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

Click-Through Rate (CTR) prediction holds a pivotal place in onlineadvertising and recommender systems since CTR prediction performance directlyinfluences the overall satisfaction of the users and the revenue generated bycompanies. Even so, CTR prediction is still an active area of research since itinvolves accurately modelling the preferences of users based on sparse andhigh-dimensional features where the higher-order interactions of multiplefeatures can lead to different outcomes. Most CTR prediction models have reliedon a single fusion and interaction learning strategy. The few CTR predictionmodels that have utilized multiple interaction modelling strategies havetreated each interaction to be self-contained. In this paper, we propose anovel model named STEC that reaps the benefits of multiple interaction learningapproaches in a single unified architecture. Additionally, our model introducesresidual connections from different orders of interactions which boosts theperformance by allowing lower level interactions to directly affect thepredictions. Through extensive experiments on four real-world datasets, wedemonstrate that STEC outperforms existing state-of-the-art approaches for CTRprediction thanks to its greater expressive capabilities.

STEC: See-Through Transformer-based Encoder for CTR Prediction