2024/09/29 by M. A. Radwan, Himaghna Bhattacharjee, Radwan, Mohamed A. +11 · 2 citations
Business, Management and Accounting · Social Sciences · #Consumer Market Behavior and Pricing #Digital Marketing and Social Media #Computational and Text Analysis Methods
paper · pdf · doi:10.48550/arxiv.2409.19824
We propose a domain-adapted reward model that works alongside an Offline A/B testing system for evaluating ranking models. This approach effectively measures reward for ranking model changes in large-scale Ads recommender systems, where model-free methods like IPS are not feasible. Our experiments demonstrate that the proposed technique outperforms both the vanilla IPS method and approaches using non-generalized reward models.