Techniques for controlling resource usage in a computing environment are provided. In one technique, a target resource usage for a particular point in time is determined for a content delivery campaign. Determining, for the content delivery campaign, a current resource usage for the particular point in time. Also, a bandwidth associated with the target resource usage at the particular point in time is determined. Based on a difference between the current resource usage and one or more boundaries of the bandwidth, a throttling factor is calculated. Based on the throttling factor, a probability of the content delivery campaign participating in a content item selection event is determined.

Disclosed is a computer implemented method of creating a profile of a user based on user behavior. The method may include receiving a plurality of Universal Resource Locators (URLs) corresponding to a plurality of webpages visited by the user. Further, the method may include retrieving content from each of the plurality of webpages based on the plurality of URLs. Furthermore, the method may include analyzing content from each of the plurality of webpages. Additionally, analyzing content from a webpage may include analyzing content corresponding to each content type present on the webpage. Further, the method may include identifying a plurality of keywords corresponding to the webpage based on the analyzing. Furthermore, the plurality of keywords may be associated with a plurality of affinity values. The plurality of keywords and the plurality of affinity values may constitute the profile of the user.

Keyword bids determined from sparse data are described. Initially, a portfolio optimization platform identifies which keywords included in a portfolio of keywords are low-impression keywords. This platform trains a machine learning model to generate bids for the low-impression keywords with historical data from a search engine. In particular, the platform trains this machine learning model according to an algorithm suited for training with sparse amounts of data, e.g., a temporal difference learning algorithm. In contrast, the platform uses different models, trained according to different algorithms than the low-impression keyword model, to generate bids for keywords determined not to be low-impression keywords. Once the low-impression keyword model is trained offline, the platform deploys the model for use online to generate actual bids for the low-impression keywords and submits them to the search engine. The platform continues to update the low-impression keyword model while deployed according to the sparse-data algorithm.

System for interacting with objects within rendered scenes in motion ranking, comprising: a server including a computer including a display device; a pointing device; at least one database communicating with the computer and including data for rendering scenes in motion on the display device, the scenes in motion including at least one video object, and data representing the at least one video object within the scenes in motion; wherein the video object is a visual component of the scenes in motion; an object inventory database communicating with the computer and containing information describing a location of said at least one video object within each of at least one image frame within the scenes in motion; wherein manipulation of the pointing device slows a display speed of the scenes in motion being rendered on the display device allowing a user to select a given video object within the scenes in motion.

A system, a machine-readable storage medium storing instructions, and a computer-implemented method are described herein to detect access of a predefined resource by a target account. Responsive to the detected access of the predefined resource, a sender account is determined for a persistent message to be received by the target account. The persistent message is sent from the sender account to the target account.

A system and method identify and provide content using identification entries. Product identification information for a product listing is received, and a matching identification entry is selected from a set of identification entries using the product identification information. The matching identification entry is assigned to the product listing for use in selecting content regarding the product listing for presentation.

An audio recognition system provides for delivery of promotional content to its user. A user interface device, locally or with the assistance of a network-connected server, performs recognition of audio in response to queries. Recognition can be through a method such as processing features extracted from the audio. Audio can comprise recorded music, singing or humming, instrumental music, vocal music, spoken voice, or other recognizable types of audio. Campaign managers provide promotional content for delivery in response to audio recognized in queries.

Systems and methods for determining location-based bid modifier suggestions include determining a content placement cost based in part on a likelihood of a user that has entered a physical establishment completing a transaction, an average transaction amount for the establishment, and an expected return on investment (ROI). A location-based bid modifier may be determined using the computed cost and a base bid amount. In some implementations, the location-based bid modifier may also be based on a probability model that models the probability of the user visiting the establishment.

Systems, methods, and apparatus, including computer program products, for configuring online properties, such as content pages of a website, through an online user interface. A system generates the online user interface and receives, over a network and through the online user interface presented by a client device, a request to insert a restricted third party file into a user's online property. The online user interface is updated to inform the user that inclusion of the third party file in the user's online property is restricted and to provide the user with options for satisfying requirements for including the third party file in the user's online property. In response to detecting a user selection of at least one of the options, the restricted third party file is received from a content repository, and is inserted into the user's online property.

A computer-implemented method includes receiving, at a transaction management computing subsystem of an advertising platform, a call for an advertisement creative to be served to an impression consumer; generating, using the transaction management computing subsystem, a set of bid requests, at least two bid requests of the set including respective subsets of user data store information associated with the impression consumer; and sending, by the transaction management computing subsystem, the set of bid requests to a set of bidding computing subsystems, each bidding computing subsystems being operable to generate a bid response based on the information included in its bid request.