Deep Time-Stream Framework for Click-Through Rate Prediction by Tracking Interest Evolution

TL;DR

This paper introduces a Deep Time-Stream framework using neural ODEs to dynamically model user interest evolution over time, significantly improving CTR prediction accuracy in industrial applications.

Contribution

It proposes a novel neural ODE-based framework that captures continuous interest evolution and can be integrated into existing CTR models without modifications.

Findings

Achieves superior performance on public and industry datasets.

Effectively models interest dynamics over time.

Enhances CTR prediction accuracy.

Abstract

Click-through rate (CTR) prediction is an essential task in industrial applications such as video recommendation. Recently, deep learning models have been proposed to learn the representation of users' overall interests, while ignoring the fact that interests may dynamically change over time. We argue that it is necessary to consider the continuous-time information in CTR models to track user interest trend from rich historical behaviors. In this paper, we propose a novel Deep Time-Stream framework (DTS) which introduces the time information by an ordinary differential equations (ODE). DTS continuously models the evolution of interests using a neural network, and thus is able to tackle the challenge of dynamically representing users' interests based on their historical behaviors. In addition, our framework can be seamlessly applied to any existing deep CTR models by leveraging the additional Time-Stream Module, while no changes are made to the original CTR models. Experiments on public dataset as well as real industry dataset with billions of samples demonstrate the effectiveness of proposed approaches, which achieve superior performance compared with existing methods.