Posterior Probability Matters: Doubly-Adaptive Calibration for Neural Predictions in Online Advertising

TL;DR

This paper introduces AdaCalib, a doubly-adaptive calibration method for neural predictions in online advertising, which improves probabilistic accuracy by leveraging posterior statistics and field-specific adjustments, leading to better online performance.

Contribution

The paper proposes AdaCalib, a novel calibration technique that adaptively adjusts predictions using posterior information and field-specific mechanisms, enhancing calibration accuracy in online ad systems.

Findings

AdaCalib significantly improves calibration performance.

Online deployment shows AdaCalib outperforms previous methods.

Field-adaptive calibration enhances posterior probability accuracy.

Abstract

Predicting user response probabilities is vital for ad ranking and bidding. We hope that predictive models can produce accurate probabilistic predictions that reflect true likelihoods. Calibration techniques aim to post-process model predictions to posterior probabilities. Field-level calibration -- which performs calibration w.r.t. to a specific field value -- is fine-grained and more practical. In this paper we propose a doubly-adaptive approach AdaCalib. It learns an isotonic function family to calibrate model predictions with the guidance of posterior statistics, and field-adaptive mechanisms are designed to ensure that the posterior is appropriate for the field value to be calibrated. Experiments verify that AdaCalib achieves significant improvement on calibration performance. It has been deployed online and beats previous approach.