Deep Situation-Aware Interaction Network for Click-Through Rate Prediction

TL;DR

This paper introduces DSAIN, a novel CTR prediction model that leverages situational features and user behavior context, significantly improving prediction accuracy and deployed on Meituan's platform.

Contribution

The paper proposes a new concept of situational features and a deep network architecture for more effective user behavior sequence modeling in CTR prediction.

Findings

DSAIN increases CTR by 2.70% in offline experiments.

DSAIN improves CPM by 2.62% and GMV by 2.16% in online A/B tests.

The model is deployed on Meituan's food delivery platform, serving main traffic.

Abstract

User behavior sequence modeling plays a significant role in Click-Through Rate (CTR) prediction on e-commerce platforms. Except for the interacted items, user behaviors contain rich interaction information, such as the behavior type, time, location, etc. However, so far, the information related to user behaviors has not yet been fully exploited. In the paper, we propose the concept of a situation and situational features for distinguishing interaction behaviors and then design a CTR model named Deep Situation-Aware Interaction Network (DSAIN). DSAIN first adopts the reparameterization trick to reduce noise in the original user behavior sequences. Then it learns the embeddings of situational features by feature embedding parameterization and tri-directional correlation fusion. Finally, it obtains the embedding of behavior sequence via heterogeneous situation aggregation. We conduct extensive offline experiments on three real-world datasets. Experimental results demonstrate the superiority of the proposed DSAIN model. More importantly, DSAIN has increased the CTR by 2.70\%, the CPM by 2.62\%, and the GMV by 2.16\% in the online A/B test. Now, DSAIN has been deployed on the Meituan food delivery platform and serves the main traffic of the Meituan takeout app.