Abstract:
Online car-hailing services can better schedule drivers with accurate citywide passenger demand forecasts. Previous research either uses passenger order history or grid region partition, which loses physical context.
Mobile traffic analysis has improved city understanding. We propose FlowFlexDP, a flexible region partition demand prediction model that integrates regional crowd flow. Passenger demand and crowd flow correlate strongly in a 1.5 million-user cellular dataset from a major Chinese city.
FlowFlexDP uses Graph Convolutional Neural Network to predict city regions of any size and shape using order history and crowd flow from cellular data. FlowFlexDP predicts passenger demand better than state-of-the-art demand prediction methods on a large data set of 6 online car-hailing applications from cellular data.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
