AdaCalib: Posterior-Guided Feature-Adaptive Calibration Model for Online Advertising

AdaCalib is a posterior‑guided feature‑adaptive calibration model for online advertising that learns per‑feature piecewise‑linear calibration functions via a deep neural network with adaptive bucketing, improving probability estimates and ranking, achieving lower Field‑RCE, higher AUC, and a 5% CVR lift in live tests.

Calibrationdeep neural networksfeature adaptation

0 likes · 19 min read

AdaCalib: Posterior-Guided Feature-Adaptive Calibration Model for Online Advertising

Baidu Geek Talk

Aug 16, 2021 · Artificial Intelligence

End-to-End Consistency Testing Solution for Click-Through Rate Models in Advertising Systems

The article describes Baidu’s end-to-end consistency testing framework for advertising click-through-rate models, which uses a five-stream verification pipeline and six implementation phases to compare Q-values across feature extraction, table conversions, and DNN computation, enabling precise detection and localization of data and model inconsistencies in production.

BaiduCTR predictionMachine learning testing

0 likes · 17 min read

End-to-End Consistency Testing Solution for Click-Through Rate Models in Advertising Systems

Alibaba Cloud Developer

Oct 31, 2018 · Artificial Intelligence

How Deep‑FSMN and Low Frame Rate Accelerate Speech Recognition

This article introduces the Deep‑FSMN (DFSMN) architecture and its integration with low‑frame‑rate (LFR) processing, showing how the combined LFR‑DFSMN acoustic model achieves higher accuracy, smaller model size, faster training, and lower latency than traditional BLSTM‑based speech recognition systems on both English and Chinese large‑vocabulary tasks.

AIDFSMNacoustic modeling

0 likes · 12 min read

How Deep‑FSMN and Low Frame Rate Accelerate Speech Recognition

iQIYI Technical Product Team

Nov 10, 2017 · Artificial Intelligence

iQIYI Recommendation System: Architecture, Model Evolution, and Ranking Strategies

The iQIYI recommendation system combines a two‑stage pipeline of recall and ranking, evolving from logistic regression to a GBDT‑FM‑DNN ensemble, using online feature storage, extensive feature engineering, and configurable strategies to deliver personalized video suggestions while addressing feature drift and multi‑objective business goals.

GBDTRecommendation Systemsdeep neural networks

0 likes · 13 min read

iQIYI Recommendation System: Architecture, Model Evolution, and Ranking Strategies