TelTrans: Applying Multi-Type Telecom Data to Transportation Evaluation and Prediction via Multifaceted Graph Modeling
This work addresses traffic prediction for transportation systems by leveraging telecom data, offering a novel approach but is incremental in method.
The paper tackles traffic prediction limitations by introducing Geographical Cellular Traffic (GCT) flow as a novel data source and proposes a graph neural network integrating multivariate, temporal, and spatial facets, achieving superior accuracy over baselines, especially in long-term predictions.
To address the limitations of traffic prediction from location-bound detectors, we present Geographical Cellular Traffic (GCT) flow, a novel data source that leverages the extensive coverage of cellular traffic to capture mobility patterns. Our extensive analysis validates its potential for transportation. Focusing on vehicle-related GCT flow prediction, we propose a graph neural network that integrates multivariate, temporal, and spatial facets for improved accuracy. Experiments reveal our model's superiority over baselines, especially in long-term predictions. We also highlight the potential for GCT flow integration into transportation systems.