DYNAMICALLY ALLOCATING COMPUTING RESOURCES TO IDENTIFY ADVERTISEMENTS FOR PRESENTATION

摘要

An advertising system has limited computing resources to spend evaluating advertisements of advertisers to determine a “best” advertisement to serve to users of a social networking system. The computing resources are allocated (e.g., by varying the number of advertisements that are considered for presentation to a user) based on the neediness of the user and/or the advertiser on a per impression basis. The neediness of a user may be determined by grouping users into groups and determining a yield curve of expected revenue per computing resource used. Then, the revenue may be maximized across impression opportunities for multiple users. The neediness of an advertiser may be determined by biasing the selection of one advertiser's advertisements over another advertiser's advertisements based on an expected revenue, an expected number of interactions of the advertisement, or otherwise maximizing a satisfaction coefficient for the advertiser.

主权项

1. A method comprising:
identifying a plurality of impression opportunities for presenting advertisements to users of a social networking system; accessing a yield curve for each of the users, each yield curve representing a group of users and indicating an expected revenue to be generated by presenting an advertisement to a user of the group per amount of computing resources used in selecting one or more advertisements for display to a user of the group of users; determining, based on the yield curves, an amount of computing resources to allocate for identifying an advertisement for each of the users, the allocation determined to maximize revenue across the impression opportunities for the users; and applying the amount of computing resources allocated to each user to identify an advertisement for presentation to each user.