• Corpus ID: 221949212

Spatial-Temporal Demand Forecasting and Competitive Supply via Graph Convolutional Networks

  title={Spatial-Temporal Demand Forecasting and Competitive Supply via Graph Convolutional Networks},
  author={Bolong Zheng and Qi Hu and Lingfeng Ming and Jilin Hu and Lu Chen and Kai Zheng and Christian S. Jensen},
We consider a setting with an evolving set of requests for transportation from an origin to a destination before a deadline and a set of agents capable of servicing the requests. In this setting, an assignment authority is to assign agents to requests such that the average idle time of the agents is minimized. An example is the scheduling of taxis (agents) to meet incoming requests for trips while ensuring that the taxis are empty as little as possible. In this paper, we study the problem of… 
Graph Neural Network for Traffic Forecasting: A Survey
This survey is the first comprehensive survey that explores the application of graph neural networks for traffic forecasting problems and reviews the rapidly growing body of recent research using different GNNs, e.g., graph convolutional and graph attention networks, in various traffic forecast problems.
An Effective Fleet Management Strategy for Collaborative Spatio-Temporal Searching: GIS Cup
A fleet management method by formulating CSTS as a minimum cost flow problem, called MCF-FM, and a continuous order dispatch strategy, which is the top performer in the agent utilization scenario and runner-up in the customer experience scenario.
SOUP: A Fleet Management System for Passenger Demand Prediction and Competitive Taxi Supply
A fleet management system called SOUP is demonstrated that accurately predicts passenger demand and significantly reduces taxi idle time and that monitors the fleet movement status.


Stochastic Origin-Destination Matrix Forecasting Using Dual-Stage Graph Convolutional, Recurrent Neural Networks
A generic learning framework that employs matrix factorization and graph convolutional neural networks to contend with the data sparseness while capturing spatial correlations and that captures spatio-temporal dynamics via recurrent neural networks extended with graph convolutions is proposed.
Distance-Aware Competitive Spatiotemporal Searching Using Spatiotemporal Resource Matrix Factorization (GIS Cup)
This work proposes an algorithm to optimize the efficiency of drivers searching for customers using non-negative matrix factorization (NMF) and randomizes the destinations of agents using the predicted resource distribution within the local neighborhood of an agent.
Spatio-Temporal Graph Convolutional and Recurrent Networks for Citywide Passenger Demand Prediction
An end-to-end deep learning framework that can achieve accurate prediction and outperform the most discriminative state-of-the-art methods for multi-step passenger demand prediction.
STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting
This work proposes to model multi-step citywide passenger demand prediction based on a graph and use a hierarchical graph convolutional structure to capture both spatial and temporal correlations simultaneously.
Origin-Destination Matrix Prediction via Graph Convolution: a New Perspective of Passenger Demand Modeling
A unified model, Grid-Embedding based Multi-task Learning (GEML) which consists of two components focusing on spatial and temporal information respectively, designed to model the spatial mobility patterns of passengers and neighboring relationships of different areas is proposed.
Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction
A Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations is proposed, which demonstrates effectiveness of the approach over state-of-the-art methods.
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
Diffusion Convolutional Recurrent Neural Network (DCRNN), a deep learning framework for traffic forecasting that incorporates both spatial and temporal dependency in the traffic flow and evaluates the framework on two real-world large scale road network traffic datasets and observes consistent improvement.
Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction
A deep-learning-based approach to collectively forecast the inflow and outflow of crowds in each and every region of a city, using the residual neural network framework to model the temporal closeness, period, and trend properties of crowd traffic.
An Effective Partitioning Approach for Competitive Spatial-Temporal Searching (GIS Cup)
STP partitions the search space into regions by considering both spatial and temporal information of the historical resource records, and compute a weight for each region and assigns a shortest-travel-time path to each agent from its current location to a relatively popular region according to the current time.