Ads Supply Personalization via Doubly Robust Learning

TL;DR

This paper introduces a scalable, doubly robust learning framework for personalized ad supply that improves long-term effect estimation and is suitable for large-scale social media platforms.

Contribution

It presents a novel, low-complexity framework utilizing doubly robust learning for better long-term ad supply personalization at industry scale.

Findings

Significant improvements in business metrics observed in offline and online tests.

Framework successfully deployed in live traffic of a major social media platform.

Enhanced accuracy in long-term treatment effect estimation.

Abstract

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.