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

In recommendation scenarios, there are two long-standing challenges, i.e.,selection bias and data sparsity, which lead to a significant drop inprediction accuracy for both Click-Through Rate (CTR) and post-click ConversionRate (CVR) tasks. To cope with these issues, existing works emphasize onleveraging Multi-Task Learning (MTL) frameworks (Category 1) or causaldebiasing frameworks (Category 2) to incorporate more auxiliary data in theentire exposure/inference space D or debias the selection bias in theclick/training space O. However, these two kinds of solutions cannoteffectively address the not-missing-at-random problem and debias the selectionbias in O to fit the inference in D. To fill the research gaps, we propose aDirect entire-space Causal Multi-Task framework, namely DCMT, for post-clickconversion prediction in this paper. Specifically, inspired by users' decisionprocess of conversion, we propose a new counterfactual mechanism to debias theselection bias in D, which can predict the factual CVR and the counterfactualCVR under the soft constraint of a counterfactual prior knowledge. Extensiveexperiments demonstrate that our DCMT can improve the state-of-the-art methodsby an average of 1.07% in terms of CVR AUC on the five offline datasets and0.75% in terms of PV-CVR on the online A/B test (the Alipay Search). Suchimprovements can increase millions of conversions per week in real industrialapplications, e.g., the Alipay Search.

DCMT: A Direct Entire-Space Causal Multi-Task Framework for Post-Click Conversion Estimation