EGEAN: An Exposure-Guided Embedding Alignment Network for Post-Click Conversion Estimation
This addresses estimation bias in online advertising systems, though it appears incremental as it builds on existing causal approaches for sample selection bias.
The paper tackles the problem of covariate shift in post-click conversion rate estimation for online advertising by proposing an Exposure-Guided Embedding Alignment Network (EGEAN) and a Parameter Varying Doubly Robust Estimator. Online A/B tests on the Meituan advertising system show the method significantly outperforms baseline models in CVR and GMV.
Accurate post-click conversion rate (CVR) estimation is crucial for online advertising systems. Despite significant advances in causal approaches designed to address the Sample Selection Bias problem, CVR estimation still faces challenges due to Covariate Shift. Given the intrinsic connection between the distribution of covariates in the click and non-click spaces, this study proposes an Exposure-Guided Embedding Alignment Network (EGEAN) to address estimation bias caused by covariate shift. Additionally, we propose a Parameter Varying Doubly Robust Estimator with steady-state control to handle small propensities better. Online A/B tests conducted on the Meituan advertising system demonstrate that our method significantly outperforms baseline models with respect to CVR and GMV, validating its effectiveness. Code is available: https://github.com/hydrogen-maker/EGEAN.