Abstract: Systems and methods for predicting who is watching a program are disclosed. Text related to the program can be reviewed, the text comprising: plot information, sub-title information, summary information, script information, or synopsis information, or any combination thereof. Pre-determined genre words and pre-determined keywords can be determined based on machine learning analysis of historical programs. Words from the text which are relevant words can be determined, the relevant words being words that help identify genre words or keywords. How closely the relevant words coincide to the pre-determined genre words can be determined by generating a breakdown of how many relevant words are the pre-determined genre words and the pre-determined keywords. It can be predicted who will watch the program based on the breakdown.

Abstract: Example methods and systems for ad insertion decision-making comprise: identifying an ad insertion opportunity in which an underlying advertisement is available for replacement by an addressable advertisement; determining a first expected revenue corresponding to presentation of the addressable advertisement and a first expected cost corresponding to presentation of the addressable advertisement, wherein the first expected cost is based on a current pacing of an advertisement campaign of the addressable advertisement; determining a second expected revenue corresponding to presentation of the underlying advertisement and a second expected cost corresponding to presentation of the underlying advertisement, wherein the second expected cost is based on a current pacing of an advertisement campaign of the underlying advertisement; determining an expected value of the ad insertion based on the first and second expected revenues and the first and second expected costs; and causing performance of the ad insertion bas

Abstract: A first data management system, which may be associated with a content management system (CMS), may receive an identifier for a content item. A content item may be an example of a picture, a blog post, an article, a video, an audio segment (e.g., a podcast) or other type of text or multimedia content. The first data management system may be configured to generate an object corresponding to the content item. The content object may be transmitted to a model corresponding to a second data management system. The model may be configured to identify relationships between data stored at the second data management system. The model may identify one or more data objects that are associated with the received content object, and return the data objects to the first data management system.

Abstract: A system and method that supports an integrated user interface experience with third party hosted applications selected and installed by a user within a user-installed native application of a user communication device.

Abstract: Systems and methods are provided for receiving a data set that includes demographic data and population data; training, based on the data set, a neural network to establish a relationship between different physical layouts of messages and responses to the different physical layouts of the messages; applying the trained neural network to a user profile to predict a physical layout of a message; generating instructions for an electronic device based on the predicted physical layout of the message, the instructions comprising the message; and transmitting the instructions to the electronic device to create a physical label having a layout corresponding to the predicted physical layout of the message.

Abstract: Improved systems and methods of facilitating placement of candidates between employers and recruiters are provided. In various implementations, such systems and methods provide an integrated interface within the ATS platform for employers and integrated interface within the talent platforms for recruiters. In another implementation, a talent platform exchange is provided that permits disparate talent platforms to communicate and thus more effectively manage the hiring process from within the platform. To this end, interfaces and other components may be provided which facilitate communication between talent platforms and a talent platform exchange. Such communication capability would enable a direct hire marketplace where employers engage recruiters to fill positions through their presently implemented ATSs.

Abstract: The systems and methods may be used to recommend an item to a consumer. The methods may comprise determining, based on a collaborative filtering algorithm, a consumer relevance value associated with an item, and transmitting, based on the consumer relevance value, information associated with the item to a consumer. A collaborative filtering algorithm may receive as an input a transaction history associated with the consumer, a demographic of the consumer, a consumer profile, a type of transaction account, a transaction account associated with the consumer, a period of time that the consumer has held a transaction account, a size of wallet, and/or a share of wallet. The method may further comprise generating a ranked list of items based upon consumer relevance values, transmitting a ranked list of items to a consumer, and/or re-ranking a ranked list of items based upon a merchant goal.

Abstract: 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.

Abstract: Disclosed in various examples are methods, systems, and machine-readable media for exposing a Representational State Transfer (RESTful) interface to users whereby management commands on a datacenter may be issued remotely from the users' workstations for secure, remote management of the datacenter. An application task automation command (e.g., a POWERSHELL® command) is executed remotely by creating a proxy command (e.g., based on a POWERSHELL® cmdlet code) to cause the application task automation command to be executed when the proxy command is remotely invoked and deploying the proxy command to a remote computer, such as the user's workstation. The remote computer issues a request including a user identifier and any parameters for the application task automation command when the corresponding proxy command has been invoked by the remote computer.

Abstract: System and method for behavioral and contextual data analytics are disclosed. An example computer system to process observational data received from a wireless device includes a memory including machine readable instructions and a processor to execute the instructions to: process the observational data to identify temporally adjacent applications to generate usage metric data, the observational data including application usage data; build a behavior model based on the identified temporally adjacent applications, the behavior model to describe user behavior associated with the wireless device; and apply the behavior model to predict a usage duration of a second application in response to usage of a first application.

Abstract: Methods and systems are provided to determine a partner fee recommendation. Such a partner fee may be a flat fee, percentage-based fee, or both, that a marketplace provider charges for sellers to use their platform. The partner fee recommendation may be calculated based on a plurality of factors. The partner fee recommendation may be based on data from a plurality of marketplaces. At least a portion of such data may be collected by a payment service provider or other service provider that provides services at multiple levels of transactions and through a plurality of marketplace platforms.

Abstract: A computer implemented method for inserting advertisement content into a program content stream includes receiving, by a headend content server, the program content stream. The program content stream includes an advertisement insertion cue. The method further includes detecting the advertisement insertion cue in the program content stream, and the advertisement insertion cue indicates an insertion point in the program content stream for inserting an advertisement. The method further includes modifying the advertisement insertion cue to indicate an expiration date and time for playout of a first advertisement content to be inserted into the program content stream, and inserting the first advertisement content into the program content stream.

Abstract: A system for natural language processing-based electronic file scanning for processing database queries is provided. In particular, the system may use natural language processing on various types of lookup data to create a consolidated lookup file containing the lookup data. The system may then receive search queries from users and produce a search output based on the consolidated lookup file. Once the search output is provided to the user, the system may, based on the user's interaction with the search output, incorporate the original search query into the consolidated lookup data file using machine learning. In this way, the system may adapt to incorporate variations and nuances of search queries received from its users over time.

Abstract: A method and an electronic device are disclosed. The method includes obtaining an image, obtaining information of the image, obtaining content information of content included in the image, obtaining related information which relates to the image based on at least one of the information of the image and the content information, and classifying the image into at least one category based on a plurality of defined information/data elements and a relation among the information/data elements and metadata of the image.

Abstract: Behavioral prediction for targeted end users is described. In one or more example embodiments, a computer-readable storage medium has multiple instructions that cause one or more processors to perform multiple operations. Targeted selectstream data is obtained from one or more indications of data object requests corresponding to a targeted end user. A targeted directed graph is constructed based on the targeted selectstream data. A targeted graph feature vector is computed based on one or more invariant features associated with the targeted directed graph. A behavioral prediction is produced for the targeted end user by applying a prediction model to the targeted graph feature vector. In one or more example embodiments, the prediction model is generated based on multiple graph feature vectors respectively corresponding to multiple end users. In one or more example embodiments, a tailored opportunity is determined responsive to the behavioral prediction and issued to the targeted end user.

Abstract: Systems and methods for incorporating intelligent virtual assistants into advertisements on social networking platforms are provided. When a user interacts with a content item, an intelligent virtual assistant is selected and put into contact with the user. The intelligent virtual assistant is provided with a context that includes information about the user in the social networking platform, information about the user in a customer relationship management platform, and information about the product, service, or entity associated with the content item. The context allows the intelligent virtual assistant to converse with the user in a way that feels natural and relevant to the user and allows the intelligent virtual assistant to answer any questions about the product, service, or entity associated with the content item.

Abstract: Provided is a method of providing an advertisement in an indoor space using a system including a processor and a memory storing information about a content of each of advertisements including a first advertisement. The method includes: (a) calculating a base fee of the first advertisement from a content of the first advertisement stored in the memory based on a first criterion determined in advance based on a viewer's impression of each advertisement; (b) calculating an additional fee of the first advertisement from the content of the first advertisement based on a second criterion determined in advance to determine whether to be an advertisement improper to the system; (c) selecting an advertisement to be provided from among the plurality of advertisements based on a sum of the base fee calculated and the additional fee calculated; and (d) outputting an instruction to provide, to the indoor space, the advertisement selected.

Abstract: A system performs an automated analysis on a set of related media content items, such as static and video display advertisements for a coordinated advertising campaign. The analysis can include, for example, recognition of products, services, brands, objects, music, speech, motion, colors and moods, in order to determine content profiles for the content items. Different sequences of the media content items are placed within the web browsing paths of individual users, and the responses to the sequences are monitored with respect to desired outcomes, such as the purchase of a product or the visiting of an advertiser's website. The content profiles, the sequences, the placements, and the responses are provided as input into a machine learning system that is trained to select sequences and placements of media content items that achieve the desired outcomes. The system can be trained in part or wholly using feedback from its own output.

Abstract: Systems and methods for determining predictive model types are provided. A method may include generating a predictive model for a web page of a web site, wherein the web page includes a configuration defining one or more objects presented with the web page, and wherein each object is associated with a predictive model. The method may include determining one or more predictive model types that are associated with the predictive model, determining one or more performance indicators that correspond to each determined predictive model type, wherein performance indicators represent one or more benefits to a website, selecting a predictive model type of the predictive model out of the one or more predictive model types, wherein the predictive model type is selected based on a performance indicator corresponding to the selected predictive model type, and determining a configuration of the web page using the selected predictive model type of the predictive model.

Abstract: Techniques of the disclosure are directed to a computing device creating and outputting, for display at client devices accessing a social media platform, targeted content. The computing device may receive candidate messages composed by users of a group of client devices, where the candidate messages each include a reference to the requisite product, brand, or market. If a candidate message has a determined interest score that satisfies a threshold interest score, the computing device includes the candidate message into a group of brand messages. The computing device may then send the targeted message to be output for display at another group of client devices, where the targeted message includes both an original portion and a carousel portion. The carousel portion includes a group of transitional windows, where each transitional window includes one of the brand messages from the group of brand messages.

Abstract: A method of providing advertisement content is provided. The method includes selecting at least some parts from among a plurality of parts of an advertisement target which are generated by segmenting an image of the advertisement target based on time, determining association data associated with the advertisement target, based on one or more of characteristics of the selected parts and context information indicating a condition where the advertisement content is displayed, and combining the selected parts and the determined association data to create the advertisement content.

Abstract: A computer-based method for collecting digital wallet data from a digital wallet transaction initiated by a user is provided. The method includes receiving registration data for a user in response to the user registering into a digital wallet application, wherein the registration data includes demographic data and device registration data including a device identifier used for identifying the user device when in communication with another computing device. The method also includes storing the registration data within at least one memory device and receiving digital wallet data as part of a digital wallet transaction initiated by the user using the digital wallet application on the user device, wherein the digital wallet data includes transaction data, device communication data, and biometric data. The method further includes comparing the digital wallet data to the registration data and linking the digital wallet data within the at least one memory device to the registration data.

Abstract: Disclosed are systems, methods, and computer-readable storage media to present content on an electronic display. In one aspect, a method includes identifying a first candidate content and a second candidate content for presentation on an electronic display, determining a first probability and a second probability that the first candidate content and the second candidate content respectively will elicit a particular type of input response, determining a first weight and a second weight based on the first probability and the second probability respectively, selecting either the first content or the second content based on the first weight and the second weight; and presenting the selected content on the electronic display.

Abstract: A query for one or more resources is received. One or more tokens associated with the query is identified based on running the query through a learning model. The one or more tokens correspond to one or more terms that the query shares context similarity to based on a history of user selections. One or more search result candidates are scored based at least on the context similarity between the one or more tokens and the query.

Abstract: Techniques for contextual search on multimedia content are provided. An example method includes extracting entities associated with multimedia content, wherein the entities include values characterizing one or more objects represented in the multimedia content, generating one or more query rewrite candidates based on the extracted entities and one or more terms in a query related to the multimedia content, providing the one or more query rewrite candidates to a search engine, scoring the one or more query rewrite candidates, ranking the scored one or more query rewrite candidates based on their respective scores, rewriting the query related to the multimedia content based on a particular ranked query rewrite candidate and providing for display, responsive to the query related to the multimedia content, a result set from the search engine based on the rewritten query.

Abstract: According to certain aspects of the disclosure, a computer-implemented method may be used for determining one or more vehicle recommendations. The method may include receiving data pertaining to a user's internet browsing activity. The received data may be indicative of the user's automotive vehicle preferences. The method may include comparing the received data to a collection of stored vehicle qualities. The method also may include identifying, based on the received data and the comparison of the received data to the collection of stored vehicle qualities, a vehicle characteristic of interest to the user. Using the vehicle characteristic of interest, one or more vehicle recommendations may be determined. One or more vehicle recommendations may be communicated to the user.

Abstract: Methods, apparatus, and processor-readable storage media for dynamically determining customer intent and related recommendations using deep learning techniques are provided herein.

Abstract: Techniques for the dynamic slotting of content items within electronic content are provided. In response to receiving a request, a first set of content items is identified and a first score is generated for each based on a first objective. Based on the first scores, a first ranking of the first set of content items is generated. A subset of the first set is selected based on the first ranking. A second set of content items that includes the subset is identified and a second score is generated for each item in the second set based on a second objective that is different than the first objective. Based on the second scores, a second ranking of the second set is generated. A subset of the second set is selected based on the second ranking. The second subset is presented on a computing device that is associated with the request.

Abstract: A method for adapting a piece of live content includes determining a reference group including at least one reference content consumer device being associated with a reference user and including a user state device for detecting a user state; determining that the piece of live content is streamed to the content consumer devices of the reference group; obtaining, from at least one of the content consumer devices of the reference group, at least one respective emotion indicator; determining an emotion; determining a target group comprising at least one target content consumer device being associated with a target user; triggering adapting of the piece of live content based on the at least one emotion indicator and a preference; and triggering the adapted content to be delayed.

Abstract: One or more computing devices, systems, and/or methods are provided. A user profile database may be analyzed to identify a first set of user profiles associated with conversion events associated with a first entity and/or a second set of user profiles that are not associated with conversion events associated with the first entity. A first set of vector representations may be generated based upon the first set of user profiles. A second set of vector representations may be generated based upon the second set of user profiles. A request for content associated with a client device may be received. A first vector representation may be generated based upon a first user profile associated with the client device. A user funnel stage score associated with the first entity may be generated based upon the first vector representation, the first set of vector representations and/or the second set of vector representations.

Abstract: Embodiments of the present disclosure relate to data correlation of data pertaining to content distributed through distinct content delivery networks including offline networks and data related to user interaction with an online presence on the distributed computer network and uses for such correlated data, including to measure and quantify latent effects of the content distributed through a distinct content delivery network, such as an offline network, on user's interactions with the online presence on the distributed computer network.

Abstract: A filtering machine receives sponsored content and filters the sponsored content according to a quality metric generated by quality model circuitry and assigned to the instance of sponsored content. The quality model circuitry generates the quality metric in accordance with historical feedback received about other sponsored content and a collection of quality factors pertaining to the sponsored content. Based on the quality metric for the sponsored content, the filtering machine can effect service of the sponsored content to a user device for display thereon.

Abstract: A technique for monitoring activity in a content delivery network is disclosed.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to generate synthetic respondent level data. Example apparatus disclosed herein include a synthetic panel generator to (i) generate a synthetic panel corresponding to a duration of time, the synthetic panel to be generated based on (a) a seed panel and (b) duration constraints based on return path data reported by a plurality of media devices, the synthetic panel representative of audiences of media presented by the plurality of media devices during the duration of time, and (ii) generate synthetic respondent level data based on viewing data of synthetic panelists in the synthetic panel. Disclosed example apparatus also include an output file generator to generate an output file based on the synthetic respondent level data.

Abstract: Methods and systems are described for providing advertising services to devices with a customized adaptive user experience based on adaptive algorithms. In one embodiment, a system includes a storage medium to store one or more software programs and an adaptive decision unit coupled to the storage medium. The adaptive decision unit includes or is coupled to processing logic that is configured to execute instructions of at least one adaptive decision algorithm to obtain data for different variables including at least two of an advertisement (ad) engagement history for a user, application (app) engagement history for the user, and in-app purchase engagement history for the user when making an ad selection decision. The at least one adaptive decision algorithm determines an ad selection decision for at least one relevant ad or ad content served in an engaging manner to a device of the user.

Abstract: Recommendation systems and techniques are described that use linear stochastic bandits and confidence interval generation to generate recommendations for digital content. These techniques overcome the limitations of conventional recommendations systems that are limited to a fixed parameter to estimate noise and thus do not fully exploit available data and are overly conservative, at a significant cost in operational performance of a computing device. To do so, a linear model, noise estimate, and confidence interval are refined by a recommendation system based on user interaction data that describes a result of user interaction with items of digital content. This is performed by comparing a result of the recommendation on user interaction with digital content with an estimate of a result of the recommendation.

Abstract: To improve monetization of electronic advertisement placement, a profile owner company operates an automatic system for identifying media properties that have interests in specific profiles or profiles of a specified category or kind. The profile owner recognizes a collected visitor profile as one that a media property has previously requested or one that is within a category that a media property has previously requested and arranges for the visitor to be tagged with a tag readable by the media property that requested such a profile. The media property can use the tag in displaying customized advertising to the visitor. Using information received from the media property, the profile owner company then records usage of the profile by the media property.

Abstract: The present disclosure relates generally to internet social media, and more specifically to techniques for determining location-related information about internet social media content. In some embodiments, a system accesses data representing a first social media post, the data including geographic location data identifying a first geographic location. The system identifies a second social media post related to the first post. The system accesses data representing the second social media post, wherein the data representing the second post does not include geographic location data identifying the first geographic location. The system analyzes the data representing the second social media post and determines a location score based at least in part on the analysis of the data representing the second social media post. If the location score exceeds a threshold location score, the system associates the second social media post with the first geographic location.

Abstract: A machine-learning tool evaluates an acquirer's current portfolio and then develops a model portfolio that mathematically redistributes the effect of the current portfolio by suggesting business categories that would better serve the acquirer from a risk/reward perspective. The machine-learning tool is trained with model portfolios and then generates a suggested portfolio that incorporates the acquirer's current partners and supplements them with additional business categories that would improve the risk/reward metric. The machine-learning tool may also select specific businesses from within the suggested business categories for the acquirer to use in achieving the suggested improvement.

Abstract: The present invention relates to an apparatus and a method for manufacturing a viewer-relation type video and, more particularly, to an apparatus and a method for manufacturing a viewer relation-type video which can compose received videos according to a relationship with a viewer and provide the composed videos to the viewer.

Abstract: The real-time digital asset sampling apparatuses, methods and systems (“RDA”) transform ad bidding requests via RDA components and/or the like into ad pricing indices, financial instruments and/or the like. In one implementation, the RDA may determine a digital asset market bid sampling distribution for a digital asset associated with a plurality of attribute parameters; submit a digital asset pricing bid to an exchange platform; determine a current digital asset price based on bidding result of the digital asset market bids sampling; and aggregate the determined current digital asset price to generate a digital asset price index for the digital asset associated with a plurality of attribute parameters.

Abstract: A method may include analyzing, using at least one processor, a corpus of data to identify a plurality of travel-related user inputs from a user; learning, using the at least one processor, a plurality of travel-related preferences for the user based on the plurality of travel-related user inputs; determining, using the at least one processor, a duration and location for a trip based in part on a query received from the user; accessing a plurality of points of interests (POIs) associated with the location, wherein respective point of interests are associated with a plurality of respective characteristics; based on the plurality of characteristics and the plurality of travel-related preferences, identifying a subset of the plurality of POIs to include in a trip itinerary; and presenting the trip itinerary to the user.

Abstract: In one embodiment, a method, system and apparatus are described for cloud digital video recorder optimization. A cloud based storage unit stores recorded content items in response to recording requests by users from among a plurality of users, each recorded content item belonging to at least one content item type category and each user belonging to at least one user type category. A processor receives log files tracking the recording requests, applies a data-driven procedure to the log files on a basis of at least one of: the at least one content item type category and the at least one user type category, and assigns each recorded content item to a group associated with a second plurality of users and a co-related group of content items of a given content item type category and determines times to delete each recorded content item from the cloud based storage unit. Related methods, systems, and apparatus are also described.

Abstract: One or more event trigger rules is stored, each event trigger rule including a trigger condition and a corresponding action. An indication is received that the trigger condition associated with a triggered event trigger rule has been satisfied. The corresponding action associated with the triggered event trigger rule is performed, based at least in part on the indication, wherein the corresponding action comprises a behavior associated with an audio advertising campaign.

Abstract: Novel tools and techniques are provided for provisioning network services, and, more particularly, to methods, systems, and apparatuses for implementing intelligent network services automation. In various embodiments, a computing system might receive one or more network performance metrics of one or more networks, might receive network usage data associated with the one or more networks, and might analyze, using one or more machine learning techniques, the received one or more network performance metrics and the received network usage data to determine whether the one or more networks can be improved in terms of network efficiency or network operations. Based on a determination that the one or more networks can be improved, the computing system might dynamically reconfigure at least one of one or more network connections within the one or more networks or one or more network resources within the one or more networks.

Abstract: A system and method for predictive pre-authorization of transactions using biometrics which uses wireless mobile devices and biometric scanning to automatically predict pre-authorized transaction amounts in a secure manner without requiring the customer to handle his or her mobile device. The system and method uses a payment facilitation device at the business location which automatically detects and recognizes registered mobile devices, displays a photo of the customer to a business employee for identity confirmation, verifies the customer with a biometrics verification database, generates a pre-authorization amount with an authorization generator, and automatically deducts payments for purchases from a pre-authorized customer account.

Abstract: Provided herein are systems, methods and computer readable media for programmatically generating and/or revising promotion offers for a merchant based on one or more merchant self-service indicators. In providing such functionality, the system can be configured to, for example, facilitate registration and verification of merchant identities, determine promotion content and parameters based on merchant self-service indicators, and monitor and analyze promotion offers for merchants with similar merchant self-service indicators. The system may determine the relative successfulness of a promotion offer for a merchant and/or category of merchant. In some embodiments, the system may be further configured to revise the promotion offer programmatically and/or upon receiving the merchant's approval of the programmatically generated proposed edits to the promotion offer.

Abstract: A computer-implemented method for selecting one or more providers having one or more specialties for a network available to members while satisfying one or more constraints, the method comprising: at a first computing device: receiving, from a second computing device separate and distinct from the first computer, a network provider request to select an optimized network of providers, the request including: a desired objective including at least one of provider cost minimization, provider average quality maximization and provider total volume maximization, one or more geographical designations, computing an optimized provider network of one or more selected providers including: applying a model that produces a non-optimized provider network of one or more providers having one or more specialties that satisfies the desired objective for the one or more geographical designations of the members without consideration of the availability in the geographical designation of one or more providers having one or more sp

Abstract: A method, apparatus, and computer program product are disclosed for improved machine learning using a statistical model. In the context of an apparatus, some example embodiments include a processor configured to cause retrieval of information regarding a plurality of consumers, and modeling circuitry configured to train a statistical model of the plurality of consumers based on the retrieved information, and predict, using the statistical model, an incremental booking value associated with the promotion for each consumer of the plurality of consumers. The processor is further configured to select a subset of the plurality of consumers for receiving impressions of the promotion. Some example embodiments may further include communications circuitry configured to transmit an impression of the promotion to each consumer in the subset of the plurality of consumers.

Abstract: To improve monetization of electronic advertisement placement, a profile owner company operates an automatic system for identifying media properties that have interests in specific profiles or profiles of a specified category or kind. The profile owner recognizes a collected visitor profile as one that a media property has previously requested or one that is within a category that a media property has previously requested and arranges for the visitor to be tagged with a tag readable by the media property that requested such a profile. The media property can use the tag in displaying customized advertising to the visitor. Using information received from the media property, the profile owner company then records usage of the profile by the media property.