A Large Scale Heterogeneous Treatment Effect Estimation Framework and Its Applications of Users' Journey at Snap
By: Jing Pan, Li Shi, Paul Lo
Potential Business Impact:
Finds best ways to show ads to each person.
Heterogeneous Treatment Effect (HTE) and Conditional Average Treatment Effect (CATE) models relax the assumption that treatment effects are the same for every user. We present a large scale industrial framework for estimating HTE using experimental data from hundreds of millions of Snapchat users. By combining results across many experiments, the framework uncovers latent user characteristics that were previously unmeasurable and produces stable treatment effect estimates at scale. We describe the core components that enabled this system, including experiment selection, base learner design, and incremental training. We also highlight two applications: user influenceability to ads and user sensitivity to ads. An online A/B test using influenceability scores for targeting showed an improvement on key business metrics that is more than six times larger than what is typically considered significant.
Similar Papers
Assumption-Lean Differential Variance Inference for Heterogeneous Treatment Effect Detection
Methodology
Tests if treatments work the same for everyone.
Reliable Selection of Heterogeneous Treatment Effect Estimators
Machine Learning (Stat)
Finds the best way to treat each person.
Evaluating and Testing for Actionable Treatment Effect Heterogeneity
Methodology
Shows if personalized medicine works better.