GNN-based Passenger Request Prediction
This addresses a specific problem for ride-sharing platforms in operations planning, but it is incremental as it builds on existing GNN and attention methods for a niche application.
The paper tackles the problem of predicting Origin-Destination (OD) flow of passengers in ride-sharing platforms, which is less studied than general demand prediction, by developing a Graph Neural Network framework with an Attention Mechanism. The results demonstrate superior performance compared to existing baselines, though no concrete numbers are provided.
Passenger request prediction is essential for operations planning, control, and management in ride-sharing platforms. While the demand prediction problem has been studied extensively, the Origin-Destination (OD) flow prediction of passengers has received less attention from the research community. This paper develops a Graph Neural Network framework along with the Attention Mechanism to predict the OD flow of passengers. The proposed framework exploits various linear and non-linear dependencies that arise among requests originating from different locations and captures the repetition pattern and the contextual data of that place. Moreover, the optimal size of the grid cell that covers the road network and preserves the complexity and accuracy of the model is determined. Extensive simulations are conducted to examine the characteristics of our proposed approach and its various components. The results show the superior performance of our proposed model compared to the existing baselines.