Spatiotemporal-Enhanced Network for Click-Through Rate Prediction in Location-based Services

TL;DR

This paper introduces StEN, a novel spatiotemporal-enhanced network for click-through rate prediction in location-based services, explicitly modeling timing and location to improve personalization and performance.

Contribution

The paper proposes a new Spatiotemporal-Enhanced Network (StEN) with modules for capturing common and personalized spatiotemporal preferences, and a target attention mechanism for better location-time awareness.

Findings

Achieves state-of-the-art results on three large-scale datasets.

Demonstrates effectiveness in takeaway industry scenarios.

Provides a new public dataset for spatiotemporal CTR prediction.

Abstract

In Location-Based Services(LBS), user behavior naturally has a strong dependence on the spatiotemporal information, i.e., in different geographical locations and at different times, user click behavior will change significantly. Appropriate spatiotemporal enhancement modeling of user click behavior and large-scale sparse attributes is key to building an LBS model. Although most of existing methods have been proved to be effective, they are difficult to apply to takeaway scenarios due to insufficient modeling of spatiotemporal information. In this paper, we address this challenge by seeking to explicitly model the timing and locations of interactions and proposing a Spatiotemporal-Enhanced Network, namely StEN. In particular, StEN applies a Spatiotemporal Profile Activation module to capture common spatiotemporal preference through attribute features. A Spatiotemporal Preference Activation is further applied to model the personalized spatiotemporal preference embodied by behaviors in detail. Moreover, a Spatiotemporal-aware Target Attention mechanism is adopted to generate different parameters for target attention at different locations and times, thereby improving the personalized spatiotemporal awareness of the model.Comprehensive experiments are conducted on three large-scale industrial datasets, and the results demonstrate the state-of-the-art performance of our methods. In addition, we have also released an industrial dataset for takeaway industry to make up for the lack of public datasets in this community.