Embodiments relate to de-obfuscated data to process at one or more artificial-intelligence (AI) decision nodes throughout a communication decision tree. Through processing directed by the communication decision tree, additional de-obfuscated data is collected and securely transmitted in de-obfuscated or re-obfuscated form to enrich underlying data structures.

Methods and apparatus for determining a unique audience exposed to media while reducing memory resources of a computing device are disclosed herein. An example apparatus includes memory; instructions in the apparatus; and processor circuitry to execute the instruction to, based on impression requests from a plurality of client devices via a network, log a plurality of impressions corresponding to media accessed at the client devices; generate a product by multiplying a count of the impressions by a square of a count of registered users of a database proprietor exposed to the media; generate a quotient by dividing the product by a count of demographic impressions logged by the database proprietor; and determine a unique audience size based on a square root of the quotient.

Online advertising campaigns are operated responsive to keyword trends. The keywords used by a group of browsers is analyzed periodically over time. A list of the most frequently used keywords is separated into those that have previously appeared on the list, referred to herein as the stable keywords, and those that are newly emerging, referred to herein as the trending keywords. The advertiser selects at least one advertising creative that the advertiser associates with the stable keywords, referred to herein as the stable creative, and at least one advertising creative that the advertiser associates with the trending keywords, referred to herein as the trendy creative. The advertising system then operates the online advertising campaign to deliver the respective stable and trendy creatives in proportion to the frequency of use of the trending versus the stable keywords.

Techniques and arrangements for generating, distributing and managing promotion campaigns are described. A promotion server may generate the promotion campaigns based on input from a merchant. The input may include a request to generate the promotion campaign, a merchant preference, or other information shared between the merchant and the promotion server. The promotion campaign may include promotions, such as coupons, discounts, or the like, to encourage transactions with a merchant. The promotions may be generated based on merchant specified criteria, a merchant transaction history, customer preferences, a customer transaction history, and/or other information processed by the promotion server. The promotions of the promotion campaign may be distributed via one or more channels, such as electronic mail, website publication, receipts, etc. Each promotion of the promotion campaign may be linked to a particular customer, thereby limiting the number of times a particular customer can take advantage of the promotion campaign.

In general, embodiments of the present invention provide systems, methods and computer readable media configured to use a per-set level optimization of the rank order of promotions to be recommended to a consumer. In some embodiments, machine learning is used offline to generate a predictive diversity model that receives one or more similarity rank features associated with a promotion (e.g., category, price band) as input, and produces an output multiplier to be applied to the promotion's respective associated relevance score (e.g., a relevance score representing a prediction of the promotion's conversion rate without diversity features). At run time, per-set optimization of the ordering of a set of promotions is implemented by adjusting the respective associated relevance scores of the promotions using the diversity model and then re-ordering the set of promotions based on their respective adjusted relevance scores.

In general, embodiments of the present invention provide systems, methods and computer readable media for a predictive recommendation system using predictive models derived from tiered feature data.

Methods, systems, and programs are presented for determining exposure rate. One method includes an operation for operation for receiving a request, from a client device, for a value of an exposure rate of a zone within a webpage, the request comprising at least one search parameter and information about a viewport of the presented webpage. A check is made to determine if the exposure rate has been previously calculated. When the exposure rate has not been previously calculated, a visibility height of the zone is calculated and stored in a memory. When the exposure rate has been calculated, the visibility height is retrieved from the memory. Recordings of members accessing the webpage are analyzed to determine when the visibility height of the zone is visible in member devices accessing the webpage. The exposure rate of the zone is calculated based on the determinations of visibility of the zone.

Systems, devices, media, instructions, and methods are provided for presentation of media collections with automated interactive advertising. In one embodiment, a client device receives content elements for display as part of a content collection. Advertising data is also received for display between selected content elements. Interaction elements are merged with the create an advertising element. During display of the advertising data, the interaction elements are presented on the client device output, and are controllable via user inputs. In various embodiments, interaction data recorded at the device is used to manage the presentation of future advertising data.

A system and method for rapidly and scalably tracking attentiveness. The system includes means for collecting relevant data streams from a plurality of client devices while consumers view content, means for analysing the collected data with an AI-driven module that outputs one or more attentiveness metrics indicative of real attention, and means for synchronising the collected data with the attentiveness metrics. The system provides the ability to synchronise attentiveness metrics with other data streams to make accessible the reasons that drive attention. A digital advertising campaign can be optimised using an effectiveness data set that expresses evolution over time of an attentiveness parameter. An effect on the attentiveness parameter caused by an adjustment to a target audience can be predicted and evaluated against a campaign objective, which can be updated for predictions that yield a positive effect.

A mobile media projector system is provided with a chassis, configured for attachment to a mobile platform, having a screen deployment mechanism. A viewing screen is selectively deployable when the mobile platform is parked in a stationary geographic location. An imaging projector subsystem projects an image onto the deployed viewing screen. Typically, the chassis is configured for attachment to an automotive vehicle with a roof, and the viewing screen is deployed over an exterior surface of the automotive vehicle. The system may include a WLAN and/or WPAN access point. A targeting application may select the geographic location from a group of stationary geographic locations, each having a weighted value. A second mobile media projector system includes a chassis configured for attachment to a roof of an automobile having a side mirror. An image projected onto the side mirror is reflected onto a surface such as the automobile door.