Moment&Cross: Next-Generation Real-Time Cross-Domain CTR Prediction for Live-Streaming Recommendation at Kuaishou

TL;DR

This paper introduces Moment&Cross, a real-time cross-domain CTR prediction framework designed for live-streaming recommendations at Kuaishou, addressing challenges of data imbalance, content unpredictability, and delayed feedback.

Contribution

The paper proposes a novel moment-aware and cross-domain learning approach to improve live-streaming CTR prediction by leveraging short-video behaviors and real-time data.

Findings

Enhanced CTR prediction accuracy in live-streaming scenarios

Effective handling of data imbalance between short-video and live-streaming

Improved recommendation timing and user engagement

Abstract

Kuaishou, is one of the largest short-video and live-streaming platform, compared with short-video recommendations, live-streaming recommendation is more complex because of: (1) temporarily-alive to distribution, (2) user may watch for a long time with feedback delay, (3) content is unpredictable and changes over time. Actually, even if a user is interested in the live-streaming author, it still may be an negative watching (e.g., short-view < 3s) since the real-time content is not attractive enough. Therefore, for live-streaming recommendation, there exists a challenging task: how do we recommend the live-streaming at right moment for users? Additionally, our platform's major exposure content is short short-video, and the amount of exposed short-video is 9x more than exposed live-streaming. Thus users will leave more behaviors on short-videos, which leads to a serious data imbalance problem making the live-streaming data could not fully reflect user interests. In such case, there raises another challenging task: how do we utilize users' short-video behaviors to make live-streaming recommendation better?