Described herein is a system for using a machine learning model to predict a metric value indicative of quality of user experience. The system can receive an indication that a mobile device was used to access electronic content. The system obtains a set of characteristics of a user of the mobile device and generates a predicted metric value indicative of a quality of user experience interacting with the electronic content by applying a trained machine learning model to the obtained set of characteristics. The machine learning model is trained on cluster data representing clusters of users of the system, and each cluster is associated with a one or more shared characteristics of users in the cluster and an average metric value selected by users in the cluster. The system selects and transmit an interactive element associated with the predicted metric value to the mobile device.

A performance optimization system (POS) includes: a POS data platform configured to store data usable to determine the POS score; a machine learning platform configured to use machine learning to determine the POS score, the machine learning platform operably connected to the POS data platform; a prediction server operably connected to the machine learning platform, the prediction server comprising a server configured to receive an advertisement request from a client demand-side platform (DSP), the prediction server further configured to create a prediction request from the advertisement request, the prediction server further configured to score the prediction request to determine a likelihood to influence an end user by exposing the end user to the brand advertisement; and a prediction request log operably connected to the prediction server, the prediction request log configured to log the scored prediction request.

Methods, apparatus, and articles of manufacture are disclosed. An example apparatus includes a co-viewing calculator to calculate a co-viewing factor corresponding to a demographic of panelists based on exposure information, an exposure time calculator to calculate a number of census co-viewer exposure minutes based on the co-viewing factor, a data aggregator to determine an aggregate exposure time total based on census exposure information and the number of census co-viewer exposure minutes, and a report generator to generate a report including the aggregate exposure time total.

A social networking system presents content items to users, who then provide feedback regarding pairs of content items. The feedback includes a selection of a content item of the pair of content items that was preferred by the user over the other content item. The social networking system uses this information to train a predictive model that scores content items based on quality. The content items may be advertisements. The social networking system uses the pair-wise comparisons of the advertisements to determine feedback coefficients in an advertising quality score prediction model using regression analysis of the pair-wise comparisons for each predictive factor in the model. In this way, the pair-wise comparisons are used to train the prediction model to understand which advertisements are more enjoyable than others. A feedback coefficient for each predictive factor may be computed based on the preferences received from the group of users.

The SOCIAL CONTENT MONITORING PLATFORM METHODS (Social-Watch) transforms social media contents via Social-Watch components, into ad effects data. A method is disclosed, comprising: identifying a request to access user social media content; obtaining user authorization credentials to access user social media content; sending an access request with the obtained user authorization credentials to a social media platform; receiving social media content data from the social media platform; determining a type of the received media content data; tagging the received media content data based on the type according to a progressive taxonomy mechanism; receive a social media analytics request for an item; querying the tagged media content data based on key terms related to the item; and determining impression heuristics for the item based on query results.

Social media content items are mapped to relevant time-based media events. These mappings are used as the basis for calculating metrics based upon the mappings, and ratings of the time-based media there from. Audience response metrics (ARMs) are calculated from the mappings, which provide an indication of audience engagement or response. In addition, ARMs provide information about the virality, depth, and breadth of the response by the viewing audience. The calculated metrics are stored and are used to generate ratings for the time-based media. The ratings may be published in whole or in part, e.g., as part of a ratings system.

Methods and apparatus for conducting test promotions in a highly scalable and cost-effective manner using randomized experiment methodology are disclosed. Test promotions of interest are presented to visitors of a website in a randomized experiment manner wherein each page presents one test promotion of interest among other promotions. The other promotions presented in the same page may be randomized. The visitors' responses with respect to the test promotions of interest are then recorded and analyzed to determine the performance of each presented test promotion of interest.

Methods and apparatus for conducting test promotions in a highly scalable and cost-effective manner using controlled experiment methodology are disclosed. Test promotions of interest are presented to visitors of a website in a controlled experiment manner wherein each page presents one test promotion of interest among other promotions. The other promotions presented in the same page are kept constant in the pages. The visitors' responses with respect to the test promotions of interest are then recorded and analyzed to determine the performance of each presented test promotion of interest.

Techniques for affecting display of content may include receiving a request for content to supplement a response to an input initiated by a first user; outputting first content in response to the request, where the first content includes a control feature that is displayable along with the first content, and where the control feature enables the first user to register a negative reaction to the first content; obtaining information relating to the first content based on the negative reaction; identifying second content having one or more characteristics in common with the first content; identifying one or more second users having one or more characteristics in common with the first user; and using the information relating to the first content in determining whether to provide the second content to the one or more second users.

Methods and apparatus to determine efficiencies of media delivery across platforms are disclosed. An example method includes obtaining a first effectiveness metric for a first platform, obtaining a first reach of the first platform with respect for a target group of audience members, and calculating a first performance metric based on the first effectiveness metric and the first reach.