Abstract: Systems and methods are described for facilitating payments and transactions using social background checks. Such systems and methods may use social networks with both individual members communicating over a network to a social authentication computing system. The authentication of transactions associated financial institutions are determined through the use of relationship measures based on social media interactions. Transactions and services available to a user are determined based on a measure of social identity through the use of social media platforms. Available contact and interaction data from one or more social media platforms is leveraged to analyze a level of trust that a transaction is not a consequence of fraudulent activity. Transactions that have a low level of risk of being a consequence of fraudulent activity are benefited through faster transaction times and other improvements.

Abstract: A method, apparatus, and computer program product for establishing an authenticated online session are provided. An example method includes receiving a request for an authenticated online session and causing, by display circuitry, presentation of an input pattern to a user. The method further includes receiving, by gaze detection circuitry, one or more images of the user's eye captured during presentation of the input pattern, and determining, by the gaze detection circuitry, an identification code represented by the one or more images. The method also includes receiving, by contextual evaluation circuitry, contextual device data of a user device associated with the user during presentation of the input pattern. The method further includes establishing, by authentication circuitry, the authenticated online session based upon the identification code and the contextual device data.

Abstract: A financial system receives a transaction request and transmits a one-time passcode to a consumer associated with the transaction request. Transmission of the one-time passcode is typically via a first channel. If the system determines that the one-time passcode was not delivered, a second channel is utilized. Depending upon the success of delivering the one-time passcode, more than one type of communication channel can be used.

Abstract: Various examples described herein are directed to systems and methods for managing multi-party transactions. A payment management system may receive a premium payment message from a user computing device. The premium payment message may describe a premium payment towards a health insurance policy held by a user of the user computing device. The payment management system may initiate a deposit of the premium payment to a premium account associated with the user. The payment management system may also receive a payment instruction from a payer system of a payer associated with the health insurance policy. The payment management system may select a first patient payment source and initiate a transfer of a payment amount to a provider.

Abstract: A method may include receiving a data file including a plurality of tuples, each respective tuple including a username and password; matching a username from a tuple in the data file to a username of an account stored in an account database; determining that the password from the tuple matches a password for the account; in response to the determining indicating a match, setting a security flag for the account identifying the account as compromised; subsequent to the security flag being set, receiving a login request with validated credentials for the account from a computing device; and in response to the login request, transmitting a request to the computing device to modify the password for the account.

Abstract: Various examples are directed to systems and methods for interfacing a computing system to a human user. For example, a graphical user interface may be provided to a user. The graphical user interface comprises a holding shape and a first income source shape indicating a first income source. The holding shape comprises a filled portion having a first filled portion level indicating a first holding balance of an account of the user. A first deposit shape may be moved from the first income source shape towards the filled portion of the holding shape. The first deposit shape may indicate a first deposit to the account from the first income source. The filled portion may be resized to a second filled portion level indicating a second holding balance of the account after the first deposit.

Abstract: Systems and methods for generating bill pay requests via an internet-enabled video displaying device are described. The transaction generating system presents users with the option to generate a bill pay request to vendors of products and/or services while the user is passively consuming video content. As video content relating to a given product or service is displayed, a notification invites the user to generate a bill pay request. The user can then use the internet-enabled video displaying device to generate and send a request to transfer funds to the vendor.

Abstract: A method may include retrieving from a data store default values of intersections of a first type of characteristic of an entity and a second type of characteristics of the entity; presenting a first portion of a user interface on an electronic display device, the first portion of the user interface including an initial matrix of: a plurality of rows, a plurality of columns, wherein, the rows columns intersect to form a plurality of cells and the cells are populated with values based on the retrieved default values. The method may further include receiving a maturity value; calculating a weighted matrix of values based on the received maturity values; applying the weighted matrix to the values of the cells in the initial matrix to generate adjusted values for each of the cells in the initial matrix; and presenting an adjusted matrix based on the adjusted values.

Abstract: Distributed firewalls reside at different points across a network. Each distributed firewall can include one or more rules that govern traffic over and/or access to the network. The rules can be discovered, converted into a standardized format, and indexed at a centralized rule database. The rules or data of the rules can be verified. The rules can be certified at the centralized database. The certification process can be based on a direction of traffic to which the rule governs. The certification process may have different levels based on the direction of traffic.

Abstract: Systems and techniques for an artificial intelligence natural language processing platform are described herein. A first dialogue configuration ruleset may be obtained for a first intent for a first entity. First user input may be received that includes a first text string from a chatbot session. The first intent may be identified from the chatbot session through evaluation of the first text string by a natural language processing engine using the first dialogue configuration ruleset. A dialogue stack may be generated for the chatbot session that includes a first state based on the first dialogue configuration ruleset. A first response to the first user input may be displayed based on the first dialogue configuration ruleset. The dialogue stack may be updated based on the first response.

Abstract: An approach for establishing and managing authentication circles is disclosed. The circles may be used to facilitate management of accounts, goals, or resources of one or more entities, or to provide an integrated view of the circumstances of, for example, family members or other interrelated persons. A person receiving assistance with the management of one or more accounts need not disclose authentication credentials to persons helping manage the accounts, enhancing security. Members may view members and access accounts administered by separate computing systems without needing credentials for each member, account, and/or computing system. The multiple accounts (which may be held at multiple institutions) need not be accessed individually by each member of the authentication circle, saving time and computing resources of users.

Abstract: Systems and methods relating to settlement of securities without revealing ownership including the end owner are described. In some implementations, ownership or control of a security may be managed by using group membership technology to revoke the signing rights of the seller and adding signing rights to the buyer. Group membership with group signatures allow for one group public key and a plurality of private keys, where each private key is associated with a group member. Signatures create by different group members are indistinguishable to verifiers but a group manager is able to determine which member has signed, link member signatures, implement controls and/or limits, and revoke and add signatory capability when needed. In some implementations, revocation of signatory capability is done with the cooperation of a Digital Certificate Authority.

Abstract: A method may include receiving data from a computing device requesting approval of a loan application; accessing time-series data associated with the user from a knowledge graph; building a feature vector based on the accessed time-series data; inputting the feature vector into a machine learning model; receiving a response from the output from the machine learning mode, the output indicating a level of approval for the user with respect to the loan application; and transmitting a response to the request based on the level of approval.

Abstract: In an example, a computer-implemented method includes determining a set of permissions that specifies types of account data of one or more financial accounts to share with a third-party, the one or more financial accounts being associated with a user and held by a financial institution, and generating authorization data that authenticates the third-party and authorizes the third-party to access the types of account data specified by the set of permissions. The method also includes transmitting the authorization data to the third-party, receiving a request for authorization that includes the authorization data and a request for account data of the one or more financial accounts that conforms to the types of account data specified by the set of permissions, authorizing the third-party based on the authorization data, and transmitting the account data that conforms to the types of account data specified by the set of permissions.

Abstract: Techniques are described for providing insurance coverage for a virtual wallet stored on a computing device. The virtual wallet has a value equal to a sum of assigned values of a plurality of virtual financial assets included in the virtual wallet. A user of the computing device purchases an insurance policy for the virtual wallet with an insured amount based on the value of the virtual wallet. The computing device is configured to send messages to an insurance server reporting an updated value of the virtual wallet based on changes to the assigned values of the virtual financial assets. The insurance server updates the insured amount of the insurance policy based on the updated value of the virtual wallet. Upon the virtual wallet being compromised, the insurance policy has an insured amount equal to the most recent updated value of the virtual wallet.

Abstract: Techniques are described for evaluating message content in each of a plurality of messages in order to improve communication between customers and customer service representatives. The disclosed techniques enable efficient evaluation of the message content in each of the messages in order to determine a readability score for each of the messages. A computing device performs the efficient evaluation by processing the message content into a binary representation using a first value to represent vowels and a second value to represent non-vowels. The binarization of the message content allows the computing device to perform a syllable count and determine a readability score for each of the plurality of messages, which may include millions of messages. Based on the readability scores, the computing device may identify readability gaps between the representative messages and the customer messages, and generate subsequent representative messages that reduce the identified readability gaps.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for session authentication. An example method includes determining, by decoding circuitry, a set of optical path lengths to use for measurement. The example method further includes receiving, by the decoding circuitry, a set of time-bin qubits. The example method further measuring, by the decoding circuitry and based on the determined set of optical path lengths, the set of time-bin qubits to generate a set of bits. The example method further includes generating, by session authentication circuitry, a session key based on the generated set of bits.

Abstract: The described financial institution computing system provides services to customers through an application programming interface (“API”). The services include user identification services to customers. The user identification services allow the customers to verify the identity of users as non-fraudulent users. Further the user identification services allow the financial institution to provide known user information to the customers for purposes of prepopulating registration forms, completing transactions, and the like. Further services, such as user account validation services, payment services, and the like are also possible through the financial institution APIs. In some situations, users are registered with the financial institution. For example, a user may also be an account holder with the financial institution. In other situations, the users are not registered with the financial institution.

Abstract: An example method is described. The method includes receiving, by a computing system, data indicative of a call into an interactive voice response (IVR) system from a user device and determining, by the computing system and based on the data, a set of actions performed by the user device within the IVR system and a corresponding set of results performed by the IVR system during the call. Additionally, the method includes converting, by the computing system, the set of actions and the corresponding set of results into a sequence of code pairs using a dictionary established based on training data, determining, by the computing system, an activity pattern during the call based on the sequence of code pairs; and calculating, by the computing system, a probability that the call is fraudulent based on the activity pattern during the call.

Abstract: A computer-based credit evaluation system is described that uses a machine learning-based credit risk model with an adverse action methodology to assess applicant credit profiles and identify adverse action factors for credit request denials. The credit risk model is trained to assess an applicant's credit profile based on characteristics. In the case of a denial, the system compares applicant values of the characteristics against anchor values for the characteristics determined based on values from a top scoring credit profile. The system uses the credit risk model to calculate a replacement score for each of the characteristics by replacing the applicant value for the characteristic with an anchor value for the characteristic. The system ranks the characteristics based on the replacement scores, and identifies the top ranked characteristics as the adverse action factors for the denial.