A computer implemented method includes allocating to an advertisement campaign, planned bookings for certain time periods and for certain digital displays from an Out Of Home inventory. The method also allocates, by a real-time bidding process, unplanned bookings to the time periods. Forecasts of unplanned bookings demand are taken into account in allocating planned bookings.

Methods and apparatus to incorporate saturation effects into marketing mix models are disclosed. An example apparatus includes means for converting adstock data associated with an advertising campaign into effective reached realized (ERR) data based on a first saturation curve, the adstock data corresponding to adstocked gross rating points generated from marketing mix input data. The apparatus further including means for performing regression analysis to: identify the first saturation curve from among a plurality of plausible curves based on a fit of different ones of the plurality of plausible curves to the marketing mix input data, the first saturation curve to define a relationship indicative of saturation effects of the advertising campaign on a target audience of the advertising campaign; and determine an impact of the advertising campaign on sales during a period of interest based on a regression analysis of the ERR data relative to sales data.

Systems and methods are disclosed for traffic filtration by content providers. One method includes receiving a content request from a device of a user; determining whether one or more container tags are associated with requested content; determining, prior to responding to the content request, whether the content request is by a user based on the content request and the one or more container tags; generating, prior to responding to the content request, an ad request based on the content request and the one or more container tags; determining, prior to responding to the content request, an ad request recipient based on the generated ad request and the one or more container tags; transmitting the ad request to the determined ad request recipient; and transmitting, over the electronic network to the device, a response to the content request when the content request is determined to be by a user.

Systems and methods are provided for electronic stimulus evaluation through one or more signals. The one or more signals protect underlying raw data relating to behavior, including purchase behavior and location-based behavior. A server platform in network communication with at least one signal buyer computer and at least one signal provider computer facilitates creation of the one or more signals. Anonymized identifiers are used to identify objects or consumers associated with behavior data and exposure to the electronic stimulus. The server platform provides optimization analytics for the stimulus based on the one or more signals, which include measurement signals, behavior signals, and lift signals.

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.

A digital brand asset system performs the steps of providing payloads for a smart brand asset to a plurality of web servers which include codes representing the smart brand asset, receiving feedbacks on how the smart brand asset is presented on the website servers, collecting web journey data of the website visitors' who have interacted with the smart brand asset, generating a report detailing how effective the smart brand asset has been on the website servers, and presenting the report on a dashboard. Generally, by monitoring the website servers and visitors interacting with the smart brand assets, a report can be generated for the brand owners to determine the effectiveness of the smart brand assets hosted on the website servers. The raw data used to generate the report can be used to autonomically and dynamically change the content based upon the interpretation of the feedbacks.

A method including receiving, at a first computing system from a second computing system, a first key and encrypted online interaction data, receiving, at the first computing system from a third computing system, a second key and encrypted offline action data encoding data indicating one or more offline actions, receiving, at the first computing system from the third computing system, executable code comprising a third key, and executing, by the first computing system, the executable code. The executable code causing the first computing system to decrypt the encrypted online interaction data and the encrypted offline action data using the first key, the second key, and the third key, correlate one or more of the offline actions in the offline action data to one or more online interactions in the online interaction data, and generate aggregate data indicating a number of offline actions correlated to the online interactions.

A facility for presenting advertising messages on behalf of multiple advertisers is described. The facility determines allocations that each specify a share for an advertiser, the specified shares all being different. The facility causes advertising messages to be presented on behalf of the advertisers in accordance with the shares specified by their allocations.

Embodiments of the present disclosure relate to data correlation of data pertaining to content distributed through distinct content delivery networks including offline networks and data related to user interaction with an online presence on the distributed computer network and uses for such correlated data, including to measure and quantify latent effects of the content distributed through a distinct content delivery network, such as an offline network, on user's interactions with the online presence on the distributed computer network.

Methods and systems for using reinforcement learning to optimizing promotions. A promotion for a product and/or service is offered to a customer using a reinforcement learning model. The customer's reaction is observed. A reward or a penalty is collected based on the customer's reaction. The reinforcement learning model is adapted based on the reward or penalty.