The main goal of this project is to construct a static temporal graph dataset(STGD) and applying a temporal graph network(TGN) to verfiy the dataset's credibility and usability. This paper includes a detailed procedure for converting tabular data to temporal graph data through innovated data pre-processing/ cleansing and self-devised TOP-K algorithms to connect graph vertices. The main learning problem for this project falls to node regression field in graphic neural network. The tabular excel data compiled from Boston Region Metropolitan Planning Organization could be found in this url: https://www.bostonmpo.org/. The source code of this project can be accessed in this github repository: https://github.com/yzw19990124/GCN-Application.git.
