Ads Supply Personalization via Doubly Robust Learning
Not on the map. Why?
Abstract (arXiv)
Ads supply personalization aims to balance the revenue and user engagement, two long-term objectives in social media ads, by tailoring the ad quantity and density. In the industry-scale system, the challenge for ads supply lies in modeling the counterfactual effects of a conservative supply treatment (e.g., a small density change) over an extended duration. In this paper, we present a streamlined framework for personalized ad supply. This framework optimally utilizes information from data collection policies through the doubly robust learning. Consequently, it significantly improves the accuracy of long-term treatment effect estimates. Additionally, its low-complexity design not only results in computational cost savings compared to existing methods, but also makes it scalable for billion-scale applications. Through both offline experiments and online production tests, the framework consistently demonstrated significant improvements in top-line business metrics over months. The framework has been fully deployed to live traffic in one of the world's largest social media platforms.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 34 references that are in the map. First posted on arXiv 29 Sep 2024.
Builds on
16 of 34 references.
References · 16
- 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 478
- 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 410
- 2016Learning Representations for Counterfactual Inferencecited by 329
- 2019Adapting Neural Networks for the Estimation of Treatment Effectscited by 287
- 2015Recursive Partitioning for Heterogeneous Causal Effectscited by 255
- 2020CausalML: Python Package for Causal Machine Learningcited by 74
- 2018Perfect Match: A Simple Method for Learning Representations For Counterfactual Inference With Neural Networkscited by 56
- 2019DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systemscited by 44
- 2017Uplift Modeling with Multiple Treatments and General Response Typescited by 41
- 2017Deep Counterfactual Networks with Propensity-Dropoutcited by 30
- 2023Explicit Feature Interaction-aware Uplift Network for Online Marketingcited by 25
- 2021Cross DQN: Cross Deep Q Network for Ads Allocation in Feedcited by 19
4 more
- 2022ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actorcited by 10
- 2022Deep Page-Level Interest Network in Reinforcement Learning for Ads Allocationcited by 8
- 2021Blending Advertising with Organic Content in E-Commerce: A Virtual Bids Optimization Approachcited by 5
- 2022Hybrid Transfer in Deep Reinforcement Learning for Ads Allocationcited by 5
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.