Posterior Probability Matters
Authors:
Open Access
- 6 July 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2645-2649
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 aims 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.Keywords
This publication has 14 references indexed in Scilit:
- Field-aware Calibration: A Simple and Empirically Strong Method for Reliable Probabilistic Predictions2020
- Calibration2018
- Deep Interest Network for Click-Through Rate Prediction2018
- Entire Space Multi-Task Model2018
- Wide & Deep Learning for Recommender Systems2016
- Deep Neural Networks for YouTube Recommendations2016
- Ups and Downs2016
- Practical Lessons from Predicting Clicks on Ads at Facebook2014
- Ad click prediction2013
- Transforming classifier scores into accurate multiclass probability estimates2002