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

Uplift modeling has shown very promising results in online marketing.However, most existing works are prone to the robustness challenge in somepractical applications. In this paper, we first present a possible explanationfor the above phenomenon. We verify that there is a feature sensitivity problemin online marketing using different real-world datasets, where the perturbationof some key features will seriously affect the performance of the uplift modeland even cause the opposite trend. To solve the above problem, we propose anovel robustness-enhanced uplift modeling framework with adversarial featuredesensitization (RUAD). Specifically, our RUAD can more effectively alleviatethe feature sensitivity of the uplift model through two customized modules,including a feature selection module with joint multi-label modeling toidentify a key subset from the input features and an adversarial featuredesensitization module using adversarial training and soft interpolationoperations to enhance the robustness of the model against this selected subsetof features. Finally, we conduct extensive experiments on a public dataset anda real product dataset to verify the effectiveness of our RUAD in onlinemarketing. In addition, we also demonstrate the robustness of our RUAD to thefeature sensitivity, as well as the compatibility with different uplift models.

Robustness-enhanced Uplift Modeling with Adversarial Feature Desensitization