Where to Go Next: A Spatio-temporal LSTM model for Next POI Recommendation

TL;DR

This paper introduces STLSTM, a spatio-temporal LSTM model that incorporates time and distance gates to better capture user check-in behaviors for next POI recommendation, significantly outperforming existing methods.

Contribution

The paper proposes a novel LSTM variant with spatio-temporal gates and coupled input-forget gates to enhance next POI recommendation accuracy.

Findings

STLSTM outperforms state-of-the-art models on four real-world datasets.

The spatio-temporal gates effectively model user check-in behaviors.

Parameter reduction improves model efficiency.

Abstract

Next Point-of-Interest (POI) recommendation is of great value for both location-based service providers and users. Recently Recurrent Neural Networks (RNNs) have been proved to be effective on sequential recommendation tasks. However, existing RNN solutions rarely consider the spatio-temporal intervals between neighbor check-ins, which are essential for modeling user check-in behaviors in next POI recommendation. In this paper, we propose a new variant of LSTM, named STLSTM, which implements time gates and distance gates into LSTM to capture the spatio-temporal relation between successive check-ins. Specifically, one-time gate and one distance gate are designed to control short-term interest update, and another time gate and distance gate are designed to control long-term interest update. Furthermore, to reduce the number of parameters and improve efficiency, we further integrate coupled input and forget gates with our proposed model. Finally, we evaluate the proposed model using four real-world datasets from various location-based social networks. Our experimental results show that our model significantly outperforms the state-of-the-art approaches for next POI recommendation.