Uber Technologies, Inc.
TRIP INFERENCES AND MACHINE LEARNING TO OPTIMIZE DELIVERY TIMES

Abstract:

Due to the noisy nature of global positioning systems (GPS), tracing a signal from a device of a delivery provider may be inadequate for the task of determining a best dispatch time. However, leveraging motion data from mobile devices provides a more detailed picture of when a delivery provider is on the road, walking, or waiting. Using this data, an example embodiment creates a trip state model that enables segmenting out each stage of a trip. The trip state model enables collection and use of historical data for individual restaurants, which allows a dispatch system to optimize pickup and delivery times for both delivery providers and consumers.