Aspects of the subject disclosure may include, for example, a method in which a processing system obtains physical and social environmental data for a communication device user, and provides content for presentation at the device. First reaction data, obtained via sensors associated with the user, indicate the user's reaction to presentation of the content; the data is analyzed to determine user affinity for the content in a context of the physical and social environments. The content is modified during the presentation; second reaction data is obtained and analyzed to determine a second user affinity for the modified content. If the affinity is enhanced, the modified content is sent to other users' equipment via a social network. Affinity responses regarding the modified content are analyzed, and a set of users is identified as an affinity group; additional content is transmitted to equipment of the affinity group. Other embodiments are disclosed.

Digital image selection techniques are described that employ machine learning to select a digital image of an object from a plurality of digital images of the object. The plurality of digital images each capture the object for inclusion as part of generating digital content, e.g., a webpage, a thumbnail to represent a digital video, and so on. In one example, digital image selection techniques are described that employ machine learning to select a digital image of an object from a plurality of digital images of the object. As a result, the service provider system may select a digital image of an object from a plurality of digital images of the object that has an increased likelihood of achieving a desired outcome and may address the multitude of different ways in which an object may be presented to a user.

Provided are systems and a method for photorealistic real-time face reenactment. An example method includes receiving a target video including a target face and a scenario including a series of source facial expressions, determining, based on the target face, one or more target facial expressions, and synthesizing, using the parametric face model, an output face. The output face includes the target face. The one or more target facial expressions are modified to imitate the source facial expressions. The method further includes generating, based on a deep neural network, a mouth region and an eyes region, and combining the output face, the mouth region, and the eyes region to generate a frame of an output video.

Techniques for prefetching operation cost based digital content and digital content with emphasis that overcome the challenges of conventional systems are described. In one example, a computing device may receive digital content representations of digital content from a service provider system, which are displayed on a user interface of the computing device. Thereafter, the computing device may also receive digital content as prefetches having a changed display characteristic as emphasizing a portion of the digital content based on a model trained using machine learning. Alternatively, the computing device may receive digital content as a prefetch based on a model trained using machine learning in which the model addresses a likelihood of conversion of a good or service and an operation cost of providing the digital content. Upon receiving a user input selecting one of the digital content representations, digital content is rendered in the user interface of the computing device.

This document describes the collection, generation, distribution, and management of online web content. The devices, systems, and methods described herein can be used to collect and generate online web content and communications. Specifically, the disclosed devices and systems may be employed to produce one or more marketing and/or advertising campaigns, as well as for monitoring, managing, defining the efficiency, effectiveness, and workability of the campaign with respect to generating user engagement, thereby accurately determining the cost benefits of the campaign. The analytic results provided may then be used to guide the generation of original web content, such as for the purposes of enhancing customer or follower experience, driving business, and for driving advertising campaigns. Alternatively, web content that is in the public domain, and determined to perform well, can be reproduced, referenced, or otherwise referred to, in the context of promoting or presenting the user's web content.

This application relates to apparatus and methods for automatically determining and providing item category advertisement recommendations. In some examples, a computing device obtains transaction data identifying historical transactions. The computing device generates a first model, and trains the first model with non-seasonal data. The computing device generates a second model, and trains the second model with seasonal data. The computing device then generates a seasonal re-rank model based on the first model and the second model. The seasonal re-rank model, when executed, identifies probabilities of purchase of categories of items. In some examples, the computing device selects item advertisements to provide for display to a customer based on the probabilities of purchase of categories of items determined by the seasonal re-rank model. The selected item advertisements may be displayed to the customer, for example, on a website.

Multitask learning is applied to predict a customer's propensity to purchase an item within a particular category of items. Then, the network is tuned using transfer learning for a specific promotional campaign. Retail revenue and promotional revenue are jointly optimized, conditioned on customer trust. Accordingly, a particular promotional program may be selected that is specific to the user.

This application relates to apparatus and methods for providing a unified serving platform that allows for the reusability of machine learning models across a plurality of websites to determine personalized content. For example, a computing device trains a machine learning model with session data identifying browsing events and transaction data identifying purchasing events for a plurality of users. The computing device receives and stores session data and transaction data associated with a first website for the customer. The computing device may then receive a request for content to display to the customer on a second website. The computing device generates label data based on the session data and transaction data associated with the first website, and executes the trained machine learning model with the label data. Based on execution of the trained machine learning model, the computing device generates content to display on the second website, and transmits the content.

Aspects of the subject disclosure may include, for example, a device having a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitates a performance of operations including identifying an occurrence of a linear advertisement aired on a network channel of a multichannel video programming distributor system; estimating a first subscriber audience of the multichannel video programming distributor system exposed to the linear advertisement; identifying a second subscriber audience of the multichannel video programming distributor system provided an addressable advertisement during the occurrence of the linear advertisement; and determining a residual audience from the first subscriber audience and the second subscriber audience, wherein the residual audience comprises viewers in the first subscriber audience that are not in the second subscriber audience. Other embodiments are disclosed.

A computing system is configured to analyze historic data generated by an optimization system to provide recommended weightings for placement of creatives on publisher's pages. The weightings may be generated by providing forecasting the likelihood that a particular creative will lead to greater conversion or revenue compared to other creatives. The creatives may be grouped into one or more phases based on the amount of statistical data available for analyzing the particular creatives such that new creatives are given sufficient weighting to receive impressions despite the lack of historical data for a creative. Performance of placed creatives may be tracked by the passing of URLs with information attached to identify the particular creative and placement.