Cross-region traffic prediction for China on OpenStreetMap

OpenStreetMap (OSM) is a free, open-source and popular mapping service. However, due to various reasons, it doesn't offer live traffic information or traffic prediction for China. This paper presents an approach and a system to learn a prediction model from graphical traffic condition data provided by Baidu Map, which is a commercial, close-source map provider in China, and apply the model on OSM so that one can predict the traffic conditions with nearly 90% accuracy in various parts of Shanghai, China, even though no traffic data is available for that area from Baidu Map. This novel system can be useful in urban planning, transportation dispatching as well as personal travel planning.