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/

Zendy Plus

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

Zendy Tools

Zendy Open

Promotions are becoming more important and prevalent in e-commerce to attractcustomers and boost sales, leading to frequent changes of occasions, whichdrives users to behave differently. In such situations, most existingClick-Through Rate (CTR) models can't generalize well to online serving due todistribution uncertainty of the upcoming occasion. In this paper, we propose anovel CTR model named MOEF for recommendations under frequent changes ofoccasions. Firstly, we design a time series that consists of occasion signalsgenerated from the online business scenario. Since occasion signals are morediscriminative in the frequency domain, we apply Fourier Transformation tosliding time windows upon the time series, obtaining a sequence of frequencyspectrum which is then processed by Occasion Evolution Layer (OEL). In thisway, a high-order occasion representation can be learned to handle the onlinedistribution uncertainty. Moreover, we adopt multiple experts to learn featurerepresentations from multiple aspects, which are guided by the occasionrepresentation via an attention mechanism. Accordingly, a mixture of featurerepresentations is obtained adaptively for different occasions to predict thefinal CTR. Experimental results on real-world datasets validate the superiorityof MOEF and online A/B tests also show MOEF outperforms representative CTRmodels significantly.

MOEF: Modeling Occasion Evolution in Frequency Domain for Promotion-Aware Click-Through Rate Prediction