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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The travel marketing platform of Alibaba serves an indispensable role forhundreds of different travel scenarios from Fliggy, Taobao, Alipay apps, etc.To provide personalized recommendation service for users visiting differentscenarios, there are two critical issues to be carefully addressed. First,since the traffic characteristics of different scenarios, it is verychallenging to train a unified model to serve all. Second, during the promotionperiod, the exposure of some specific items will be re-weighted due to manualintervention, resulting in biased logs, which will degrade the ranking modeltrained using these biased data. In this paper, we propose a novelScenario-Aware Ranking Network (SAR-Net) to address these issues. SAR-Netharvests the abundant data from different scenarios by learning users'cross-scenario interests via two specific attention modules, which leverage thescenario features and item features to modulate the user behavior features,respectively. Then, taking the encoded features of previous module as input, ascenario-specific linear transformation layer is adopted to further extractscenario-specific features, followed by two groups of debias expert networks,i.e., scenario-specific experts and scenario-shared experts. They outputintermediate results independently, which are further fused into the finalresult by a multi-scenario gating module. In addition, to mitigate the datafairness issue caused by manual intervention, we propose the concept ofFairness Coefficient (FC) to measures the importance of individual sample anduse it to reweigh the prediction in the debias expert networks. Experiments onan offline dataset covering over 80 million users and 1.55 million travel itemsand an online A/B test demonstrate the effectiveness of our SAR-Net and itssuperiority over state-of-the-art methods.

SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios