EGEAN: An Exposure-Guided Embedding Alignment Network for Post-Click Conversion Estimation

TL;DR

This paper introduces EGEAN, a novel neural network model that aligns embeddings guided by exposure data to improve post-click conversion rate estimation, effectively addressing covariate shift and bias issues in online advertising.

Contribution

The study proposes EGEAN, a new exposure-guided embedding alignment network, and a parameter varying doubly robust estimator to enhance CVR estimation under covariate shift conditions.

Findings

EGEAN significantly outperforms baseline models in CVR and GMV metrics.

The method effectively mitigates covariate shift bias in online advertising.

Online A/B tests validate the model's practical effectiveness.

Abstract

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.