A General Framework for Debiasing in CTR Prediction
This addresses the limitation of existing debiasing methods that cannot handle complex scenarios in CTR prediction, offering a more versatile solution for applications such as search and recommendation systems.
The paper tackles the problem of debiasing in click-through rate (CTR) prediction by proposing a general framework that avoids oversimplified assumptions about click probability, achieving considerable improvements in scenarios like query auto completion and route recommendation, with consistent gains in online experiments.
Most of the existing methods for debaising in click-through rate (CTR) prediction depend on an oversimplified assumption, i.e., the click probability is the product of observation probability and relevance probability. However, since there is a complicated interplay between these two probabilities, these methods cannot be applied to other scenarios, e.g. query auto completion (QAC) and route recommendation. We propose a general debiasing framework without simplifying the relationships between variables, which can handle all scenarios in CTR prediction. Simulation experiments show that: under the simplest scenario, our method maintains a similar AUC with the state-of-the-art methods; in other scenarios, our method achieves considerable improvements compared with existing methods. Meanwhile, in online experiments, the framework also gains significant improvements consistently.