T-STAR: A Context-Aware Transformer Framework for Short-Term Probabilistic Demand Forecasting in Dock-Based Shared Micro-Mobility

2026-02-06

AI Summary

This work addresses the challenge of modeling short-term fluctuations and uncertainty in high-resolution (15-minute) docked bike-sharing demand forecasting. To this end, we propose T-STAR, a two-stage spatiotemporal adaptive framework that first captures stable hourly demand patterns and then integrates recent demand dynamics with real-time contextual signals—such as metro passenger flows—via a Transformer architecture to produce probabilistic short-term predictions. Our approach innovatively decouples long-term regularities from short-term perturbations, introduces context-aware hierarchical spatiotemporal modeling, and enables zero-shot transfer to unseen regions. Evaluated on the Washington D.C. Capital Bikeshare dataset, T-STAR consistently outperforms state-of-the-art methods across both deterministic and probabilistic metrics, demonstrating strong spatiotemporal generalization and robustness.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

Reliable short-term demand forecasting is essential for managing shared micro-mobility services and ensuring responsive, user-centered operations. This study introduces T-STAR (Two-stage Spatial and Temporal Adaptive contextual Representation), a novel transformer-based probabilistic framework designed to forecast station-level bike-sharing demand at a 15-minute resolution. T-STAR addresses key challenges in high-resolution forecasting by disentangling consistent demand patterns from short-term fluctuations through a hierarchical two-stage structure. The first stage captures coarse-grained hourly demand patterns, while the second stage improves prediction accuracy by incorporating high-frequency, localized inputs, including recent fluctuations and real-time demand variations in connected metro services, to account for temporal shifts in short-term demand. Time series transformer models are employed in both stages to generate probabilistic predictions. Extensive experiments using Washington D.C.'s Capital Bikeshare data demonstrate that T-STAR outperforms existing methods in both deterministic and probabilistic accuracy. The model exhibits strong spatial and temporal robustness across stations and time periods. A zero-shot forecasting experiment further highlights T-STAR's ability to transfer to previously unseen service areas without retraining. These results underscore the framework's potential to deliver granular, reliable, and uncertainty-aware short-term demand forecasts, which enable seamless integration to support multimodal trip planning for travelers and enhance real-time operations in shared micro-mobility services.

Problem

• short-term demand forecasting
• shared micro-mobility
• probabilistic forecasting
• dock-based bike-sharing
• high-resolution prediction

Innovation

• Transformer
• probabilistic forecasting
• two-stage architecture
• context-aware
• zero-shot transfer