A processor receives requests for content items and identifies a first subset of machine learning (ML) models that satisfy a reliability criterion and a second subset of ML models that fail to satisfy the reliability criterion, wherein each ML model is associated with a respective content template and is trained to output a probability that a target associated with an input set of characteristics would perform a target action responsive to being presented with a content item generated based on the respective associated content template. The processing logic assigns each request to either a first group or a second group based on a ratio of a number of ML models in the first subset to a number of ML models in the second subset. For each request in the first group, the processor generates a content item based on a content template associated with the first subset.

Methods, systems, and computer program products for determining user representations based on matching. A matching request associated with a user is received. Event search data for a plurality of events for the plurality of users is obtained. A merged user representation for a plurality of candidates associated with the plurality of users is generated based on the event search data. A subset of candidates from the plurality of candidates is selected based on the merged user representation. Pairwise features are determined based on similarities between the subset of the candidates. A learned user representation is determined by identifying, using a machine learning algorithm, at least one user of the plurality of users from the subset of the candidates based on the pairwise features. The learned user representation associated with the at least one identified user of the plurality of users is provided.

An executable resource management system provides for generating an external service candidate communication based on a candidate selection score and a candidate selection context. The candidate selection score is generated using one or more candidate selection scoring models. The candidate selection context comprises a mapping of a candidate element with an internal executable resource and is generated based on communication corpus metadata and internal executable resource data. The score may represent semantic similarity between a given candidate element and a past candidate element, a classification of the given candidate element into a category represented by a semantically similar past candidate element, and/or an association between the given candidate element and a communication operation associated with a semantically similar past candidate element.

Techniques for providing and selecting targeted content as well as measuring targeted content selection at weakly connected devices are described herein. In some embodiments, a server tags media content items with attribute(s) and content attribute (CA) scores before transmitting the tagged media content items to a weakly connected device, where the CA scores are used to locally determine user attribute (UA) scores representing levels of interest for the attribute(s) based on viewed content. Once receiving a set of targeted content items (e.g., advertisements) having attributes from the server, the weakly connected device selects an advertisement based at least in part on the attributes and the UA scores. In some embodiments, the server obtains UA scores from the weakly connected devices and in conjunction with panel data and data from fully connected devices, measures times an advertisement being viewed at the weakly connected devices by a segment of audience.

Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for a content acquisition system to recommend for acquisition a subset of content items selected from a set of content items available for purchase in relation to a content recommendation system currently used in a media environment. The content acquisition system may include a content recommendation system simulator to estimate an impact function value for a potential subset of content items of the set of content items available for purchase based on the currently used content recommendation system. Afterwards, an acquisition recommender can recommend for acquisition a subset of content items based on an optimized objective function value calculated based on an optimization model while meeting one or more budget constraints.

Vehicles, components, and methods present information based on context, for example presenting a first list or menu of items (e.g., food) or first set of signage or color scheme when in a first location or during a first period, and presenting a second list or menu of items (e.g., food) or second set of signage or color scheme when in a second location or during a second period. For instance, a first menu of items (e.g., relatively more expensive entrees, beverages) may be displayed via one or more displays or screens at a first location during a first period, and a second menu of items (e.g., relatively less expensive entrees, beverages) may be displayed at a second location during a second period. Context (e.g., present location, destination, date, day, period of time, event, size of crowd, movement of crowd, weather) may be manually provided, or autonomously discerned, and presentation automatically.

A system is disclosed for presenting advertisements for products and related products for a consumer based on the products being purchased.

A server computer system identifies a user and a destination document. The server computer system identifies recommendations that correspond to the user and the destination document. The server computer system determines grades for the recommendations based on the user and/or the destination document. The server computer system determines serving probabilities for the recommendations based on the proportions of the grades and provides the serving probabilities to serve the recommendations.

Techniques for using machine learning to configure social media campaigns are disclosed. A social relationship management (SRM) service performs supervised machine learning to generate a learned model, at least by: generating feature vectors based on training data including campaign configuration data and one or more campaign success metrics; and performing pattern recognition on the feature vectors to determine one or more preferred campaign configurations. The SRM service publishes messages to one or more social media platforms and receives user interaction data associated with users' interactions with the messages. The SRM service performs unsupervised machine learning to update the learned model based at least in part on the user interaction data. The SRM service receives a request to configure a social media campaign, applies data associated with the request to the learned model to determine a preferred campaign configuration, and configures the social media campaign based on the preferred campaign configuration.

An online system maintains various models each corresponding to an action, with a model determining a likelihood of an online system user performing the action after being presented with content. A publishing user provides the online system with a content item for presentation to users of the online system and with information identifying sets of users to be presented with the content item. Different sets of users have one or more differing characteristics. The online system applies various models to identified users in each set to determine likelihoods of users in each set performing actions corresponding to different models after being presented with the content item. Based on the likelihoods, the online system selects actions for each set and presents the publishing user with information identifying actions selected for each set.