An attention-based encoder-decoder model predicts next-hour bike station demand and returns across all 766 NYC stations, outperforming its LSTM and GRU baselines by about 40% RMSE.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Micromobility Flow Prediction: A Bike Sharing Station-level Study via Multi-level Spatial-Temporal Attention Neural Network
An attention-based encoder-decoder model predicts next-hour bike station demand and returns across all 766 NYC stations, outperforming its LSTM and GRU baselines by about 40% RMSE.