Confidence-Aware Multi-Field Model Calibration

arXiv:2402.17655v1 Announce Type: new
Abstract: Accurately predicting the probabilities of user feedback, such as clicks and conversions, is critical for ad ranking and bidding. However, there often exist unwanted mismatches between predicted probabilities and true likelihoods due to the shift of data distributions and intrinsic model biases. Calibration aims to address this issue by post-processing model predictions, and field-aware calibration can adjust model output on different feature field values to satisfy fine-grained advertising demands. Unfortunately, the observed samples corresponding to …

abstract arxiv biases bidding confidence cs.lg data feedback intrinsic issue post-processing processing ranking shift true type user feedback