Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

Click-Through Rate (CTR) prediction holds a pivotal place in online advertising and recommender systems since CTR prediction performance directly influences the overall satisfaction of the users and the revenue generated by companies. Even so, CTR prediction is still an active area of research since it involves accurately modelling the preferences of users based on sparse and high-dimensional features where the higher-order interactions of multiple features can lead to different outcomes. Most CTR prediction models have relied on a single fusion and interaction learning strategy. The few CTR prediction models that have utilized multiple interaction modelling strategies have treated each interaction to be self-contained. In this paper, we propose a novel model named STEC that reaps the benefits of multiple interaction learning approaches in a single unified architecture. Additionally, our model introduces residual connections from different orders of interactions which boosts the performance by allowing lower level interactions to directly affect the predictions. Through extensive experiments on four real-world datasets, we demonstrate that STEC outperforms existing state-of-the-art approaches for CTR prediction thanks to its greater expressive capabilities.

Serdarcan Dilbaz, Hasan Saribas• 2023

Related benchmarks

TaskDatasetResultRank
Click-Through Rate PredictionAvazu (test)
AUC0.7664
191
CTR PredictionCriteo (test)
AUC0.8143
141
CTR PredictionFrappe
AUC0.985
83
CTR PredictionMovieLens
AUC97.15
55
CTR PredictionIndustrial Production (offline)
Delta AUC0.0126
3
CTR PredictionNews Recommendation Production System Online A/B Test (Day 1)
ΔCTR1.247
2
CTR PredictionNews Recommendation Production System Online A/B Test (Day 5)
Delta CTR3.651
2
CTR PredictionNews Recommendation Production System Online A/B Test (Day 2)
Delta CTR0.002
2
CTR PredictionNews Recommendation Production System Online A/B Test (Day 3)
ΔCTR-1.409
2
CTR PredictionNews Recommendation Production System Online A/B Test (Day 4)
Delta CTR (Relative Lift)1.09
2
Showing 10 of 13 rows

Other info

Follow for update