Conditional Quantile Estimation for Uncertain Watch Time in Short-Video Recommendation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909613536837632 |
|---|---|
| author | Lin, Chengzhi Liu, Shuchang Wang, Chuyuan Liu, Yongqi |
| author_facet | Lin, Chengzhi Liu, Shuchang Wang, Chuyuan Liu, Yongqi |
| contents | Accurately predicting watch time is crucial for optimizing recommendations and user experience in short video platforms. However, existing methods that estimate a single average watch time often fail to capture the inherent uncertainty in user engagement patterns. In this paper, we propose Conditional Quantile Estimation (CQE) to model the entire conditional distribution of watch time. Using quantile regression, CQE characterizes the complex watch-time distribution for each user-video pair, providing a flexible and comprehensive approach to understanding user behavior. We further design multiple strategies to combine the quantile estimates, adapting to different recommendation scenarios and user preferences. Extensive offline experiments and online A/B tests demonstrate the superiority of CQE in watch-time prediction and user engagement modeling. Specifically, deploying CQE online on a large-scale platform with hundreds of millions of daily active users has led to substantial gains in key evaluation metrics, including active days, engagement time, and video views. These results highlight the practical impact of our proposed approach in enhancing the user experience and overall performance of the short video recommendation system. The code will be released https://github.com/justopit/CQE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_12223 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Conditional Quantile Estimation for Uncertain Watch Time in Short-Video Recommendation Lin, Chengzhi Liu, Shuchang Wang, Chuyuan Liu, Yongqi Machine Learning Artificial Intelligence Accurately predicting watch time is crucial for optimizing recommendations and user experience in short video platforms. However, existing methods that estimate a single average watch time often fail to capture the inherent uncertainty in user engagement patterns. In this paper, we propose Conditional Quantile Estimation (CQE) to model the entire conditional distribution of watch time. Using quantile regression, CQE characterizes the complex watch-time distribution for each user-video pair, providing a flexible and comprehensive approach to understanding user behavior. We further design multiple strategies to combine the quantile estimates, adapting to different recommendation scenarios and user preferences. Extensive offline experiments and online A/B tests demonstrate the superiority of CQE in watch-time prediction and user engagement modeling. Specifically, deploying CQE online on a large-scale platform with hundreds of millions of daily active users has led to substantial gains in key evaluation metrics, including active days, engagement time, and video views. These results highlight the practical impact of our proposed approach in enhancing the user experience and overall performance of the short video recommendation system. The code will be released https://github.com/justopit/CQE. |
| title | Conditional Quantile Estimation for Uncertain Watch Time in Short-Video Recommendation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2407.12223 |