Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for selecting a routing provider that is best suited to deliver each individual message. The message exchange system selects a routing provider based on customer criteria provided by the customer, bids provided by the routing providers and/or performance of the routing providers. The message exchange system ranks the bids based on a ranking value calculated for each bid based on the cost value associated with the bid, the quality score of the associated routing provider and the customer criteria. The message exchange system selects a bid based on the resulting ranking values. For example, the message exchange system selects the bid that is ranked the highest based on the ranking values. The message exchange system then transmits the message to its intended recipient via the routing provider associated with the selected bid.

Abstract: A method, system, and computer program product for representational learning of product formulas are provided. The method accesses a set of product formulas. Each product formula includes a set of ingredient tuples. A directed graph is generated from the set of product formulas. The directed graph including a node for each ingredient of the sets of ingredient tuples of the set of formulas. The method generates a weighted graph from the directed graph. The weighted graph has a weight assigned to each edge in the directed graph. The method generates an embedding model based on the directed graph. A set of embeddings is determined for the weighted graph where each node is represented with low-dimensional numerical vectors.

Abstract: Implementations set forth herein relate to systems, methods, and apparatuses for operating applications that allow users to indicate their willingness to provide items and/or services to other users and/or a third party. When an item is indicated as available for requesting, and an item is thereafter requested by a requesting user, a server device can cause instances of an item transferring application to provide a corresponding indication to item transferring users within a certain context. Values can be submitted by item transferring users, based on their current context, in furtherance of providing services that facilitate transfer of an item from an item creating user to an item requesting user. Other values can be submitted by the item transferring users in furtherance of characterizing a task of transferring items from a third party entity, who may not be accessing an associated application, to an item requesting user.

Abstract: The present disclosure relates to a recommender system and method. Unlike known systems, which learn neural network parameters during training and fix the input vectors, the recommender system learns both the input vectors and machine learning model parameters during training. In one embodiment, the initial user and item input vectors are interaction vectors that are based on known and unknown user feedback. The non-zero elements of the interaction vectors correspond user-item pairs for which feedback is known, and the zero elements corresponding to user-item pairs for which feedback is unknown. The non-zero elements of the interaction vectors are learnable parameters during the training phase. The user and item vectors, as well as the model parameters, learned during the training phase are used in a prediction and recommendation phase to make product recommendations for a user.

Abstract: A computer system and method for transacting business over the Internet relating to vehicle purchasing. A first computer data base is provided having information regarding vehicles for sale wherein each vehicle has associated vehicle data parameters and a second computer data base is provided having information regarding a user wherein each user has associated user data parameters. A vehicle purchase server is provided that includes application software including a routine permitting the selection of specific vehicle data parameters from the first data base contingent upon user data parameters contained in the second data base based upon inquiries from a user regarding a vehicle description. Vehicle matching results including one or more vehicles recommended for the user are presented via a GUI accessible by the user.

Abstract: A result ranking system can include a computing device that is configured to obtain a plurality of items based on a query and a value corresponding to each item of the plurality of items. The computing system can also be configured to retrieve a value distribution corresponding to the query and generated based on customer interaction data. The computing system can also, for each item of the plurality of items, determine a feature value based on the value distribution and the corresponding value of the item. The computing system can be further configured to transmit the plurality of items to a customer device for display in an arrangement based on the corresponding feature value.

Abstract: A system may a processor that may receive image data of a vehicle via one or more image sensors and retrieve vehicle data regarding the vehicle from a vehicle database based on the image data. The vehicle database may include a first set of data regarding a plurality of vehicles. The processor may then retrieve financial data regarding a user from a financial database, such that the financial database includes a second set of data regarding financial information concerning the user. The processor may then determine one or more financial products associated with a purchase of the vehicle, generate one or more visualizations representative of the one or more financial products, and modify the image data depicted on a display to include the one or more visualizations.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing programs and methods for performing operations comprising: receiving a request from a client device of a first user to engage in a shared virtual reality shopping experience with a second user; generating, for display on respective client devices of the first and second users, the shared virtual reality shopping experience comprising a plurality of virtual reality items that represent real-world products; receiving, from the client device of the second user, data indicating a selection of a first virtual reality item of the plurality of virtual reality items made by the second user; and modifying a display attribute of the first virtual item in the display of the shared virtual reality shopping experience on the client device of the first user to indicate the selection of the first virtual reality item made by the second user.

Abstract: A content delivery system consolidates aggregates and analyzes content. Content may be construed broadly, such as text, video, audio, merchandise, news, bands, festivals, venues, release dates, concerts, performances, etc. The system may obtain content, filter content and/or apply preferences and/or analytics to determine a particular content. Analytics may include various content matching processes, such as hashing, for example. A notification may be generated based on the particular content and the notification may be sent, to a user's portable device for example. An aggregation application on the portable device may present an indication of the notification and response to selection of the notification. For example, the aggregation application may display the content associated with the notification. The aggregation application may track the user's behavior and update various analytics based on the tracking information.

Abstract: A system includes a processor configured to wirelessly receive vehicle usage data. The processor is also configured to aggregate received data over time. The processor is further configured to classify vehicle usage into a predetermined category based on the aggregated received data. Also, the processor is configured to access a set of maintenance recommendations associated with the predetermined category and send a maintenance recommendation based on a correspondence between the aggregated data and a value associated with one of the maintenance recommendations.

Abstract: A system includes software that allows users to use one or more sources of sizing information to make purchasing decisions. The system uses three-dimensional (or 3D) scans of customers to make apparel recommendations. The 3D scans are compared to sizing information in the system, to determine which products are most suitable for the customer. Sizing information the system can use are information from manufacturers as well as sizing feedback from previous customers.

Abstract: A computer implemented method of image analysis is disclosed. The method comprises receiving, from a first computing device associated with a first human user, a communication indicating that the first human user has selected one or more items for purchase and has purchased the items; receiving, from the first computing device, identifying information of the items; identifying one or more merchants offering the items for sale; receiving one or more images depicting the first human user using the items; after receipt of the images, automatically determining, based on visual characteristics of the images, that the items are depicted in the images; and transmitting, for display to the second human user, an automatically generated augmented graphical user interface comprising the images and hyperlinks that convey the second human user to a merchant website allowing the second human user to purchase the items from the merchants.

Abstract: An approach to facilitating pricing of virtual containers is provided. Item prices associated with obtaining item instances of virtual items in a game space may be determined. Probabilities that container instances of virtual containers will provide individual ones of the item instances of the virtual items upon activation by users in the game space may be determined. Container prices to be associated with obtaining the container instances of the virtual containers may be determined based on the determined item prices and/or the determined probabilities. A store interface may present offers to the users to purchase the container instances of the virtual containers at the determined container prices.

Abstract: Techniques are described for generating transaction data for a transaction, the transaction data generated with varying fidelity levels based on various constraints. In response to a transaction request from a client, a contract engine may perform service call(s) that instruct network service(s) to generate transaction data. The service call(s) may include constraint(s) on the generation of the transaction data, such as a time limit or a requested fidelity. The network service(s) may generate the transaction data at a particular fidelity based on the time limit, requested fidelity, or other criteria such as current load on the network service(s). The transaction data may be communicated to the contract engine with a fidelity indicator. Lower fidelity transaction data may be sent to the client to enable a low latency user experience. The lower fidelity transaction data may subsequently be replaced with higher fidelity transaction data generated with higher latency.

Abstract: A method and system for improved management of a purchase order comprises searching online for at least one product or group of products similar to each other to be ordered from a generic supplier and obtaining a confirmation of availability. The step of searching for the product to be ordered from the generic supplier can be extended to search for the product or the group of products or alternative products available at at least one alternative supplier. The product or group of products or the alternative products found at the alternative supplier are inserted into a shopping cart of the alternative supplier and compared with the product or the group of products of the generic supplier. The extension of the search is started automatically by a search and compare software application authorized by the user and provided by the alternative supplier.

Abstract: Methods, systems, and apparatuses are described herein for providing purchase recommendations by analyzing social networks using machine learning. A machine learning model may be trained to select one or more of the first plurality of users. Purchase intention data that indicates an intention of a first user to acquire a type of asset may be received. Social networking data that comprises a plurality of associations between a second plurality of users may be received. Purchase history data indicating one or more purchases, of one or more assets associated with the type of asset, made by the second plurality of users may be received. The trained machine learning model may be provided the data. In return, the trained machine learning model may provide an indication of a second user. A notification may be sent to the second user.

Abstract: A content delivery system consolidates aggregates and analyzes content. Content may be construed broadly, such as text, video, audio, merchandise, news, bands, festivals, venues, release dates, concerts, performances, etc. The system may obtain content, filter content and/or apply preferences and/or analytics to determine a particular content. Analytics may include various content matching processes, such as hashing, for example. A notification may be generated based on the particular content and the notification may be sent, to a user's portable device for example. An aggregation application on the portable device may present an indication of the notification and response to selection of the notification. For example, the aggregation application may display the content associated with the notification. The aggregation application may track the user's behavior and update various analytics based on the tracking information.

Abstract: Systems and methods to provide transaction-related insight information for an establishment. In some aspects of the present disclosure, a digital image captured at a location of a user can be received. The digital image can be analyzed to identify an establishment. Transaction data between customers and the establishment can be retrieved. Transaction-related insight information about the establishment can be generated based on the data. The transaction-related insight information can be provided to the user.

Abstract: Provided are various mechanisms and processes for generating dynamic merchant similarity predictions. In one aspect, a system is configured for receiving historical datasets that include a series of merchants from historical browsing sessions generated by one or more users. The merchants are converted into corresponding vector representations for training a predictive model to output associated merchants based on a generated weighted vector space. Once sufficiently trained, data from a new browsing session may be received, which may include a target merchant. The target merchant is input into the predictive model as a vector to output one or more context merchants having vectors with the highest cosine similarity value to the target merchant vector. Selected context merchants may then be transmitted to the user device as targeted merchant suggestions in the new browsing session. The predictive models may be continuously trained using data received from subsequent browsing sessions.

Abstract: Systems and methods are disclosed for providing purchase recommendations. According to some examples, a method may include: determining a set of vehicle characteristics represented in a candidate set of vehicles; for each vehicle characteristic in the set of vehicle characteristics, determining a percentage of the candidate set possessing the respective vehicle characteristic; selecting, from the set of vehicle characteristics, a vehicle characteristic based on a proximity of the respectively determined percentage to 50%; transmitting, to a user device associated with a user, an inquiry for a user preference regarding the selected vehicle characteristic; receiving, from the user device, a response indicating the user preference regarding the selected vehicle characteristic; excluding vehicles from the candidate set based on the indicated user preference to obtain a reduced candidate set; and transmitting, to the user device, a recommendation of one or more vehicles from the reduced candidate set.