Fragment and Integrate Network (FIN): A Novel Spatial-Temporal Modeling Based on Long Sequential Behavior for Online Food Ordering Click-Through Rate Prediction

TL;DR

This paper introduces FIN, a novel spatial-temporal modeling framework for online food ordering CTR prediction, which effectively captures long sequential behaviors and improves prediction accuracy and revenue.

Contribution

The paper proposes the Fragment and Integrate Network (FIN), a new paradigm that models long user behavior sequences with spatial-temporal detail, outperforming existing methods.

Findings

FIN achieves 5.7% CTR improvement in real-world deployment.

FIN demonstrates superior accuracy and scalability on public and production datasets.

The integrated approach effectively captures complex spatial-temporal interactions.

Abstract

Spatial-temporal information has been proven to be of great significance for click-through rate prediction tasks in online Location-Based Services (LBS), especially in mainstream food ordering platforms such as DoorDash, Uber Eats, Meituan, and Ele.me. Modeling user spatial-temporal preferences with sequential behavior data has become a hot topic in recommendation systems and online advertising. However, most of existing methods either lack the representation of rich spatial-temporal information or only handle user behaviors with limited length, e.g. 100. In this paper, we tackle these problems by designing a new spatial-temporal modeling paradigm named Fragment and Integrate Network (FIN). FIN consists of two networks: (i) Fragment Network (FN) extracts Multiple Sub-Sequences (MSS) from lifelong sequential behavior data, and captures the specific spatial-temporal representation by modeling each MSS respectively. Here both a simplified attention and a complicated attention are adopted to balance the performance gain and resource consumption. (ii) Integrate Network (IN) builds a new integrated sequence by utilizing spatial-temporal interaction on MSS and captures the comprehensive spatial-temporal representation by modeling the integrated sequence with a complicated attention. Both public datasets and production datasets have demonstrated the accuracy and scalability of FIN. Since 2022, FIN has been fully deployed in the recommendation advertising system of Ele.me, one of the most popular online food ordering platforms in China, obtaining 5.7% improvement on Click-Through Rate (CTR) and 7.3% increase on Revenue Per Mille (RPM).