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

TL;DR

The paper introduces MOEF, a novel CTR prediction model that leverages frequency domain analysis of occasion signals to adaptively model evolving promotional contexts, improving online recommendation accuracy.

Contribution

MOEF uniquely applies Fourier Transform to occasion signals and employs an Occasion Evolution Layer to better handle distribution shifts in dynamic e-commerce scenarios.

Findings

MOEF outperforms existing CTR models on real-world datasets.

Online A/B tests show significant CTR improvements with MOEF.

Frequency domain modeling enhances occasion representation in CTR prediction.

Abstract

Promotions are becoming more important and prevalent in e-commerce to attract customers and boost sales, leading to frequent changes of occasions, which drives users to behave differently. In such situations, most existing Click-Through Rate (CTR) models can't generalize well to online serving due to distribution uncertainty of the upcoming occasion. In this paper, we propose a novel CTR model named MOEF for recommendations under frequent changes of occasions. Firstly, we design a time series that consists of occasion signals generated from the online business scenario. Since occasion signals are more discriminative in the frequency domain, we apply Fourier Transformation to sliding time windows upon the time series, obtaining a sequence of frequency spectrum which is then processed by Occasion Evolution Layer (OEL). In this way, a high-order occasion representation can be learned to handle the online distribution uncertainty. Moreover, we adopt multiple experts to learn feature representations from multiple aspects, which are guided by the occasion representation via an attention mechanism. Accordingly, a mixture of feature representations is obtained adaptively for different occasions to predict the final CTR. Experimental results on real-world datasets validate the superiority of MOEF and online A/B tests also show MOEF outperforms representative CTR models significantly.