# Real-Time Forecasting of Dockless Scooter-Sharing Demand: A Spatio-Temporal Multi-Graph Transformer Approach

arXiv: https://arxiv.org/abs/2111.01355 · HTML: https://mlsanity.com/paper/2111.01355/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2021.

## Built on by (most cited first, 6 of 6)

- [Travel Demand Forecasting: A Fair AI Approach](https://mlsanity.com/paper/2303.01692/) (2023)
- [Examining spatial heterogeneity of ridesourcing demand determinants with explainable machine learning](https://mlsanity.com/paper/2209.07980/) (2022)
- [ICN: Interactive Convolutional Network for Forecasting Travel Demand of Shared Micromobility](https://mlsanity.com/paper/2306.13897/) (2023)
- [Situational-Aware Multi-Graph Convolutional Recurrent Network (SA-MGCRN) for Travel Demand Forecasting During Wildfires](https://mlsanity.com/paper/2304.06233/) (2023)
- [A Comprehensive Machine Learning Framework for Micromobility Demand Prediction](https://mlsanity.com/paper/2507.02715/) (2025)
- [A Grid-Based Framework for E-Scooter Demand Representation and Temporal Input Design for Deep Learning: Evidence from Austin, Texas](https://mlsanity.com/paper/2603.13609/) (2026)

## Abstract (arXiv)

Accurately forecasting the real-time travel demand for dockless scooter-sharing is crucial for the planning and operations of transportation systems. Deep learning models provide researchers with powerful tools to achieve this task, but research in this area is still lacking. This paper thus proposes a novel deep learning architecture named Spatio-Temporal Multi-Graph Transformer (STMGT) to forecast the real-time spatiotemporal dockless scooter-sharing demand. The proposed model uses a graph convolutional network (GCN) based on adjacency graph, functional similarity graph, demographic similarity graph, and transportation supply similarity graph to attach spatial dependency to temporal input (i.e., historical demand). The output of GCN is subsequently processed with weather condition information by the Transformer to capture temporal dependency. Then, a convolutional layer is used to generate the final prediction. The proposed model is evaluated for two real-world case studies in Washington, D.C. and Austin, TX, respectively, and the results show that for both case studies, STMGT significantly outperforms all the selected benchmark models, and the most important model component is the weather information. The proposed model can help the micromobility operators develop optimal vehicle rebalancing schemes and guide cities to better manage dockless scooter-sharing operations.