An RL agent that picks personalized weights for a linear ad ranking utility raised treated-segment CTR by 9.7% and CTR30 by 7.7% in Pinterest's production system.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest
An RL agent that picks personalized weights for a linear ad ranking utility raised treated-segment CTR by 9.7% and CTR30 by 7.7% in Pinterest's production system.