Abstract:
During operation of the system, a user of a portable electronic device provides a request to enroll in a financial service associated with a provider. For example, the financial service may facilitate financial transactions via a financial application that executes on the portable electronic device. Then, an electronic device determines that the user is an existing customer of at least one of a set of financial institutions that have a business relationship with the provider, where the provider is other than one of the financial institutions. Next, the electronic device enrolls the user in the financial service without requesting additional information from the user. By leveraging the business relationship between the user and one of the financial institutions in the set of financial institutions, the user can avoid having to perform a complicated enrollment process in order to start using the financial service.
Abstract:
A method and system detects and addresses abnormalities in a financial management system. The method and system include gathering financial data related to financial transactions of the users of the financial management system and generating profile data related to patterns in the financial transaction data by analyzing the financial transaction data. The method and system further include detecting abnormalities in the financial management system by comparing subsequent financial transaction data to the profile data.
Abstract:
A method and system groups user accounts in a financial management system based on the similarities of the financial transactions associated with the accounts. The financial management system receives financial transaction data related to a plurality of financial transactions of a plurality of users. Each of the financial transactions is associated with an account of a user. The financial management system generates account characteristics vector data including, for each account, an account characteristics vector based on the financial transactions associated with the account. The financial management system groups the accounts by performing grouping analysis on the account characteristics vectors.
Abstract:
A technique for facilitating customization of a software application is described. During this customization technique, an indicator, which indicates that a software application for an electronic device has been discovered by a user, is provided to a publisher of the software application. In response to the indicator, the publisher provides a token to the user. This token identifies a customized application-delivery service for the software application and/or a user-specific customization of the software application. Note that the customized application-delivery service and the user-specific customization are based on information about the user associated with the user's pre-existing or just-established relationship with the publisher. Next, the token is provided to an application-delivery service, and the application-delivery service provides the customized software application to the electronic device or a computer, for example, using the customized application-delivery service.
Abstract:
Aspects of the present disclosure provide techniques for training a machine learning model. Embodiments include determining a set of unlabeled user transaction records associated with a user. Embodiments include selecting a first unlabeled user transaction record associated with a first vendor from the set of unlabeled user transaction records based on a transaction record prioritization scheme. Embodiments include presenting the first unlabeled user transaction record to the user in a label query. Embodiments include receiving, from the user in response to the label query, a label of a first account for the first unlabeled user transaction record. Embodiments include selecting a second unlabeled user transaction record associated with a second vendor from the set of unlabeled user transaction records based on: the transaction record prioritization scheme, and a determination that the second vendor is least likely to be categorized by the user in the first account.
Abstract:
A method and system identify characteristics of financial transaction description strings. The method and system trains a dictionary generation model with a machine learning process to classify financial transaction description strings. The dictionary generation model generates a dictionary that indicates key substrings from the financial transaction description strings that were most predictive in classifying the financial transaction description strings.
Abstract:
During a financial transaction, a customer provides a token that identifies the customer to a peripheral device (which is other than a credit-authorization terminal or a magnetic-stripe reader) coupled to the point-of-sale terminal. Then, a unified point-of-sale service object executing on the point-of-sale terminal, which is a driver for a virtual peripheral device, performs one or more operations based on at least the token to obtain financial information associated with the customer. After providing the financial information and transaction information associated with the financial transaction to a financial institution specified in the financial information, the point-of-sale terminal receives a confirmation from the financial institution that the financial transaction has been completed. For example, the confirmation may be received via a credit-authorization-terminal service object that is a driver for the credit-authorization terminal.
Abstract:
During a security technique, an electronic device determines a name by a applying a function to a shared secret, which is shared between a user and another user. This name is advertised in a network. After discovery by another electronic device (which is associated with the other user), the electronic device generates a first encrypted message from an unencrypted message using a cryptographic key. The electronic device provides the first encrypted message to the other electronic device, and receives a second encrypted message from the other electronic device. Using the cryptographic key, the electronic device decrypts the second encrypted message. Moreover, the electronic device receives confirmation that the other electronic device was able to decrypt the first encrypted message, thereby authenticating that the secure connection has been established.
Abstract:
During a transaction, an electronic device (such as a cellular telephone) captures a gesture performed by a user of the electronic device. This gesture is analyzed to determine salient features, such as accelerations of the electronic device during the gesture and associated time intervals. Then, the electronic device generates a token based on the salient features, and provides the token to a server. When a second token, associated with the token, is received by the server from a second electronic device, the server establishes a secure connection between the electronic device and the second electronic device.
Abstract:
A technique for establishing a common encrypted link between a first electronic device and a second electronic device in physical proximity in a system is described. During operation of the system, a user of a first electronic device in the system provides a notification that initiates secure device pairing. In response to the notification, the first electronic device conducts a first key exchange in an audible audio spectrum to the second electronic device in the system using a first zero-knowledge protocol. After the first key is received by the second electronic device, the second electronic device conducts a second key exchange in the audible audio spectrum to the first electronic device using a second zero-knowledge protocol, thereby establishing the common encrypted link between the first electronic device and the second electronic device.