressed by a user is time-variant, i.e., a user activates different interests at different time. However, most previous CTR prediction methods overlook the correlation between the activated interest and the occurrence time, resulting in what they actually learn is the mixture of the interests expressed by the user at all time, rather than the real-time interest at the certain prediction time. To capture the correlation between the activated interest and the occurrence time, in this paper we investigate users' interest evolution from the perspective of the whole time line and develop two regular patterns: periodic pattern and time-point pattern. Based on the two patterns, we propose a novel time-aware long- and short-term user interest modeling method to model users' dynamic interests at different time. Extensive experiments on public datasets as well as an industrial dataset verify the effectiveness of exploiting the two patterns and demonstrate the superiority of our proposed method compared with other state-of-the-art ones.