Abstract: Various examples are directed to computer-implemented systems and methods for providing a triage tool for investment advising. A method includes displaying, by a processor of a computer, an image on a graphical user interface (GUI) of a device of a user. The image includes information related to financial account management for the user. Input options are provided to the user on the GUI including at least two directional swipe input options to obtain the user's positive or negative response to the image. The processor receives the user's response to the input options, and determines a profile of the user based on the user's response to the input options. The processor provides directed financial investment advice and tailored financial products, based on the profile of the user, to increase applicability and effectiveness of wealth management for the user.

Abstract: Off-policy evaluation of a new “target” policy is performed using historical data gathered based on a previous “logging” policy to estimate the performance of the target policy. An estimator may be used, wherein either a quality-based estimator or a quality-agnostic estimator is used to weight the difference between an observed reward in the historical data and an estimated reward generated by the target policy. A quality-agnostic estimator may be used to evaluate an importance weight according to a threshold. In such examples, when the importance weight exceeds the threshold, the quality-agnostic estimator clips the importance weight at the threshold, thereby providing an fixed upper bound irrespective of the quality of the reward predictor. In other examples, a quality-based estimator is used, in which an upper bound incorporates the quality of the reward predictor in order to modify an importance weight used by the estimator.

Abstract: Certain aspects of the present disclosure provide techniques for vectorization of transactions including: receiving electronic transaction information of one or more transactions of a user; for each transaction of the one or more transactions: segmenting the electronic transaction information of the transaction into one or more transaction words; generating a second transaction description related to the transaction; and identifying a category of the transaction; generating, based on the corresponding identified categories of the one or more transactions, a set of transaction history data of the user; providing the set of transaction history data of the user as an input to a machine learned model trained to output a set of word embedding vectors; determining, based on an output of the machine learned model comprising a set of word embedding vectors, a set of similar merchants; and providing the set of similar merchants for display to the user.

Abstract: Aspects of the present disclosure involve a system and method for malware detection. The system and method introduce a probabilistic model that can observe user transaction data over a predetermined window of time. Then, using posterior probability, the system can determine whether multiple users where present during the window observed.

Abstract: Disclosed are example methods, systems, and devices for integrating payment API services provided by a service provider computing system with a client application. The client application running on a user device may allow a user to make payments and/or to submit payments for approval and may communicate payment information to a client computing system. If a payment is submitted for approval via the client application, the client computing system may make API calls to the service provider computing system to, for example, submit, view, and/or cancel payments. Payments may be approved by a second user using a second device. The service provider computing system initiates fund transfers for approved payments. Payments may be submitted within the operating environment of the client application without use of an application or website of the service provider.

Abstract: Methods and systems are disclosed for generating recommendations for causes of computer alerts that are automatically detected by a machine learning algorithm are described. For example, the system may receive a first feature vector with an unknown alert status, wherein the first feature vector represents values corresponding to a plurality of computer states in a first computer system. The system may input the first feature vector into an artificial neural network, wherein the artificial neural network is trained to detect a known alert status based on a set of training data comprising labeled feature vectors corresponding to the known alert status, and wherein the artificial neural network is trained to detect conditional expectations the plurality of computer states in an inputted feature vector.

Abstract: The present disclosure generally relates to user interfaces for managing peer-to-peer transfers. In some examples, a device provides user interfaces for initiating and managing transfers. In some examples, a device provides user interfaces corresponding to completed transfers. In some examples, a device provides user interfaces for providing visually distinguishable message object appearances based on message designation. In some examples, a device provides user interfaces for activating accounts for accepting and sending transfers. In some examples, a device provides user interfaces for exchanging accounts for use in a transfer. In some examples, a device provides user interfaces for splitting transfers between two or more accounts. In some examples, a device provides user interfaces for generating and displaying a transfers history list. In some examples, a device provides user interfaces for voice-activation of transfers.

Abstract: A computer-implemented method and system for automating electronic content delivery of predictive information to a customer service representative of a company. A first customer data set is entered in the computer system for identifying a customer. Displayed on a first desktop on a representative's computer system is information related to the customer which may include purchased company products and services of the customer based on the first data set. A second data set is entered in the computer system by the representative contingent upon interaction between the representative and the customer. Perform predictive analytics upon at least a portion of the first and second data sets to determine predictive information relevant to the customer. Display on a second desktop on the representative's computer system the predictive information for review by the representative during an interaction with the customer.

Abstract: Systems and methods for fleet forward energy and energy credits purchase are disclosed. An example transaction-enabling system may include a resource requirement circuit to aggregate a resource requirement for a fleet of machines to perform a task; a forward resource market circuit to access a forward market for energy; and a machine resource acquisition circuit to execute a transaction on the forward market for energy in response to the aggregated resource requirement.

Abstract: Various aspects of the disclosure relate to using a verifiable and distributed encoding as a digital currency (e.g., cryptocurrency). According to some embodiments, systems and methods can be executed to transfer cash or “hard” currency responsive to exchange of cryptocurrency supported by blockchain technology. In further example, the systems and methods are tailored to operate within a specified/defined community that ensures the efficient operation of the system by ensuring liquidity of the transfer. According to one embodiment, the system is configured to distribute stable coin, issuing the coin at a discounted value (e.g., relative to a redemption or cash equivalent face value). For example, by issuing coin at a discount the system automatically facilitates peer-to-peer physical cash transfers.

Abstract: Technologies are generally described for context sensitive display of information on a consumable delivery vehicle with en route preparation. An on-board controller may receive different sets of sensor data associated with time, location, temperature, humidity, captured images, and/or captured audio from sensors on the vehicle or at a destination location. The sensor data may be analyzed/processed at the on-board controller or by a remote control system and instructions may be generated for display of context sensitive information based on received sensor data and/or processed sensor data. One or more displays on the vehicle may display images are associated with a branding, a menu, a pricing, and/or an advertisement based on the generated instructions.

Abstract: Systems and methods are disclosed for payment system that uses one-time use tokens for securely facilitating and controlling user purchases using company funds. A user (e.g., driver) may generate a request to make a purchase using a user application. The request may be sent to a server running a payment system that may generate a one-time use token for the purchase of an item (e.g., fuel). The one-time use token may have an expiration time and may only be redeemable at certain locations (e.g., fueling stations) that have been preapproved. The system may send the user application running on the user device the token for purchasing fuel and approved locations. The user may input the token to a controller at an approved location which may request that the server authenticate the token and approve the purchase. Once authenticated and approved, the controller may permit the purchase of the desired item.

Abstract: Methods and systems are employed for completing a transaction via an internet-connected vehicle by leveraging a multi-factor authentication to compare vehicle identification information and user identification information based on stored information. In addition, methods and systems are provided for completing a transaction via an internet-connected vehicle by automatic enforcement of business rules (e.g., parental control spending tools, or employee spending tracking tools).

Abstract: A system and method for checking the sanction status of an entity to determine whether the entity is prohibited from engaging in transactions with an organization. The system and method include receiving a request to form an agreement between an organization and an entity and maintaining, in a sanctioned entity blacklist, associations between a plurality of entities and a plurality of identifiers. Each identifier of the plurality of identifiers indicates that a respective entity of the plurality of entities has sanctioned entity status prohibiting the respective entity from engaging in a transaction with one or more organizations. The system and method include determining a sanctioned entity status associated with the entity based on a digital certificate and the sanctioned entity blacklist. The system and method include generating, responsive to determining the sanctioned entity status associated with the entity, an error condition indicating that the digital certificate failed validation.

Abstract: A system and method according to which a donation transaction is conducted. The method includes providing, via a network, an embeddable form, wherein the embeddable form is associated with a non-profit, and wherein the embeddable form is adapted to be displayed on a graphical user interface to receive payment data and payment metadata associated with the payment data. The method also includes: transmitting, via the embeddable form and the network, the payment data to a third-party server for tokenization of the payment data; receiving, by a software development kit (“SDK”) and via the network, a unique token associated with the payment data, and the payment metadata associated with the payment data; executing, by the SDK, the donation transaction in accordance with the unique token and the payment metadata; and storing, by the SDK, the unique token associated with the payment data and the payment metadata.

Abstract: In some examples, a computer-implemented method of managing an advertising exchange is provided. The method uses email data and provides an interactive user interface for controlling management of data in an email channel. One or more inputs of online audience data is received. The online audience data includes email channel inventory from multiple publishers, Offline audience data including offline shopping behavior is sourced from at least one or more offline source. The online audience data and the offline audience data is included in a unified customer database, and the interactive user interface includes interface elements selectable to present online and offline audience data sourced from the unified customer database.

Abstract: A computer-implemented method of continuously updating information about a customer approved for a mortgage, the customer associated with a customer identification number. In one aspect, the method may include monitoring information accessed from a blockchain corresponding to the customer identification number, the information used to determine the customer is approved for a mortgage. In addition, the method may further include receiving new information about the customer, the new information used to determine the customer is approved for a mortgage. Further, the method may include updating a block of the blockchain to include the new information and recalculating the amount in which the customer is approved for a mortgage based upon the new information received.

Abstract: Systems and methods using IOT input to validate a loan guarantee are disclosed. An example system may include an Internet of Things (IoT) data input circuit to interpret a loan guarantee parameter; an IoT data collection circuit to collect data using at least one algorithm that is configured to monitor IoT information collected from and about an entity involved in a loan in response to the loan guarantee parameter; and a guarantee validation circuit to validate a guarantee for the loan in response to the monitored IoT information.

Abstract: Disclosed are systems and methods for mitigation of fraudulent transactions. In some embodiments, a server is communicatively coupled to a user device, and is configured to receive a proposed transaction from a merchant device communicatively coupled to the server, apply a dynamic classification algorithm to the proposed transaction to determine if the proposed transactions appears to be fraudulent, generate a user verification request when the proposed transaction appears to be fraudulent, transmit the user verification request to a user computing device communicatively coupled to the server, receive an approval or a refusal of the proposed transaction based on the user verification request, and process the proposed transaction based on the received approval or refusal of the proposed transaction.

Abstract: A payment reader can have one or more kernels capable of performing certain payment processing functions but not capable of performing certain, more processing-intensive payment processing functions. The payment reader may be designed to selectively assign processing tasks to application layer kernels located on a mobile device and/or a cloud-based device external to the payment reader, the mobile device having more or different processing resources than the payment reader. The selective assignment may be made dynamically based on the measurement of a condition of the reader or an occurrence of an event, such as a determination that the payment reader cannot process a transaction, that the payment reader does not have sufficient battery strength to process the transaction, or that there has been a tampering attempt at the payment reader. The payment reader also has a physical layer module, which module maintains its processing on the payment reader.