Methods, systems, and apparatus, including computer programs encoded on computer storage media, for grouping users are provided. One embodiment of the methods includes: dividing a plurality of users targeted by the an advertisement candidate into a plurality of user buckets, wherein each of the plurality of user buckets is associated with a first conversion score; obtaining a trained prediction model corresponding to the advertisement, wherein the trained prediction model is able to predict a conversion score based at least on the first conversion score associated with a user bucket and a second conversion score associated with a group of user buckets comprising the user bucket; and constructing an optimization model using the trained prediction model, wherein an objective function of the optimization problem is to maximize a total conversion score with a grouping strategy determined by solving the optimization problem.

A computer-implemented method can facilitate delivery of targeted content to user devices in situations in which historic tracking data (e.g., cookie data) is generally unavailable and/or unreliable. A p-dimensional embedding of websites can be generated based on a group of user devices for whom tracking data is available. Conversion event data that indicates indicating whether that audience member performed a conversion action can be received. A machine learning model can be trained using the conversion event data and the positions of websites appearing in the conversion event data within the p-dimensional embedding to predict a likelihood of conversion and/or a type of content to provide given a position in the p-dimensional embedding. When an indication that a user device is accessing a website is received, a position of that website in the p-dimensional embedding can be determined and targeted content can be delivered to the user device.

A computer-implemented method can facilitate delivery of targeted content to user devices in situations in which historic tracking data (e.g., cookie data) is generally unavailable and/or unreliable. A p-dimensional embedding of websites can be generated based on a group of user devices for whom tracking data is available. Conversion event data that indicates indicating whether that audience member performed a conversion action can be received. A machine learning model can be trained using the conversion event data and the positions of websites appearing in the conversion event data within the p-dimensional embedding to predict a likelihood of conversion and/or a type of content to provide given a position in the p-dimensional embedding. When an indication that a user device is accessing a website is received, a position of that website in the p-dimensional embedding can be determined and targeted content can be delivered to the user device.

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.

Systems and methods for real-time matching of promotional content to content that a user is currently consuming. Content that is currently being consumed is classified into descriptive categories, such as by determining a vector of content features where this vector is in turn used to classify the currently-played content. Promotional content having classifications that match the classifications of the currently-played content is then determined. Matching promotional content may then be played for the user in real time. In this manner, systems and processes of embodiments of the disclosure may identify promotional content matching what the user is currently watching, so as to present users promotional content tailored to subject matter the user is currently interested in.

A computer-implementation method for dataless contextual targeting includes the following steps. First, automatically crawling noisy labeled corpora from one or more sites using a category mapping from first categories to second categories. Second, applying one or more statistical methods to automatically mine representative keywords for each of the first categories from the noisy labeled corpora. Applying dataless classification learning to induce a text classifier with the automatically mined representative keywords and unlabeled web pages as input.

A computer-implemented method is disclosed. The method includes using reverse geo-coding to determine user transaction locations for a user, determining a number of user transactions for the user that correspond to each of a plurality of statistical area levels, determining a subdivision of each of the plurality of statistical area levels that has the highest number of domestic card present transactions for the user, identifying an effective area of influence (EAI) for the user, based on a determination of a statistical area level that has the highest number of domestic card present transactions for the user, and accessing geographically classified statistics from public data sources related to one or more of the plurality of the statistical area levels. A location based market recommendation is generated based on the geographically classified statistics and the effective area of influence.

Methods and systems for generating a messaging campaign are described. A set of intended recipients is identified for a proposed messaging campaign associated with an online store. A set of recommended parameters is determined for the proposed messaging campaign, the set of recommended parameters including a recommended distribution channel for each recipient group identified in the set of intended recipients.

A portable billboard is presented including a portable media projection subsystem to selectively project media and to supply an enablement signal in response to the media being projected. A location device supplies a geographic location of the media projection subsystem. A verifier receives the enablement signal and the geographic location, and supplies verification information responsive to the media being projected from a stationary location for a predetermined minimum duration of time. A communications subsystem receives verification information and either stores the information for subsequent downloads, or transmits the information to a central controlling server. A targeting subsystem permits an entity to select a target stationary location from a plurality of value weighted target stationary locations. The targeting application typically provides a reward in response to a value of the selected target stationary location.

This document describes the autonomous 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 in an automatic and autonomous manner. Specifically, the disclosed methods, devices, and systems may be employed to produce one or more communications and/or advertising campaigns, as well as for monitoring, managing, defining the efficiency, effectiveness, and workability of the campaign with respect to generating predicted user engagements, thereby accurately determining the cost benefits of the communication campaign. The system may track, evaluate, and provide analytic results that may then be used to better guide the system parameters for customizing autonomous communications directed one or more characteristics of a defined target audience.