Chao-Jiang / ST-MGCN-keras

Spatiotemporal Multi-Graph Convolution Network for Ride-hailing Demand Forecasting implementation with keras

ST-MGCN-keras

This is a Keras implementation of Spatiotemporal Multi-Graph Convolution Network(ST-MGCN) model from the paper "Spatiotemporal Multi-Graph Convolution Network for Ride-hailing Demand Forecasting".

Model architecture

Requirements:

• numpy 1.14.2
• python 3

Usage

$ python main.py

Code Organization

• main.py:

Reference

Geng X, Li Y, Wang L, et al. Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2019, 33: 3656-3663.

Follow us

Knowledge-Precipitation-Tribe