2021-04-23, 11:15–11:45, Track 2
In this talk, we will demonstrate how two large open datasets - Uber Movement and OpenStreetMap (OSM) - can be used to develop a pretty robust travel time predictor for urban travel. We use open-source routing libraries to build a machine learning model that can accurately predict travel time across many cities of the world.
The foundation of our model is the anonymized and aggregated taxi trip data shared by Uber through their Uber Movement platform. This is a large dataset which has both spatial and temporal components to it. We combine this dataset with OpenStreetMap road network and routing data to build a model of travel time that accounts for travel distance, hour-of-the-day and historic traffic. We will demonstrate the process and show a live demo of the model in action.
We will introduce modern geospatial libraries such as geopandas, shapely, folium and services such as Open Source Routing Machine and OpenRouteService that make working with large spatio-temporal datasets easy. Come and learn about how you can use these open datasets and learn about incorporating spatial datasets in your data science workflows.
See the code and demo online!