发表机构
Twitch Interactive; Amazon Prime Video（Twitch互动公司; 亚马逊Prime视频）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对直播推荐中用户行为稀疏延迟、数据有偏差的问题，提出延迟窗口、多模型架构、分段感知定向及MMoE集成的多目标排序方案，经测试可提升DAV、ARPU等指标，且在Twitch上也有效。
AI 中文摘要
娱乐直播服务的推荐系统面临的最具挑战性问题之一是用户行为稀疏且存在延迟，交互数据对不同用户群体存在偏差。与用户行为遵循线性序列的电商应用不同，直播观众会同时进行观看、聊天、关注、消费等多种行为，每种行为的延迟各不相同。我们通过三项核心贡献解决这些挑战：1）延迟窗口方法，将反馈收集范围扩展至即时响应之外；2）多模型架构，结合新鲜与延迟信号，以及分段感知定向模块，针对用户生命周期的不同阶段优化排序得分；3）多门混合专家（MMoE）集成，联合建模相关目标，同时相比独立模型减少41.9%的模型参数。在线A/B测试显示出显著提升，包括日活跃观众（DAV）增长0.09%，每年新增数百万活跃观众日，高参与度观众的上限人均收入（ARPU）增长0.56%。观众分段定向为新用户和低参与度观众额外实现了0.15%的DAV提升，而MMoE增强则带来了0.08%的整体DAV增长和0.27%的新增关注。所提系统以低延迟处理排序请求，为不同用户群体平衡多个业务目标提供了可扩展的方法。此外，我们在Twitch移动直播流上测试了多模型架构，实现了用户-频道正向交互（点击、关注、点赞）增长1.12%，证明了其在主要用例之外的适用性。
英文摘要
One of the most challenging problems entertainment live-streaming services face in recommendation systems is that user behaviors are sparse and delayed, and interaction data exhibits bias for different user segments. Unlike e-commerce applications where user actions follow linear sequences, live-streaming viewers engage in multiple concurrent behaviors of watching, chatting, following, and spending, each occurring with varying delays. We address these challenges through three key contributions: 1) a delayed window approach that extends feedback collection beyond immediate responses, 2) a multi-model architecture that combines fresh and delayed signals, and a segment-aware targeting module that optimizes ranking scores differently across user lifecycle stages, and 3) Multi-gate Mixture-of-Experts (MMoE) integration that jointly models correlated targets while reducing model parameters by 41.9% compared to independent models. Online A/B testing demonstrates significant improvements, including a +0.09% increase in Daily Active Viewers (DAV), generating millions more annual active viewer days, and +0.56% increase in highly engaged viewers' capped Average Revenue Per User (ARPU). Viewer-segment targeting achieved an additional +0.15% DAV improvement for newer and less engaged viewers, while MMoE enhancement added +0.08% overall DAV and +0.27% new follows. The proposed system processes ranking requests with low latency, providing a scalable approach for balancing multiple business objectives across diverse user populations. In addition, we tested the multi-model architecture on the Twitch mobile live feed and achieved a +1.12% increase in positive user-channel interactions (clicks, follows, and likes), demonstrating applicability beyond the primary use case.
Comments9 pages, 3 figures. Accepted to the Industry Track of the 20th ACM Conference on Recommender Systems (RecSys 2026)
