STAGformer model improves bike-sharing demand forecasting

Researchers have developed STAGformer, a novel Spatio-Temporal Agent Graph Transformer designed for accurate station-level demand forecasting in bike-sharing systems. This model efficiently captures complex spatio-temporal dependencies and long-range interactions using a unique agent attention mechanism, reducing computational complexity. Experiments on NYC Citi-Bike and Chicago Divvy-Bike datasets show STAGformer significantly outperforms existing methods in forecasting accuracy. AI

IMPACT Enhances operational efficiency for micro-mobility services through improved demand prediction.

RANK_REASON Research paper detailing a new model for spatio-temporal forecasting. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• Chicago Divvy-Bike
• DagsHub
• Gotit.pub
• Hugging Face
• NYC Citi-Bike
• ScienceCast
• STAGformer

• paper
• model release
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →