MultiSlot ReRanker: A Generic Model-based Re-Ranking Framework in Recommendation Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929207547789312 |
|---|---|
| author | Xiao, Qiang Charles Muralidharan, Ajith Tiwana, Birjodh Jia, Johnson Borisyuk, Fedor Gupta, Aman Woodard, Dawn |
| author_facet | Xiao, Qiang Charles Muralidharan, Ajith Tiwana, Birjodh Jia, Johnson Borisyuk, Fedor Gupta, Aman Woodard, Dawn |
| contents | In this paper, we propose a generic model-based re-ranking framework, MultiSlot ReRanker, which simultaneously optimizes relevance, diversity, and freshness. Specifically, our Sequential Greedy Algorithm (SGA) is efficient enough (linear time complexity) for large-scale production recommendation engines. It achieved a lift of $+6\%$ to $ +10\%$ offline Area Under the receiver operating characteristic Curve (AUC) which is mainly due to explicitly modeling mutual influences among items of a list, and leveraging the second pass ranking scores of multiple objectives. In addition, we have generalized the offline replay theory to multi-slot re-ranking scenarios, with trade-offs among multiple objectives. The offline replay results can be further improved by Pareto Optimality. Moreover, we've built a multi-slot re-ranking simulator based on OpenAI Gym integrated with the Ray framework. It can be easily configured for different assumptions to quickly benchmark both reinforcement learning and supervised learning algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_06293 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MultiSlot ReRanker: A Generic Model-based Re-Ranking Framework in Recommendation Systems Xiao, Qiang Charles Muralidharan, Ajith Tiwana, Birjodh Jia, Johnson Borisyuk, Fedor Gupta, Aman Woodard, Dawn Artificial Intelligence Information Retrieval In this paper, we propose a generic model-based re-ranking framework, MultiSlot ReRanker, which simultaneously optimizes relevance, diversity, and freshness. Specifically, our Sequential Greedy Algorithm (SGA) is efficient enough (linear time complexity) for large-scale production recommendation engines. It achieved a lift of $+6\%$ to $ +10\%$ offline Area Under the receiver operating characteristic Curve (AUC) which is mainly due to explicitly modeling mutual influences among items of a list, and leveraging the second pass ranking scores of multiple objectives. In addition, we have generalized the offline replay theory to multi-slot re-ranking scenarios, with trade-offs among multiple objectives. The offline replay results can be further improved by Pareto Optimality. Moreover, we've built a multi-slot re-ranking simulator based on OpenAI Gym integrated with the Ray framework. It can be easily configured for different assumptions to quickly benchmark both reinforcement learning and supervised learning algorithms. |
| title | MultiSlot ReRanker: A Generic Model-based Re-Ranking Framework in Recommendation Systems |
| topic | Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2401.06293 |