Item Level Exploration Traffic Allocation in Large-scale Recommendation Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916736854392832 |
|---|---|
| author | Wang, Dong Jiao, Junyi Bhadury, Arnab Zhang, Yaping Gao, Mingyan |
| author_facet | Wang, Dong Jiao, Junyi Bhadury, Arnab Zhang, Yaping Gao, Mingyan |
| contents | This paper contributes to addressing the item cold start problem in large-scale recommender systems, focusing on how to efficiently gain initial visibility for newly ingested content. We propose an exploration system designed to efficiently allocate impressions to these fresh items. Our approach leverages a learned probabilistic model to predict an item's discoverability, which then informs a scalable and adaptive traffic allocation strategy. This system intelligently distributes exploration budgets, optimizing for the long-term benefit of the recommendation platform. The impact is a demonstrably more efficient cold-start process, leading to a significant increase in the discoverability of new content and ultimately enriching the item corpus available for exploitation, as evidenced by its successful deployment in a large-scale production environment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09033 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Item Level Exploration Traffic Allocation in Large-scale Recommendation Systems Wang, Dong Jiao, Junyi Bhadury, Arnab Zhang, Yaping Gao, Mingyan Information Retrieval This paper contributes to addressing the item cold start problem in large-scale recommender systems, focusing on how to efficiently gain initial visibility for newly ingested content. We propose an exploration system designed to efficiently allocate impressions to these fresh items. Our approach leverages a learned probabilistic model to predict an item's discoverability, which then informs a scalable and adaptive traffic allocation strategy. This system intelligently distributes exploration budgets, optimizing for the long-term benefit of the recommendation platform. The impact is a demonstrably more efficient cold-start process, leading to a significant increase in the discoverability of new content and ultimately enriching the item corpus available for exploitation, as evidenced by its successful deployment in a large-scale production environment. |
| title | Item Level Exploration Traffic Allocation in Large-scale Recommendation Systems |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2505.09033 |