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

Most Recommender Systems (RecSys) do not provide an indication of confidencein their decisions. Therefore, they do not distinguish between recommendationsof which they are certain, and those where they are not. Existing confidencemethods for RecSys are either inaccurate heuristics, conceptually complex orcomputationally very expensive. Consequently, real-world RecSys applicationsrarely adopt these methods, and thus, provide no confidence insights in theirbehavior. In this work, we propose learned beta distributions (LBD) as a simpleand practical recommendation method with an explicit measure of confidence. Ourmain insight is that beta distributions predict user preferences as probabilitydistributions that naturally model confidence on a closed interval, yet can beimplemented with the minimal model-complexity. Our results show that LBDmaintains competitive accuracy to existing methods while also having asignificantly stronger correlation between its accuracy and confidence.Furthermore, LBD has higher performance when applied to a high-precisiontargeted recommendation task. Our work thus shows that confidence in RecSys ispossible without sacrificing simplicity or accuracy, and without introducingheavy computational complexity. Thereby, we hope it enables better insight intoreal-world RecSys and opens the door for novel future applications.

A Lightweight Method for Modeling Confidence in Recommendations with Learned Beta Distributions