Simple but Efficient: A Multi-Scenario Nearline Retrieval Framework for Recommendation on Taobao
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_ | 1866929450615046144 |
|---|---|
| author | Ma, Yingcai Wang, Ziyang Yan, Yuliang Wu, Jian Jiang, Yuning Li, Longbin Chen, Wen Huang, Jianhang |
| author_facet | Ma, Yingcai Wang, Ziyang Yan, Yuliang Wu, Jian Jiang, Yuning Li, Longbin Chen, Wen Huang, Jianhang |
| contents | In recommendation systems, the matching stage is becoming increasingly critical, serving as the upper limit for the entire recommendation process. Recently, some studies have started to explore the use of multi-scenario information for recommendations, such as model-based and data-based approaches. However, the matching stage faces significant challenges due to the need for ultra-large-scale retrieval and meeting low latency requirements. As a result, the methods applied at this stage (collaborative filtering and two-tower models) are often designed to be lightweight, hindering the full utilization of extensive information. On the other hand, the ranking stage features the most sophisticated models with the strongest scoring capabilities, but due to the limited screen size of mobile devices, most of the ranked results may not gain exposure or be displayed. In this paper, we introduce an innovative multi-scenario nearline retrieval framework. It operates by harnessing ranking logs from various scenarios through Flink, allowing us to incorporate finely ranked results from other scenarios into our matching stage in near real-time. Besides, we propose a streaming scoring module, which selects a crucial subset from the candidate pool. Implemented on the "Guess You Like" (homepage of the Taobao APP), China's premier e-commerce platform, our method has shown substantial improvements-most notably, a 5% uptick in product transactions. Furthermore, the proposed approach is not only model-free but also highly efficient, suggesting it can be quickly implemented in diverse scenarios and demonstrate promising performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_00247 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Simple but Efficient: A Multi-Scenario Nearline Retrieval Framework for Recommendation on Taobao Ma, Yingcai Wang, Ziyang Yan, Yuliang Wu, Jian Jiang, Yuning Li, Longbin Chen, Wen Huang, Jianhang Information Retrieval In recommendation systems, the matching stage is becoming increasingly critical, serving as the upper limit for the entire recommendation process. Recently, some studies have started to explore the use of multi-scenario information for recommendations, such as model-based and data-based approaches. However, the matching stage faces significant challenges due to the need for ultra-large-scale retrieval and meeting low latency requirements. As a result, the methods applied at this stage (collaborative filtering and two-tower models) are often designed to be lightweight, hindering the full utilization of extensive information. On the other hand, the ranking stage features the most sophisticated models with the strongest scoring capabilities, but due to the limited screen size of mobile devices, most of the ranked results may not gain exposure or be displayed. In this paper, we introduce an innovative multi-scenario nearline retrieval framework. It operates by harnessing ranking logs from various scenarios through Flink, allowing us to incorporate finely ranked results from other scenarios into our matching stage in near real-time. Besides, we propose a streaming scoring module, which selects a crucial subset from the candidate pool. Implemented on the "Guess You Like" (homepage of the Taobao APP), China's premier e-commerce platform, our method has shown substantial improvements-most notably, a 5% uptick in product transactions. Furthermore, the proposed approach is not only model-free but also highly efficient, suggesting it can be quickly implemented in diverse scenarios and demonstrate promising performance. |
| title | Simple but Efficient: A Multi-Scenario Nearline Retrieval Framework for Recommendation on Taobao |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2408.00247 |