预测直播未来内容吸引力，提升实时推荐精准度
LiveForesighter: Generating Future Information for Live-Streaming Recommendations at Kuaishou
- 基于当前直播状态预测未来10分钟内用户兴趣
- 在快手真实数据上提升点击率和观看时长
- 适合做直播推荐系统优化的研究者与工程师
直播作为一种新型媒体形式，近年来迅速发展，但其动态变化的内容和用户需长时间观看（>10分钟）才能产生有价值行为（如送礼物、购买商品）的特性，给实时推荐带来挑战。本文提出LiveForesighter，旨在根据当前直播状态预测未来一段时间内用户的兴趣点，解决‘如何在当前时刻发现用户未来可能感兴趣的直播’这一关键问题。模型结合实时互动信号与内容演化趋势，实现对直播未来吸引力的动态建模。在快手真实数据集上的实验表明，该方法显著优于基线模型，在点击率和平均观看时长上均有明显提升。
原文摘要 · Abstract (English)
Live-streaming, as a new-generation media to connect users and authors, has attracted a lot of attention and experienced rapid growth in recent years. Compared with the content-static short-video recommendation, the live-streaming recommendation faces more challenges in giving our users a satisfactory experience: (1) Live-streaming content is dynamically ever-changing along time. (2) valuable behaviors (e.g., send digital-gift, buy products) always require users to watch for a long-time (>10 min). Combining the two attributes, here raising a challenging question for live-streaming recommendation: How to discover the live-streamings that the content user is interested in at the current moment, and further a period in the future?
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。