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

Players in the online ad ecosystem are struggling to acquire the user datarequired for precise targeting. Audience look-alike modeling has the potentialto alleviate this issue, but models' performance strongly depends on quantityand quality of available data. In order to maximize the predictive performanceof our look-alike modeling algorithms, we propose two novel hybrid filteringtechniques that utilize the recent neural probabilistic language modelalgorithm doc2vec. We apply these methods to data from a large mobile adexchange and additional app metadata acquired from the Apple App store andGoogle Play store. First, we model mobile app users through their app usagehistories and app descriptions (user2vec). Second, we introduce contextawareness to that model by incorporating additional user and app-relatedmetadata in model training (context2vec). Our findings are threefold: (1) thequality of recommendations provided by user2vec is notably higher than currentstate-of-the-art techniques. (2) User representations generated through hybridfiltering using doc2vec prove to be highly valuable features in supervisedmachine learning models for look-alike modeling. This represents the firstapplication of hybrid filtering user models using neural probabilistic languagemodels, specifically doc2vec, in look-alike modeling. (3) Incorporating contextmetadata in the doc2vec model training process to introduce context awarenesshas positive effects on performance and is superior to directly including thedata as features in the downstream supervised models.

Learning Continuous User Representations through Hybrid Filtering with doc2vec