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

The homepage recommendation on most E-commerce applications places items in ahierarchical manner, where different channels display items in differentstyles. Existing algorithms usually optimize the performance of a singlechannel. So designing the model to achieve the optimal recommendation listwhich maximize the Click-Through Rate (CTR) of whole homepage is a challengeproblem. Other than the accuracy objective, display diversity on the homepageis also important since homogeneous display usually hurts user experience. Inthis paper, we propose a two-stage architecture of the homepage recommendationsystem. In the first stage, we develop efficient algorithms for recommendingitems to proper channels while maintaining diversity. The two methods can becombined: user-channel-item predictive model with diversity constraint. In thesecond stage, we provide an ordered list of items in each channel. Existingre-ranking models are hard to describe the mutual influence between items inboth intra-channel and inter-channel. Therefore, we propose a Deep \&Hierarchical Attention Network Re-ranking (DHANR) model for homepagerecommender systems. The Hierarchical Attention Network consists of an itemencoder, an item-level attention layer, a channel encoder and a channel-levelattention layer. Our method achieves a significant improvement in terms ofprecision, intra-list average distance(ILAD) and channel-wise Precision@k inoffline experiments and in terms of CTR and ILAD in our online systems.

Re-ranking With Constraints on Diversified Exposures for Homepage Recommender System