English

MultiSlot ReRanker: A Generic Model-based Re-Ranking Framework in Recommendation Systems

Artificial Intelligence 2024-01-15 v1 Information Retrieval

Abstract

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%+6\% to +10% +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.

Keywords

Cite

@article{arxiv.2401.06293,
  title  = {MultiSlot ReRanker: A Generic Model-based Re-Ranking Framework in Recommendation Systems},
  author = {Qiang Charles Xiao and Ajith Muralidharan and Birjodh Tiwana and Johnson Jia and Fedor Borisyuk and Aman Gupta and Dawn Woodard},
  journal= {arXiv preprint arXiv:2401.06293},
  year   = {2024}
}

Comments

10 pages

R2 v1 2026-06-28T14:14:49.508Z