Modeling User Retention through Generative Flow Networks
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_ | 1866917689213059072 |
|---|---|
| author | Liu, Ziru Liu, Shuchang Yang, Bin Xue, Zhenghai Cai, Qingpeng Zhao, Xiangyu Zhang, Zijian Hu, Lantao Li, Han Jiang, Peng |
| author_facet | Liu, Ziru Liu, Shuchang Yang, Bin Xue, Zhenghai Cai, Qingpeng Zhao, Xiangyu Zhang, Zijian Hu, Lantao Li, Han Jiang, Peng |
| contents | Recommender systems aim to fulfill the user's daily demands. While most existing research focuses on maximizing the user's engagement with the system, it has recently been pointed out that how frequently the users come back for the service also reflects the quality and stability of recommendations. However, optimizing this user retention behavior is non-trivial and poses several challenges including the intractable leave-and-return user activities, the sparse and delayed signal, and the uncertain relations between users' retention and their immediate feedback towards each item in the recommendation list. In this work, we regard the retention signal as an overall estimation of the user's end-of-session satisfaction and propose to estimate this signal through a probabilistic flow. This flow-based modeling technique can back-propagate the retention reward towards each recommended item in the user session, and we show that the flow combined with traditional learning-to-rank objectives eventually optimizes a non-discounted cumulative reward for both immediate user feedback and user retention. We verify the effectiveness of our method through both offline empirical studies on two public datasets and online A/B tests in an industrial platform. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06043 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Modeling User Retention through Generative Flow Networks Liu, Ziru Liu, Shuchang Yang, Bin Xue, Zhenghai Cai, Qingpeng Zhao, Xiangyu Zhang, Zijian Hu, Lantao Li, Han Jiang, Peng Information Retrieval Recommender systems aim to fulfill the user's daily demands. While most existing research focuses on maximizing the user's engagement with the system, it has recently been pointed out that how frequently the users come back for the service also reflects the quality and stability of recommendations. However, optimizing this user retention behavior is non-trivial and poses several challenges including the intractable leave-and-return user activities, the sparse and delayed signal, and the uncertain relations between users' retention and their immediate feedback towards each item in the recommendation list. In this work, we regard the retention signal as an overall estimation of the user's end-of-session satisfaction and propose to estimate this signal through a probabilistic flow. This flow-based modeling technique can back-propagate the retention reward towards each recommended item in the user session, and we show that the flow combined with traditional learning-to-rank objectives eventually optimizes a non-discounted cumulative reward for both immediate user feedback and user retention. We verify the effectiveness of our method through both offline empirical studies on two public datasets and online A/B tests in an industrial platform. |
| title | Modeling User Retention through Generative Flow Networks |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2406.06043 |