MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction

TL;DR

MobTCast is a Transformer-based model that integrates temporal, semantic, social, and geographical contexts, including an auxiliary location prediction task, to enhance human mobility prediction accuracy.

Contribution

The paper introduces MobTCast, a novel multi-context Transformer model with an auxiliary location prediction branch and consistency loss for improved next POI prediction.

Findings

Outperforms state-of-the-art methods in mobility prediction

Effectively models multiple contexts including social and geographical

Demonstrates the benefit of auxiliary tasks and consistency loss

Abstract

Human mobility prediction is a core functionality in many location-based services and applications. However, due to the sparsity of mobility data, it is not an easy task to predict future POIs (place-of-interests) that are going to be visited. In this paper, we propose MobTCast, a Transformer-based context-aware network for mobility prediction. Specifically, we explore the influence of four types of context in the mobility prediction: temporal, semantic, social and geographical contexts. We first design a base mobility feature extractor using the Transformer architecture, which takes both the history POI sequence and the semantic information as input. It handles both the temporal and semantic contexts. Based on the base extractor and the social connections of a user, we employ a self-attention module to model the influence of the social context. Furthermore, unlike existing methods, we introduce a location prediction branch in MobTCast as an auxiliary task to model the geographical context and predict the next location. Intuitively, the geographical distance between the location of the predicted POI and the predicted location from the auxiliary branch should be as close as possible. To reflect this relation, we design a consistency loss to further improve the POI prediction performance. In our experimental results, MobTCast outperforms other state-of-the-art next POI prediction methods. Our approach illustrates the value of including different types of context in next POI prediction.