Abstract: Embodiments of the present invention provide methods, systems, apparatuses, and computer program products for predicting consumer behavior. In one embodiment a method is provided comprising automatically creating a link graph comprising nodes representing webpages, links representing hyperlinks, and weights for each link representing a number of times a hyperlink associated with the respective link redirected the a user devices from a webpage associated with a first node connected to the link to a webpage associated with a second node connected to the link; and determining based on the link graph a programmatically expected path for a particular user, wherein the programmatically expected path identifies, at least, two or more webpages that the particular user is programmatically expected to visit and specifying a programmatically expected order at which the particular user will visit the webpages.

Abstract: An online system displays an ordering interface and, responsive to receiving a request from a client device associated with a user to place an order, retrieves information describing a set of unused credits provided to the user by each of one or more programs. The system identifies a set of the program(s), wherein the set of unused credits provided by each identified program is eligible to be used for acquiring an item in the order. The system accesses and applies a machine-learning model to predict an expiration of the set of unused credits provided to the user by each identified program based on the retrieved information and a current time. The system ranks the set of programs based on the prediction(s), determines a default allocation of a subset of each set of unused credits to the order based on the ranking, and updates the interface to include the default allocation.

Abstract: Embodiments herein describe connecting a customer in a retail store with an expert. In one example, this connection is made using a shelf IO device. Using a product ID provided by the shelf IO device, a computing system can identify an expert and determine whether they are available to help the customer. For example, the system may identify an expert that is currently in the same store as the customer, or the expert may be available to conduct a phone conversation or teleconference using the customer's mobile phone.

Abstract: An electronic device includes a communicator; at least one memory storing information associated with a neural network model for predicting a target device for each time zone from a plurality of time zones for an advertising content; and at least one processor configured to: acquire, from a plurality of external devices, data corresponding to a use history of a user; acquire, based on the data corresponding to the use history, a plurality of feature values corresponding to a respective external device from the plurality of external devices by allocation of each feature value of the plurality of feature values to a respective time zone from the plurality of time zones, input the plurality of feature values into the neural network model, and acquire score information for a plurality of probabilities that the plurality of external devices are related to a label by allocation of each probability of the plurality of probabilities to a respective time zone from the plurality of time zones, identify, based on the sc

Abstract: The subject matter of this specification can be embodied in, among other things, a method that receives at a server a first request to rebroadcast a first sponsored content item that was displayed on the social network to the first user to a second user. A second request to display at least one sponsored content item to the second user when the second user accesses an electronic document associated with the social network is received at the server. The first sponsored content item is retrieved for rebroadcast from one or more sponsored content items indicated for rebroadcast to the second user. The first sponsored content item is output to the second user of the social network in response to the second request to display and without requiring the second user to select the first sponsored content item for display.

Abstract: A system can recommend a next action for a user. A memory can store user data corresponding to the user and can include historic interaction points. A behavior pattern can be identified based on two or more interaction points stored in the user data. An intent of the user based on the behavior pattern can be identified. The intent can be based on a previous behavior pattern of another user. Several probabilities that the user will meet one or more objectives can be determined based on the intent. The probabilities can be scored using and used to assign a policy to the first user. A next action can be recommended based on the policy and executed with respect to the user. The outcome of the recommended next action can be stored to the user data.

Abstract: The present specification provides, amongst other things, a computing network computing optimization and method that can select and generate a digital redirect token for association with content that includes a proposed travel schema with an affiliation with the content.

Abstract: Disclosed embodiments may include a method for generating meal recommendations by receiving first data and user input data. The system may generate a food profile and estimate of ingredients based on the first data and the user input data. The system may generate, based on the estimate of ingredients, one or more cooking instructions or an output that the user does not have sufficient ingredients. If cooking instructions are generated, the system may generate and transmit a graphical user interface comprising the one or more cooking instructions based on the estimate of ingredients for display. If it is determined the user does not have sufficient ingredients, the system may generate and transmit a graphical user interface comprising one or more dining options for the user for display.

Abstract: Technology is described for providing electronic advertisements on an aircraft. A server onboard the aircraft may receive a notification that a public announcement is occurring on the aircraft. The server may identify an announcement tag associated with the public announcement. The server may select an electronic advertisement based in part on the announcement tag associated with the public announcement. The electronic advertisement may be selected from a data store of electronic advertisements. The server may send the electronic advertisement to a client device to be displayed via a graphical user interface on the client device after the public announcement is finished.

Abstract: A purpose of the present invention is to achieve highly accurate optimization for a submodular function when a policy is optimized without preparing data for machine learning. An optimization apparatus (100) according to the present invention includes a determination unit (110) that determines one or more execution policies from a predetermined policy in an objective function having diminishing marginal utility and convexity, a reward acquisition unit (120) that acquires reward, which is an execution result in the objective function for the determined execution policy, a calculation unit (130) that calculates an update rate of the policy based on the reward, and an update unit (140) that updates the policy based on the update rate.

Abstract: Methods, configured mobile devices, and computer-readable media for displaying content on mobile devices are disclosed. An exemplary method of displaying content on a mobile device includes receiving a first content request provided by a native app that closed and that is executing on one or more processors of the mobile device; responsive to receiving the first content request, determining whether the native app is permitted to display app content on a screen of the mobile device while the native app is closed, wherein said determining includes examining at least one of: mobile device location, mobile device motion, and date/time; and in the event that the native app is permitted to display app content on the screen of the mobile device while the native app is closed: transmitting a second content request to a content server; receiving app content from the content server in response to the second content request; and displaying the app content on the screen of the mobile device.

Abstract: A system can be configured to provide an advertiser budget control system designed to work within the confines of a privacy preserving content delivery environment intended to reduce or eliminate third-party cookies. This system uses a control system, a PID controller and duty cycle, to control budget delivery to place content within a browser. The control system can be used to stably deliver budget with real-time delivery rate updates while also preventing over-spending of budget.

Abstract: Systems and methods for automatically determining and providing digital advertisements with ensured relevancy to a search query are disclosed. In some embodiments, based on historical user session data, a query is determined to be a head query, torso query, or tail query. For each sponsored item, a relevance score is generated to represent a degree of relevancy between the sponsored item and the query, and it is determined whether the sponsored item is eligible to be recommended in response to the query based on: (a) comparing the relevance score to a first threshold when the query is a head or torso query, or (b) comparing the relevance score to a second threshold when the query is a tail query. Based on all sponsored items that are eligible to be recommended, a ranked list of recommended items is generated for display based on an auction mechanism.

Abstract: Technology is disclosed for facilitating and processing cross-merchant promotions. In examples, the disclosed technology comprises identifying a first merchant and a second merchant as complementary merchants based at least in part on first transaction data associated with a plurality of merchants; generating a recommendation for the first and second merchants to participate in a cross-merchant promotion; receiving an indication that the first merchant and the second merchant intend to participate in the cross-merchant promotion; receiving second transaction data for a second transaction of the first merchant; applying the cross-merchant promotion to the second transaction based at least in part on a payment card number offered for payment in the second transaction; processing payment for the second transaction based at least in part on the cross-merchant promotion; and apportioning the payment between the first and second merchant according to an agreement between them.

Abstract: The present application describes systems, methods and devices for creative asset management, some of which can be utilized in closed/batch supply and/or open real-time bidding (RTB) supply opportunities. The present application further describes systems, methods and devices for omni-channel creative asset management that may have bi-directional features. In particular, in some embodiments, the creative asset management systems, methods, and devices described herein can allow advertisers to consolidate their online advertising efforts into a central platform.

Abstract: Systems and methods for displaying mobile ads on a mobile device of a user are disclosed. In various embodiments, a mobile application (app) is provided to the mobile device for installation, where the mobile app is configured to display mobile ads to a device screen of the mobile device. A server communicatively coupled to the mobile device tracks a reward associated with the user where the reward is based on enabling the mobile device to receive mobile ads. The server transmits one or more mobile ads to the mobile device, which, upon receipt at the mobile device, causes the mobile app to display the one or more mobile ads outside of the mobile app.

Abstract: A customer service system for providing customer service using a robot for customer service is provided. A first acquisition unit acquires first information regarding a topic provided by a person in charge of response in a negotiation between a visitor and the person in charge of response. A second acquisition unit acquires a detection result regarding speech and behavior of the visitor by the robot. An estimation unit estimates a reaction of the visitor on a basis of the detection result acquired by the second acquisition unit. An output unit outputs second information regarding the reaction estimated by the estimation unit.

Abstract: In one embodiment, an analytics tracking system is disclosed that comprises an interface in electronic communication with one or more consumer devices configured to enable a corresponding consumer to access the interface via a mobile application. The system further comprises a consumer data store comprising data regarding at least one consumer, a movement data store comprising data regarding locations and/or movement of the at least one consumer, and an online behavior data (OBD) data store comprising data associated with browsing and/or application data histories of the at least one consumer. The system further comprises a dynamic analysis system configured to analyze data from the consumer data store, the movement data store, and the OBD data store to generate at least one of custom information for the at least one consumer or identify a location for presentation of information to the at least one consumer.

Abstract: Systems and methods for assessing quality of and detecting defects in retail products include a housing having an interior, a product holding surface, an image capture device configured to capture an image of the product, a lighting element configured to provide lighting within the housing, an electronic database configured to store electronic data including reference image data associated with the product and representing the product in various sizes and various quality states, and a processor-based control circuit in communication with the first image capture device and the electronic database. The control circuit is configured to obtain image data representing the image of the product, obtain the reference image data, analyze the image data and the reference image data to identify the product and identify a size of a defect present on the product, and output a notification indicating whether or not the product is of acceptable quality.

Abstract: A system and process to create a lookalike model for a target audience to deliver advertisements are disclosed. According to one embodiment, the method comprises selecting survey data from a survey database that relates to an advertisement. A heterogenous treatment effect (HETE) model is trained on the survey data. Persuadable customers are identified from the survey database for the advertisement based on the HETE model. An optimized customer list is generated using personally identifiable information.