Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating models. In some implementations, a system obtains data that comprises promotions and parameters for an opportunity. The system generates transformation spaces based on the promotions and the parameters, wherein each transformation space comprises states, each state is based on the parameters for a particular promotion. The system iterates over a number of iterations. For each transformation space, the system adjusts a state of the transformation space based on actions. The system generates a model by combining each adjusted state. The system generates an entropy for the model. The system compares the entropy to a threshold value, wherein the threshold value corresponds to one of the parameters. In response to determining that the entropy exceeds the threshold value, the system iterates. The system provides the generated model for output.

Technologies are provided for the generating of optimal policies for bidding in auctions having unknown dynamics. In some embodiments, a computing system can configure many multi-armed bandit (MAB) models defining candidate directed contents for a sequence of pages. A particular MAB model of the many MAB models defines candidate directed contents for a particular page in the sequence of pages, where each arm in the particular MAB model corresponds to a candidate impression on the particular page. The computing system can then determine a solution to an optimization problem with respect to an objective function based on an expected long-term reward for a defined impression on the first page, a defined impression on the second page, and a defined impression on the third page. The solution results in respective directed content for presentation on the first, second, and third pages.

Methods, computer-readable media, and devices for auditing digital content to validate that the digital content is authentic, secure, and reaching the intended audience are disclosed. In one example, a method performed by a processing system including at least one processor includes launching a web browser application, wherein the launching includes instantiating a simulated user profile, and wherein the simulated user profile includes a simulated web browsing history, detecting, by the processing system, an item of digital content that is presented to the web browser application in response to the simulated user profile, determining, by the processing system, a relevance of the item of digital content to the simulated user profile, and generating, by the processing system, a report that indicates the relevance of the item of digital content to the user profile.

Methods, systems, and storage media for generating leads for vendors through a social media program are disclosed. Exemplary implementations may: estimate a conversion rank for an online promotion for a targeted prospect based at least in part on historical data of conversion ranks for a sample of the targeted prospect; simulate the online promotion to the sample of the targeted prospect; calculate a likelihood of conversion based on the simulating of the online promotion to the sample of the targeted prospect; and cause display of the likelihood of conversion as a confidence score.

A computer-implemented method includes one or more processors configured for receiving ad scoring data corresponding to a biometric response to an advertisement displayed on a computing device user interface at a first time, receiving ad feature data corresponding to the advertisement, and generating first model output data corresponding to a user engagement score based on ad scoring data and ad feature data. Further, the method includes receiving user interface activity data corresponding to graphical images displayed at the first time, generating second model output data corresponding to a watching ad classification based on the user interface activity data and the ad feature data, determining an ad effectiveness score based on the first model output data and the second model output data, and generating ad improvement data based on the ad effectiveness score and the ad feature data, the ad improvement data comprising recommendations to adjust features of the advertisement.

Devices, systems, and methods are provided for goal-based audience selection. A method for generating an audience using machine learning may include receiving a request to generate an audience for an advertisement campaign, the request including an objective associated with presentation of the advertisement campaign. The method may include determining first user actions based on the objective, and identifying first users of a system who performed the first user actions using the system. The method may include determining second user actions performed by the first users prior to performing the first user actions, and identifying second users of the system who performed the second user actions and failed to perform the first user actions. The method may include generating a target audience to which to present the advertisement campaign, and causing presentation of the advertisement campaign to the target audience.

Techniques described herein are directed to centralized brand asset management. In an example, a first computing device associated with a first point-of-sale (POS) service can receive an instruction to update a web page of a merchant, wherein the instruction to update the web page of the merchant changes a brand asset of the merchant. The first computing device can send a request to update the brand asset of the merchant to a centralized data storage storing one or more brand assets of one or more merchants. The centralized data storage can update the brand asset to an updated brand asset, which can be available to at least a second computing device associated with a second POS service. The second POS service can update a respective POS service feature based on the updated brand asset.

Systems and methods are disclosed for determining an estimate of available user impressions on a network, comprising receiving a request for an estimate of available user impressions for viewing one or more media elements on a network, the request comprising one or more viewer demographic group limitations. A request may be received to include deterministic users and probabilistic users in the estimate of available user impressions. A number of deterministic users may be determined based on query results from a deterministic user data set. A number of probabilistic users may be determined based on query results from a probabilistic user data set, and the estimate of available user impressions may be determined based on the number of deterministic users and the number of probabilistic users.

Techniques and systems are described to enable users to optimize a digital marketing content system by analyzing an effect of components of digital marketing content on audience segments, environments of consumption, and channels of consumption. A computing device of an analytics system receives user interaction data describing an effect of user interaction with multiple items of digital marketing content on achieving an action for multiple audience segments. The analytics system identifies which of a plurality of components are included in respective items of digital marketing content. The analytics system generates data identifying different aspects that likely had an effect on the achieving an action on the items of digital marketing content, such as components of the items of digital marketing content, environments of consumption, channels of consumption. The analytics system outputs a result based on the data in a user interface.

Methods, systems, apparatus, and articles of manufacture to determine causal effects are disclosed herein. An example apparatus includes a weighting engine to calculate a first set of weights corresponding to a first treatment dataset, a second set of weights corresponding to a second treatment dataset, and a third set of weights corresponding to a control dataset, the weighting engine to increase an operational efficiency of the apparatus by calculating the first set of weights, second set of weights, and third set of weights independently, a weighting response engine to calculate a first weighted response for the first treatment dataset, a second weighted response for the second treatment dataset, and determine a causal effect between the first treatment dataset and the second treatment dataset based on a difference between the first weighted response and the second weighted response, and a report generator to transmit a report to an audience measurement entity.