Criteo Uplift
PulseAugur coverage of Criteo Uplift — every cluster mentioning Criteo Uplift across labs, papers, and developer communities, ranked by signal.
-
New research uses A/B test data to guide adaptive experiment design
A new research paper explores using historical data from A/B tests to inform the design of adaptive experiments, particularly those employing contextual bandits. The study introduces a method that combines off-policy ev…
-
New uplift modeling methods improve causal inference with cross-head attention
Researchers have introduced the Cross-Head Attention Uplift Network (CHAUN) and a Robust Adversarial Inverse Propensity Score (RA-IPS) method to improve uplift modeling. CHAUN utilizes shared feature embeddings and cros…
-
New framework improves ad pacing with calibrated uncertainty
A new research paper introduces a decision-calibrated conformal framework designed to improve pacing decisions in streaming advertising. This framework addresses uncertainties in future inventory, demand, and user exper…