A Spatio-Temporal Spot-Forecasting Framework for Urban Traffic Prediction
This work addresses spatio-temporal forecasting for urban traffic, offering an adaptable and interpretable solution, though it appears incremental in nature.
The paper tackled urban traffic prediction by developing an interpretable attention-based neural network framework, achieving stable and superior results compared to state-of-the-art alternatives.
Spatio-temporal forecasting is an open research field whose interest is growing exponentially. In this work we focus on creating a complex deep neural framework for spatio-temporal traffic forecasting with comparatively very good performance and that shows to be adaptable over several spatio-temporal conditions while remaining easy to understand and interpret. Our proposal is based on an interpretable attention-based neural network in which several modules are combined in order to capture key spatio-temporal time series components. Through extensive experimentation, we show how the results of our approach are stable and better than those of other state-of-the-art alternatives.