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

Sequential recommendation predicts users' next behaviors with theirhistorical interactions. Recommending with longer sequences improvesrecommendation accuracy and increases the degree of personalization. Assequences get longer, existing works have not yet addressed the following twomain challenges. Firstly, modeling long-range intra-sequence dependency isdifficult with increasing sequence lengths. Secondly, it requires efficientmemory and computational speeds. In this paper, we propose a Sparse AttentiveMemory (SAM) network for long sequential user behavior modeling. SAM supportsefficient training and real-time inference for user behavior sequences withlengths on the scale of thousands. In SAM, we model the target item as thequery and the long sequence as the knowledge database, where the formercontinuously elicits relevant information from the latter. SAM simultaneouslymodels target-sequence dependencies and long-range intra-sequence dependencieswith O(L) complexity and O(1) number of sequential updates, which can only beachieved by the self-attention mechanism with O(L^2) complexity. Extensiveempirical results demonstrate that our proposed solution is effective not onlyin long user behavior modeling but also on short sequences modeling.Implemented on sequences of length 1000, SAM is successfully deployed on one ofthe largest international E-commerce platforms. This inference time is within30ms, with a substantial 7.30% click-through rate improvement for the onlineA/B test. To the best of our knowledge, it is the first end-to-end long usersequence modeling framework that models intra-sequence and target-sequencedependencies with the aforementioned degree of efficiency and successfullydeployed on a large-scale real-time industrial recommender system.

Sparse Attentive Memory Network for Click-through Rate Prediction with Long Sequences