LiveForesighter: Generating Future Information for Live-Streaming Recommendations at Kuaishou
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915144723857408 |
|---|---|
| author | Lu, Yucheng Cao, Jiangxia Kuan, Xu Cheng, Wei Jiang, Wei Zhang, Jiaming Shuang, Yang Zhaojie, Liu Hong, Liyin |
| author_facet | Lu, Yucheng Cao, Jiangxia Kuan, Xu Cheng, Wei Jiang, Wei Zhang, Jiaming Shuang, Yang Zhaojie, Liu Hong, Liyin |
| contents | 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? |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06557 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LiveForesighter: Generating Future Information for Live-Streaming Recommendations at Kuaishou Lu, Yucheng Cao, Jiangxia Kuan, Xu Cheng, Wei Jiang, Wei Zhang, Jiaming Shuang, Yang Zhaojie, Liu Hong, Liyin Information Retrieval 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? |
| title | LiveForesighter: Generating Future Information for Live-Streaming Recommendations at Kuaishou |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2502.06557 |