Scene-wise Adaptive Network for Dynamic Cold-start Scenes Optimization in CTR Prediction

TL;DR

This paper introduces SwAN, a novel scene-wise adaptive network designed to improve cold-start recommendations in dynamic multi-scene environments, demonstrating significant online performance gains in real-world deployment.

Contribution

The paper presents a new adaptive network architecture that effectively addresses cold-start challenges in multi-scene recommendation systems, with practical deployment results.

Findings

5.64% CTR improvement over baselines

5.19% increase in daily order volume

Successful deployment in Meituan's online service

Abstract

In the realm of modern mobile E-commerce, providing users with nearby commercial service recommendations through location-based online services has become increasingly vital. While machine learning approaches have shown promise in multi-scene recommendation, existing methodologies often struggle to address cold-start problems in unprecedented scenes: the increasing diversity of commercial choices, along with the short online lifespan of scenes, give rise to the complexity of effective recommendations in online and dynamic scenes. In this work, we propose Scene-wise Adaptive Network (SwAN), a novel approach that emphasizes high-performance cold-start online recommendations for new scenes. Our approach introduces several crucial capabilities, including scene similarity learning, user-specific scene transition cognition, scene-specific information construction for the new scene, and enhancing the diverged logical information between scenes. We demonstrate SwAN's potential to optimize dynamic multi-scene recommendation problems by effectively online handling cold-start recommendations for any newly arrived scenes. More encouragingly, SwAN has been successfully deployed in Meituan's online catering recommendation service, which serves millions of customers per day, and SwAN has achieved a 5.64% CTR index improvement relative to the baselines and a 5.19% increase in daily order volume proportion.