Abstract: A computer-implemented method comprises receiving training data corresponding to a plurality of trips, the training data including at least a value for a set of attributes for each of the plurality of trips, the set of attributes including an indication of when in a week a trip is taken or in which of a plurality of meal-based time zones in a day the trip is taken, the training data including an actual travel time for each of the plurality of trips. The method further comprises creating and storing, in computer memory, a digital model that is configured to predict a travel time for a future trip based on the training data, the digital model including a set of parameters corresponding to the set of attributes, the digital model including a plurality of sets of values for the set of parameters.

Abstract: Systems and methods for using machine learning to estimate courier arrival times are described herein. According to an embodiment, a server computer receives a request to deliver to a requester prepared items associated with a preparation entity. The server additionally receives courier data identifying available couriers within the geographic region of the preparation entity and current request data identifying current requests to deliver prepared items from a plurality of entities in the geographic region. The server uses a trained machine learning system to compute an estimated pickup time, using at least the courier data and courier request data as inputs. The server computer then routes a preparation request to the preparation entity along with the estimated pickup time.