English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Counterfactual evaluation of novel treatment assignment functions (e.g.,advertising algorithms and recommender systems) is one of the most crucialcausal inference problems for practitioners. Traditionally, randomizedcontrolled trials (A/B tests) are performed to evaluate treatment assignmentfunctions. However, such trials can be time-consuming, expensive, and evenunethical in some cases. Therefore, offline counterfactual evaluation oftreatment assignment functions becomes a pressing issue because a massiveamount of observational data is available in today's big data era.Counterfactual evaluation requires handling the hidden confounders -- theunmeasured features which causally influence both the treatment assignment andthe outcome. To deal with the hidden confounders, most of the existing methodsrely on the assumption of no hidden confounders. However, this assumption canbe untenable in the context of massive observational data. When such data comeswith network information, the later can be potentially useful to correct hiddenconfounding bias. As such, we first formulate a novel problem, counterfactualevaluation of treatment assignment functions with networked observational data.Then, we investigate the following research questions: How can we utilizenetwork information in counterfactual evaluation? Can network informationimprove the estimates in counterfactual evaluation? Toward answering thesequestions, first, we propose a novel framework, \emph{Counterfactual NetworkEvaluator} (CONE), which (1) learns partial representations of latentconfounders under the supervision of observed treatments and outcomes; and (2)combines them for counterfactual evaluation. Then through extensiveexperiments, we corroborate the effectiveness of CONE. The results imply thatincorporating network information mitigates hidden confounding bias incounterfactual evaluation.

Counterfactual Evaluation of Treatment Assignment Functions with Networked Observational Data