| CPC G06Q 30/0619 (2013.01) [G06N 7/01 (2023.01); G06Q 10/087 (2013.01); G06Q 30/0201 (2013.01); G06Q 30/0202 (2013.01); G06Q 30/0631 (2013.01); G06Q 30/0633 (2013.01); G06Q 30/0641 (2013.01)] | 16 Claims |
|
1. A method comprising, at an online concierge system comprising at least one processor and memory:
retrieving, by the online concierge system, historical orders from a user received by the online concierge system over a network, each historical order including one or more items selected by the user and associated with a time when the online concierge system received a historical order from the user;
for each of at least a set of items included in at least one historical order:
determining, by the online concierge system, time intervals between pairs of consecutive historical orders including an item of the set;
determining, by the online concierge system, an interval between orders including the item of the set from the determined time intervals; and
storing, at the online concierge system, the interval between orders in association with the user and in association with the item of the set;
receiving, by the online concierge system, a request to create an order from the user;
identifying, by the online concierge system, an item having an interval between orders greater than an amount of time between a time of a most recent previously received order including the item and a time when the request to create the order was received that is within a threshold duration of the interval between orders stored in association with the user and with the item;
determining, by the online concierge system, a category of items including the identified item;
selecting, by the online concierge system, an item from the determined category, comprising:
retrieving, by the online concierge system, an amount of compensation the online concierge system receives from an entity associated with one or more items of the determined category for selecting an item of the one or more items;
accessing, by the online concierge system, a purchase model for predicting a probability of the user purchasing an item in the determined category, wherein the purchase model comprises a machine learning model trained by:
accessing a training dataset that describes attributes of an item of a determined category and historical purchase information of the item included in the historical orders from the user;
performing a learning process on the purchase model to train the weights of the model based on the training dataset;
updating the training dataset with recent purchase information; and
retraining the purchase model based on the updated training dataset;
determining, by the online concierge system, a probability of the user purchasing each item of the determined category, wherein determining the probability comprises: applying the trained purchase model to each combination of the user and an item in the determined category;
converting, by the online concierge system, the amounts of compensation the online concierge system receives for selecting the item of the one or more items and the determined probabilities into a common unit of measurement;
calculating, by the online concierge system, a value for each item of the determined category by combining the converted amounts of compensation the online concierge system receives and the determined probabilities into a common unit of measurement; and
selecting, by the online concierge system, an item of the determined category based on the calculated values; and
generating, by the online concierge system, an interface for the order for which the request was received that includes information identifying the selected item from the determined category for display to the user without receiving input from the user.
|