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

A common task for recommender systems is to build a pro le of the interestsof a user from items in their browsing history and later to recommend items tothe user from the same catalog. The users' behavior consists of two parts: thesequence of items that they viewed without intervention (the organic part) andthe sequences of items recommended to them and their outcome (the bandit part).In this paper, we propose Bayesian Latent Organic Bandit model (BLOB), aprobabilistic approach to combine the 'or-ganic' and 'bandit' signals in orderto improve the estimation of recommendation quality. The bandit signal isvaluable as it gives direct feedback of recommendation performance, but thesignal quality is very uneven, as it is highly concentrated on therecommendations deemed optimal by the past version of the recom-mender system.In contrast, the organic signal is typically strong and covers most items, butis not always relevant to the recommendation task. In order to leverage theorganic signal to e ciently learn the bandit signal in a Bayesian model weidentify three fundamental types of distances, namely action-history,action-action and history-history distances. We implement a scalableapproximation of the full model using variational auto-encoders and the localre-paramerization trick. We show using extensive simulation studies that ourmethod out-performs or matches the value of both state-of-the-art organic-basedrecommendation algorithms, and of bandit-based methods (both value andpolicy-based) both in organic and bandit-rich environments.

BLOB : A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals