Using a trained model for displaying elements of user interface to facilitate engagement by a user of an online system with user interface elements
AssigneeMaplebear Inc.
InventorsSanchit Gupta, Axel Mange
Life of this patent
Estimating the term…
Loading patent…
AssigneeMaplebear Inc.
InventorsSanchit Gupta, Axel Mange
Estimating the term…
A trained model of an online system is used to display elements of a user interface of a user's device in a manner that increases a likelihood of user's engagement. Upon receiving a request from the user for a page of user interface elements and retrieving a set of user interface elements, the online system applies the trained model to predict a likelihood of user's engagement with each user interface element in the set for each incentive amount of multiple incentive amounts. The online system identifies, based on the likelihood of user's engagement with each user interface element for each incentive amount, an optimal incentive amount for each user interface element. The online system ranks the set of user interface elements based on the likelihood of user's engagement for the optimal incentive amount and displays the set of user interface elements at the user interface according to the ranking.
A method, performed at a computer system comprising a processor and a computer-readable medium, comprising:
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:
A computer system comprising:
Dependencies are inferred from the claim text.