Unbiased Delayed Feedback Label Correction for Conversion Rate Prediction

TL;DR

This paper introduces ULC, a novel label correction framework for conversion rate prediction that uses an auxiliary model and counterfactual labeling to address delayed feedback issues, improving accuracy over existing methods.

Contribution

The paper proposes an unbiased label correction method using auxiliary models and counterfactual data, advancing the handling of delayed feedback in conversion rate prediction.

Findings

ULC effectively alleviates delayed feedback bias.

ULC outperforms previous state-of-the-art methods.

Theoretical proof confirms unbiasedness of the label-corrected loss.

Abstract

Conversion rate prediction is critical to many online applications such as digital display advertising. To capture dynamic data distribution, industrial systems often require retraining models on recent data daily or weekly. However, the delay of conversion behavior usually leads to incorrect labeling, which is called delayed feedback problem. Existing work may fail to introduce the correct information about false negative samples due to data sparsity and dynamic data distribution. To directly introduce the correct feedback label information, we propose an Unbiased delayed feedback Label Correction framework (ULC), which uses an auxiliary model to correct labels for observed negative feedback samples. Firstly, we theoretically prove that the label-corrected loss is an unbiased estimate of the oracle loss using true labels. Then, as there are no ready training data for label correction, counterfactual labeling is used to construct artificial training data. Furthermore, since counterfactual labeling utilizes only partial training data, we design an embedding-based alternative training method to enhance performance. Comparative experiments on both public and private datasets and detailed analyses show that our proposed approach effectively alleviates the delayed feedback problem and consistently outperforms the previous state-of-the-art methods.