Machine learning model for predicting scheduled delivery for a self-picked order

A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to perform steps comprising:

• receiving, via a network and from a smart shopping cart at a location of a retailer, a signal indicating that a user of an online system is physically present at the location of the retailer;
• gathering, via sensors mounted to the smart shopping cart, ordering data including information about a set of items added by the user from the location of the retailer to the smart shopping cart;
• responsive to receiving the signal, accessing a user targeting model, wherein the user targeting model is a machine-learning model trained to predict a likelihood of the user accepting an offer for a scheduled delivery of an order including the set of items, and wherein content of the order is to be self-picked by the user at the location of the retailer;
• applying the user targeting model to user data including information about the user and the ordering data to generate a score for the user indicative of the likelihood of the user accepting the offer for the scheduled delivery of the order;
• responsive to the score for the user being greater than a threshold score, generating a list of service options for the scheduled delivery of the order;
• and
• causing a user interface of the smart shopping cart to display the list of service options for the scheduled delivery of the order prompting the user to select, via the user interface of the smart shopping cart, a service option for the scheduled delivery of the order from the list of service options.

A computer system comprising:

• a processor;
• and
• a non-transitory computer-readable storage medium having instructions that, when executed by the processor, cause the computer system to perform steps comprising:
• receiving, via a network and from a smart shopping cart at a location of a retailer, a signal indicating that a user of an online system is physically present at the location of the retailer;
• gathering, via sensors mounted to the smart shopping cart, ordering data including information about a set of items added by the user from the location of the retailer to the smart shopping cart;
• responsive to receiving the signal, accessing a user targeting model, wherein the user targeting model is a machine-learning model trained to predict a likelihood of the user accepting an offer for a scheduled delivery of an order including the set of items, and wherein content of the order is to be self-picked by the user at the location of the retailer;
• applying the user targeting model to user data including information about the user and the ordering data to generate a score for the user indicative of the likelihood of the user accepting the offer for the scheduled delivery of the order;
• responsive to the score for the user being greater than a threshold score, generating a list of service options for the scheduled delivery of the order;
• and
• causing a user interface of the smart shopping cart to display the list of service options for the scheduled delivery of the order prompting the user to select, via the user interface of the smart shopping cart, a service option for the scheduled delivery of the order from the list of service options.