Facebook, Inc.

David Paul Capel

Loren William Abrams

Jinfu Leng

Alisson Gusatti Azzolini

Stuart Michael Bowers

Hussein Mohamed Hassan Mehanna

Harsh Doshi

Andrey Malevich

Sai Nishanth Parepally

Benjamin Casey Roberts

An advertising system provides advertisements to client devices. To select advertisements, the advertising system identifies previously selected advertisements to determine which presentations of the advertisement are still in-flight and have not yet resulted in conversion event. The advertising system predicts total advertising spend based on the in-flight advertisements, and adjusts a paced bid for the advertisement by determining whether the estimated total advertising spend, reflecting predicted in-flight advertisements, is above or below an expected spending to reach a budget for the advertising campaign, which may increase or decrease the paced bid.

Modifying advertisement bids using predicted advertisement performance

A system receives event information describing an event performed by a user with a content provider. The system identifies a property associated with the content provider whose aggregation conditions are satisfied by the event. The system selects an aggregator to which to send the information based on the user. The selected aggregator stores an event entry in its aggregator store with the event information and an indication of the property. The aggregator determines an aggregate value of the user for the property based on event entries in the aggregator store associated with the user and the property. The system provides a content item associated with the content provider to the user based on audience conditions of the property being satisfied by the aggregate value. The system also determines a removal time for each event entry and schedules an aggregation event for updating the user's aggregate value at removal time.

Scheduling events for a dynamic audience platform

An online system identifies an additional feature to evaluate for inclusion in a machine learned model. The additional feature is based on characteristics of one or more dimensions of information maintained by the online system. To generate data for evaluating the additional feature, the online system generates various partitions of stored data, where each partition includes characteristics associated with one or more dimensions on which the additional feature is based. Using values of characteristics in a partition, the online system generates values for the additional feature and includes the values of the additional feature in the partition. Values for the additional feature are generated for various partitions based on the values of characteristics in each partition. The online system combines multiple partitions that include values for the additional feature to generate a training set for evaluating a machine learned model including the additional feature.

Evaluating modifications to features used by machine learned models applied by an online system

Storage of events for a dynamic audience platform

Growing community of inventors

Belmont, CA, United States of America

David Paul Capel