MultiSlot ReRanker: A Generic Model-based Re-Ranking Framework in Recommendation Systems
This addresses the challenge of balancing multiple objectives in recommendation systems for users and platforms, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of optimizing relevance, diversity, and freshness in recommendation systems by proposing MultiSlot ReRanker, a generic model-based re-ranking framework, which achieved a lift of +6% to +10% offline AUC.
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.