In an example embodiment, a bid of an impression of a piece of content, while dynamically set at impression time, may be based on a base bid that is something of a rough indicator of what the estimated price will be. That base bid then is adjusted dynamically up or down at impression time. This base bid can be determined by dividing the expected number of impressions for a day by a total daily budget. The expected number of impressions may be determined by using the empirical number of impressions from the previous day. As such, in an example embodiment, the prediction of the number of impressions for a day utilizes a corrected version of the empirical number of impressions from the prior day, with the corrected version based on a specialized formula with weights trained by a machine learning algorithm.

A method includes determining, by a computing system, a probability of whether at least a threshold portion of a particular advertisement will be presented on a particular content presentation device, and a cost associated with presentation of the particular advertisement on the particular content presentation device. The computing system calculates an expected revenue associated with presentation of the particular advertisement based on the probability and the cost. When the expected revenue exceeds a threshold revenue, the computing system communicates the particular advertisement to the particular content presentation device.

One or more aspects of the present disclosure are directed to a digital social medial platform configured to automatically identify and tag elements in an upload content using machine learning techniques. In one aspect, a method includes receive media content; automatically identify one or more elements and associated metadata in the media content using a machine learning technique; embed one or more hashtags within the media content, each of which corresponds to one of the one or more elements identified in the media content; publish the media content with the one or more hashtags; track engagements of one or more users with the media content having the one or more hashtag to yield a set of statistics; and generate a user-specific loyalty identifier for a user associated with the media content, based on the set of statistics.

Embodiments of the present invention provide systems, methods, and computer storage media directed at controlling a campaign. In embodiments, a method includes receiving event values respectively associated with corresponding events. The method can then utilize these event values in calculating an estimated impression value for a present logical interval of the campaign. The method can further include generating a price control signal based on a desired return on investment (ROI) associated with the campaign and an observed ROI of a previous logical interval of the campaign. Based on the estimated impression value and the price control signal, a bid price can be computed for the current logical interval of the campaign. This bid price can then be transmitted to a market associated with the campaign. Other embodiments may be described and/or claimed herein.

A system and methods for providing accurate counting of advertisement impressions is described. The system and methods include bloom filter technology or other space-efficient probabilistic data structure algorithms to efficiently determine whether any particular advertisement impression across an enormous set of possibilities has been viewed previously or not, without having to search through every instance of rendering of any particular advertisement impression. The present system and methods include arrays of multiple bloom filters and manipulate them to correct for false positives when conditions create the risk of false positives that may have occurred during data capture on a browser. In addition, the system and methods generate unique qualification identifiers for advertising served, which is evaluated by the bloom filters before a count is incremented.

Systems and methods for performing near real-time merging of distributed data streams are described. For example, streams of ad impressions, ad clicks, and conversions are sorted by user id into virtual buckets. The buckets of data are distributed across multiple servers, so that each server can process their respective buckets of data independently. Each server uses synchronization logic to determine a running delay distribution of the data streams. Based on the delay distributions, merge processing of the streams is appropriately delayed to ensure that the ad impression and ad click stream information needed for correlating with the conversion stream information is likely to be available in real time.

A display apparatus displaying content corresponding to an installation location and a server providing content considering the installation location of the display apparatus are provided. The display apparatus includes: a display; a communication interface configured to communicate with an external server; and a processes configured to control the communication interface to receive, from the external server, content including an element with a large number of expected viewers identified based on at least one of a number of viewers or an installation location, and control the display to display the received content.

Methods and apparatus to estimate census level audience sizes, impression counts, and duration data are disclosed. Example instructions cause one or more processor to at least set up a system of equations based on first census data; select a census parameter value based on a constraint for census parameter selection, the constraint based on media access represented in panel data; iteratively solve for second census data that satisfies the system of equations using the panel data and the census parameter value, the second census data including an audience size value, an impression count value, and a duration value for a media item accessed by anonymous audience members in a demographic group; and generate a report including the second census data.

An example apparatus includes an audience size calculator circuitry to determine a first census-level audience size, and an impression count calculator circuitry to determine a first census-level impression count. The example apparatus includes a verification controller circuitry to determine whether the first one of the plurality of cross-demographic total census audience parameter values satisfies a first constraint; determine the first one of the plurality of cross-demographic total census impression parameter values satisfies a second constraint based on the first census-level impression count; and when the first constraint is not satisfied or the second constraint is not satisfied: (a) discard the first one of the cross-demographic total census audience parameter values and the first one of the cross-demographic total census impression parameter values, and (b) select a second one of the cross-demographic total census audience parameter values and a second one of the cross-demographic total census impression parameter values.

A system and method for allocating credit for an advertising conversion among various advertising touchpoints encounter by the consumer is provided. The system and method comprise receiving data pertaining to touchpoints and conversions of an advertising campaign across multiple channels. Users are correlated across the channels and the various conversions, touchpoints, and touchpoint attributes are identified. Each touchpoint attribute and touchpoint attribute value is assigned a weight. An attribution algorithm is selected, and coefficients are calculated using the assigned weights. The algorithm is executed and true scores corresponding to the touchpoints encountered by each converting user are computed.