Context-aware graph convolutional network for dynamic origin-destination prediction

• Main Authors: NATHANIEL, Juan, ZHENG, Baihua
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Graph Convolutional Network (GCN); Markov Chain; public transportation; OD prediction; explainable AI (XAI); Databases and Information Systems; Theory and Algorithms; Transportation
• Online Access: https://ink.library.smu.edu.sg/sis_research/6922; https://ink.library.smu.edu.sg/context/sis_research/article/7925/viewcontent/Paper__1_.pdf
• Institution: Singapore Management University

A robust Origin-Destination (OD) prediction is key to urban mobility. A good forecasting model can reduce operational risks and improve service availability, among many other upsides. Here, we examine the use of Graph Convolutional Net-work (GCN) and its hybrid Markov-Chain (GCN-MC) variant to perform a context-aware OD prediction based on a large-scale public transportation dataset in Singapore. Compared with the baseline Markov-Chain algorithm and GCN, the proposed hybrid GCN-MC model improves the prediction accuracy by 37% and 12% respectively. Lastly, the addition of temporal and historical contextual information further improves the performance of the proposed hybrid model by 4 –12%.