Interest Clock: Time Perception in Real-Time Streaming Recommendation System

TL;DR

Interest Clock is a novel time perception method for streaming recommendation systems that encodes user preferences into a clock-based embedding, improving recommendation accuracy and user engagement.

Contribution

The paper introduces the Interest Clock method, a universal approach to model time-aware user preferences in streaming recommendation systems, with successful deployment in industry.

Findings

Online A/B tests showed +0.509% in user active days.

Online A/B tests showed +0.758% in app duration.

Offline experiments confirmed effectiveness.

Abstract

User preferences follow a dynamic pattern over a day, e.g., at 8 am, a user might prefer to read news, while at 8 pm, they might prefer to watch movies. Time modeling aims to enable recommendation systems to perceive time changes to capture users' dynamic preferences over time, which is an important and challenging problem in recommendation systems. Especially, streaming recommendation systems in the industry, with only available samples of the current moment, present greater challenges for time modeling. There is still a lack of effective time modeling methods for streaming recommendation systems. In this paper, we propose an effective and universal method Interest Clock to perceive time information in recommendation systems. Interest Clock first encodes users' time-aware preferences into a clock (hour-level personalized features) and then uses Gaussian distribution to smooth and aggregate them into the final interest clock embedding according to the current time for the final prediction. By arming base models with Interest Clock, we conduct online A/B tests, obtaining +0.509% and +0.758% improvements on user active days and app duration respectively. Besides, the extended offline experiments show improvements as well. Interest Clock has been deployed on Douyin Music App.