| CPC G06N 5/04 (2013.01) [G01C 21/3691 (2013.01); G01C 21/3697 (2013.01); G06F 17/18 (2013.01); G06F 30/20 (2020.01); G06N 20/00 (2019.01); G06Q 10/04 (2013.01); G06Q 10/063 (2013.01); G06Q 10/0833 (2013.01); G06Q 10/0838 (2013.01); G06Q 10/08355 (2013.01)] | 21 Claims |
|
1. A computer-implemented method comprising:
receiving training data corresponding to a plurality of trips, the training data including at least a value for one of 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;
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 being created based on a plurality of sets of values of a set of parameters corresponding to the set of attributes, wherein the plurality of sets of values for the set of parameters have been determined by implementing quantile regression based on a plurality of actual travel times, wherein each value of a corresponding parameter corresponds to a specific quantile among a plurality of different quantiles, corresponding to the plurality of the actual travel times based on corresponding attributes;
receiving a request with specific data for a specific trip prior to a delivery, the specific data of the request including a range between two different quantiles determined by the quantile regression for a travel time estimate, and an indication when in a week the specific trip will be taken or in which of the plurality of meal-based time zones of a day the specific trip will be taken;
calculating a specific travel time for the specific trip using the digital model;
determining a specific prediction interval for the specific travel time using the digital model based on the plurality of sets of values for the set of parameters by applying the values for the set of parameters corresponding to the range between the two different quantiles among the plurality of different quantiles determined by the quantile regression to obtain a lower bound and an upper bound for the travel time estimate, wherein the lower bound and the upper bound for the travel time estimate are obtained from a set of 30%, 40%, 50%, 60%, and 70% quantiles among the plurality of different quantiles;
causing display of the specific travel time and the specific prediction interval;
in response to a courier's failure to complete a route of the specific trip within the specific prediction interval around the specific travel time, providing a broader prediction interval for a subsequent trip along a same route using the digital model, wherein providing the broader prediction interval comprises increasing the lower bound and the upper bound for the travel time estimate by one quantile each from the set of 30%, 40%, 50%, 60%, and 70% quantiles among the plurality of different quantiles, wherein the increasing the lower bound and the upper bound for the travel time estimate corresponds to a higher confidence level than the specific prediction interval around the specific travel time;
wherein the method is performed by one or more computing devices.
|