This document describes, among other things, systems, methods, devices, and other techniques for using information about how long various videos were presented at client devices to determine subsequent video recommendations and search results. In some implementations, a computing can include a modeling apparatus, a front-end server, a request manager, one or more video file storage devices, a video selector, or a combination of some or all of these. The video selector can select video content for a particular digitized video among a plurality of digitized videos to serve to a computing device responsive to a request. The selection can be based at least in part on how long the particular digitized video has been presented at client devices associated with users having characteristics that match one or more characteristics of the user that submitted the request for video content, as indicated by the modeling apparatus.

An example includes splitting audience member records into child nodes based on comparisons of first ones of attribute-value pairs of the audience member records to a first threshold, the attribute-value pairs representative of database subscriber activity data of corresponding audience members; in response to a quantity of ones of the audience member records in a first child node not satisfying the minimum leaf size, storing a terminal node value to indicate the first child node as a terminal node associated with one age category; in response to the quantity of the ones of the audience member records in the first child node satisfying the minimum leaf size, storing an intermediate node value to indicate the first child node as an intermediate node; and generating an age-correction model based on terminal nodes to facilitate correcting a database subscriber age characteristic associated with a media impression that is logged by a server.

Methods, systems, and machine-readable media are provided to facilitate content receiver control for particularized output of content items based on intra-content metrics. Observation data, corresponding to indications of detected content receiver operations associated with a content receiver and mapped to a first set of content items, may be processed. A first set of intra-content metrics may be detected. An audiovisual pattern of intra-content metrics may be mapped based on correlating the set of observation data with the first set of intra-content metrics. A second set of content items may be processed to detect a second set of intra-content metrics. A subset of the second set of content items may be selected based on a visual category and/or an audio category of the audiovisual pattern of intra-content metrics. The subset may be specified to cause a content receiver to modify operations to record and/or output content corresponding to the subset.

The present disclosure relates to a computer-implemented process for evaluating user activity, user preference, and/or user habit via one or more personal devices and providing precisely timed and situationally targeted content recommendations. It is an object of the present disclosure to provide a technological solution to the long felt need in small scale content recommendation systems caused by the technical problem of generating situationally targeted and user preference targeted content recommendations for users of an interactive electronic system.

Methods and apparatus to estimate demographics of a household are disclosed. An example method to determine demographics for non-panelist households includes calculating a first demographic constraint average and a second demographic constraint average based on a first demographic distribution of a first tuning event of a household and a second demographic distribution of a second tuning event of the household. The household is a non-panelist household. The example method also includes, based on the first demographic constraint average, determining a first likelihood of the household being associated with a first demographic constraint. The example method also includes, based on the second demographic constraint average, determining a second likelihood of the household being associated with a second demographic constraint. The example method also includes estimating a household characteristic of the household based on the first likelihood and the second likelihood.

The disclosed technology includes systems and methods for time-shifted prefetching of predicted content for wireless users. The disclosed technology can include a method of prefetching video data. The method can include retrieving video data and feature data and generating a video candidate set comprising selected videos. The method can include determining principal components of each video in the video candidate set by performing a principal component analysis. Furthermore, the method can include determining predicted videos using a k-nearest neighbor classifier. The predicted videos can be videos of the video candidate set that are likely to be viewed by a user at a future time. The method can include outputting instructions to the user device to prefetch the predicted videos by downloading the predicted videos to the user device.

Protecting against an impersonation scam in a live video stream. In some embodiments, a method may include periodically extracting and storing signature features from verified video streams of verified streamers, identifying an unverified live video stream of an unverified streamer being viewed by one or more users, extracting and storing signature features from the unverified live video stream, computing overall distance scores between the signature features of the unverified live video stream and the signature features of the verified video streams, determining whether the unverified streamer is impersonating one or more of the verified streamers by determining whether one or more of the overall distance scores are less than a distance threshold, determining whether one or more text signature features of the unverified live video stream include an impersonation scam, and performing a remedial action to protect the one or more users from the impersonation scam.

Methods, apparatus, systems and articles of manufacture are disclosed to project ratings for future broadcasts of media. Disclosed example methods include normalizing, with a processor, audience measurement data corresponding to media exposure data, social media exposure data and programming information associated with a future quarter to determine normalized audience measurement data. Disclosed example methods also include classifying a media asset based on the programming information to determine a media asset classification. Disclosed example methods also include building, with the processor, a projection model based on a first subset of the normalized audience measurement data, the first subset of the normalized audience measurement data associated with a first time frame relative to the future quarter, the first subset of the normalized audience measurement data based on the media asset classification, and applying, with the processor, the programming information to the projection model to project ratings for the media asset.

The herein disclosed technology provides methods and systems for intelligently predicting viewer sentiments invoked by a collection of digital content (e.g., a web-based digital channel) based on an assessment of channel metadata, such as channel metadata defining an association between the channel and one or more other channels; channel history data for the channel; and demographic information about the channel.

Methods and apparatus to estimate demographics of a household are disclosed. An example method to determine demographics for non-panelist households includes calculating a first demographic constraint average and a second demographic constraint average based on a first demographic distribution of a first tuning event of a household and a second demographic distribution of a second tuning event of the household. The household is a non-panelist household. The example method also includes, based on the first demographic constraint average, determining a first likelihood of the household being associated with a first demographic constraint. The example method also includes, based on the second demographic constraint average, determining a second likelihood of the household being associated with a second demographic constraint. The example method also includes estimating a household characteristic of the household based on the first likelihood and the second likelihood.