An Attention-Based Spatiotemporal LSTM Network for Next POI Recommendation

Next point-of-interest (POI) recommendation, also known as a natural extension of general POI recommendation, is recently proposed to predict user's next destination and has attracted considerable research interest. It focuses on learning users’ sequential patterns of check-in behavior and on training personalized recommendation models using different types of contextual information. Unfortunately, most of the previous studies failed to incorporate the spatiotemporal contextual information, which plays a critical role in analyzing user check-in behavior, into recommending the next POI. In recent years, embedding learning and recurrent neural network (RNN) based approaches show promising performance for modeling sequential patterns of check-in behavior in next POI recommendation. However, not all of the historical check-in records contribute equally to the next-step check-in behavior. To provide better next POI recommendation performance, we first proposed a spatiotemporal long and short-term memory (ST-LSTM) network. By feeding the spatiotemporal contextual information into the LSTM network in each step, ST-LSTM can model the spatial and temporal information better. Also, we developed an attention-based spatiotemporal LSTM (ATST-LSTM) network for next POI recommendation. By using the attention mechanism, ATST-LSTM can focus on the relevant historical check-in records in a check-in sequence selectively using the spatiotemporal contextual information. Besides, we conducted a comprehensive performance evaluation using large-scale real-world datasets collected from two popular location-based social networks, namely Gowalla and Brightkite. Experimental results indicated that the proposed ATST-LSTM network outperformed two state-of-the-art next POI recommendation approaches regarding three commonly-used evaluation metrics.

1 Introduction

The boom of the mobile Internet facilitates the widespread application of location-based social networks (LBSNs), such as Foursquare,1.

https://foursquare.com.

Loopt,2.

http://www.loopt.com.

and Yelp,3.

http://www.yelp.com.

in human society. Users on LBSNs can find any points of interest (POIs), post their check-ins, and share their life experiences in the real world via mobile devices and location-based services (LBSs). A large number of users’ check-in records have been used to improve user experience on LBSNs by accurate location prediction services. As an extension of general POI recommendation [1], [2], [3], [4], next POI recommendation (or called successive POI recommendation) has become an active research focus in the academic and industrial field [5]. Its primary goal is to predict the next POI a user may visit at a specific time point by mining the user's check-in records and other types of information available [6].