STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting

TL;DR

This paper introduces STG2Seq, a hierarchical graph convolutional model that captures spatial-temporal dependencies for accurate multi-step passenger demand forecasting in vehicle sharing services.

Contribution

It proposes a novel hierarchical graph convolutional structure with encoders and an attention-based output for improved multi-step demand prediction.

Findings

Outperforms baseline methods on three real-world datasets

Effectively models dynamic spatial-temporal dependencies

Achieves state-of-the-art forecasting accuracy

Abstract

Multi-step passenger demand forecasting is a crucial task in on-demand vehicle sharing services. However, predicting passenger demand over multiple time horizons is generally challenging due to the nonlinear and dynamic spatial-temporal dependencies. In this work, we propose to model multi-step citywide passenger demand prediction based on a graph and use a hierarchical graph convolutional structure to capture both spatial and temporal correlations simultaneously. Our model consists of three parts: 1) a long-term encoder to encode historical passenger demands; 2) a short-term encoder to derive the next-step prediction for generating multi-step prediction; 3) an attention-based output module to model the dynamic temporal and channel-wise information. Experiments on three real-world datasets show that our model consistently outperforms many baseline methods and state-of-the-art models.