Abstract: Aspects described herein may allow for authenticating a user by generating a customized set of authentication questions based on patterns that are automatically detected and extracted from user data. The user data may include transaction data collected over a period of time. By automatically detecting user patterns that correspond to user behavior over a period of time, an authentication system may be able to generate information that is recognizable to an authentic user but difficult to guess or circumvent for any other user.

Abstract: Systems and methods for implementing a single step processing for two-step transactions involving an initial and a final amount. The proposed systems and methods incorporates a built-in logical operations and parameter acquisition scheme for identification of two-step transaction and internal computation of the final amount based on user specified logical operations and input parameters. Data values, corresponding to the input parameters, may be dynamically extracted from the transactions string and/or obtained from one or more applications running on the user device, and subsequently, processed with the specified logical operations to generate a final transaction amount from the initial transaction amount referenced in the transaction request. The final transaction amount may then be validated and a single authentication response transmitted to a payment gateway initiating the request.

Abstract: Methods, systems, and apparatuses are described herein for improving the accuracy of synthetic authentication questions by analyzing third party account data. A request for access to a first account associated with a user may be received. The first account may be managed by a first organization. A transactions database might be queried for first account data. Second account data corresponding to a second account associated with the user might be received. That second account may be managed by a second organization different from the first organization. One or more second transactions, unique to the second account, may be identified. A synthetic transaction, configured to be different from transactions in the first account and the one or more second transactions, may be generated. An authentication question may be generated based on the synthetic transaction. Access to the first account might be provided based on a response to the authentication question.

Abstract: Aspects described herein may use a machine learning model to identify transactions likely to be remembered by a user and that may be used to generate challenge questions to authenticate the user. An individual may request an action related to a financial account. In response to the request, the machine learning model may determine a likelihood an authorized user of the financial account will remember one or more recent transactions. The likelihood of each candidate transaction may be compared to a predetermined threshold to determine a subset of recent transactions. Information relating to the subset of recent transactions may be used to generate one or more challenge questions to pose to the user. The user's responses to the challenge questions may be used to evaluate whether the user is the authorized user of the financial account or is a fraudster or imposter.

Abstract: Methods, systems, and apparatuses are described herein for improving computer authentication processes through computer-based authentication in a manner that excludes P2P transactions from being presented in false options presented to users. A computing device may receive a request for access to an account from a user. The computing device may provide transaction data to a machine learning model. The computing device may receive one or more merchant names related to P2P transactions from the machine learning model. The computing device may generate a modified set of false merchant choices for the user by excluding merchants related to P2P transactions. An authentication question may be generated, and access to the account may be provided based on a response to the authentication question.

Abstract: The disclosed technology relates to assessing and securing credit risk using creditworthiness tokens issued in a blockchain network responsive to particular financial events. An exemplary blockchain node device may store an issuance smart contract associated with an identity and including a first wallet address and allocation parameters. An event query may be sent to an oracle device external to the blockchain network. The event query may include the identity. Event data associated with the identity may then be received from the oracle device in response to the event query. A number of creditworthiness tokens is determined based on an application of the allocation parameters to the event data. The determined number of creditworthiness tokens is then allocated to the identity via the first wallet address. Thereafter, the creditworthiness tokens can be transferred or collateralized, e.g., and can represent creditworthiness for the identity across financial institutions.

Abstract: Methods, systems, and apparatuses are described herein for improving the accuracy of authentication questions using e-mail processing. A request for access to an account may be received from a user device. A plurality of organizations may be identified. One or more e-mail associated with the account may be identified. The e-mails may be processed to identify one or more organizations that correspond to transactions conducted by a user. A modified plurality of organizations may be generated by removing, from the plurality of organizations, the one or more organizations. An authentication question may be generated and provided to the user device. A response to the authentication question may be received, and the user device may be provided access based on the response.

Abstract: Systems and methods for identifying malicious cryptographic wallet addresses are disclosed. The systems and methods can receive a first plurality of tokens and an indication of a potentially malicious cryptographic wallet address from a requesting user. The system can identify a plurality of associated wallet addresses, and compare the associated wallet addresses to a stored list of malicious cryptographic wallet addresses. The system can determine a subset of the identified associated cryptographic wallet addresses that are malicious and assign a maliciousness rating to the potentially malicious cryptographic wallet address. The system can provide the maliciousness rating to the requesting user.

Abstract: In some implementations, a system may receive an input indicating an interaction party identifier corresponding to a selected interaction party, wherein a geographic location may be associated with the interaction party identifier. The system may receive aspect preference data indicating one or more aspects to determine a similarity between the selected interaction party and one or more other interaction parties. The system may identify one or more identified interaction parties having geographic locations within a distance threshold of the geographic location associated with the interaction party identifier. The system may use a machine learning model to determine similarity scores for the one or more identified interaction parties based on one or more aspects associated with historical interactions with the one or more identified interaction parties. The system may transmit, to a user device, data indicating one or more similar interaction parties having similarity scores above a score threshold.

Abstract: Aspects described herein may allow for authenticating a user by generating a customized set of authentication questions based on spending patterns that are automatically detected and extracted from user data. The user data may include transaction data collected over a period of time that may indicate the types of merchants that a user frequently transacts with. By automatically detecting user patterns that correspond to user behavior over a period of time, an authentication system may be able to generate authentication questions about those spending patterns that are easily answerable to an authentic user but difficult to guess or circumvent for any other user.

Abstract: Aspects described herein may use a machine learning model to identify transactions likely to be remembered by a user and that may be used to generate challenge questions to authenticate the user. An individual may request an action related to a financial account. In response to the request, the machine learning model may determine a likelihood an authorized user of the financial account will remember one or more recent transactions. The likelihood of each candidate transaction may be compared to a predetermined threshold to determine a subset of recent transactions. Information relating to the subset of recent transactions may be used to generate one or more challenge questions to pose to the user. The user's responses to the challenge questions may be used to evaluate whether the user is the authorized user of the financial account or is a fraudster or imposter.

Abstract: Disclosed herein are system, method, and computer program product embodiments for training and deploying a machine learning model to generate an assessment of risks and mitigations in response to a novel initiative request. After generating labeled data from a corpus of prior risk assessments, a machine learning model may be trained to programmatically generate a risk assessment in response to a novel initiative request. The system may provide for centralized control over the creation, review, and approval of initiative requests. The system may further analyze consumer-facing applications deployed by an organization and train the machine learning model to algorithmically determine consumer-facing applications potentially affected by an initiative request.

Abstract: Disclosed herein are system, method, and computer program product embodiments for training and deploying a machine learning model to generate an assessment of risks and mitigations in response to a novel initiative request. After generating labeled data from a corpus of prior risk assessments, a machine learning model may be trained to programmatically generate a risk assessment in response to a novel initiative request. A risk auditor may subsequently review the risk assessment generated using the machine learning model to provide various feedback reflecting the accuracy of the risks and mitigations. The machine learning model may then be retrained based on the feedback provided by the risk auditor to provide more accurate risks and mitigations in response to future initiatives.

Abstract: Disclosed embodiments may include a method for authenticating calls for a call center where the user can authenticate before or after starting a call to a call center using an application on a user device. The system determines what level of authentication is necessary depending on the task the user wants to accomplish during the call. The system may direct the user to provide credentials, such as a username and password, for some tasks. Other tasks may require the user to verify their financial card by taking a photo of their financial card or tapping their financial card to their device and allow the device to interact with the financial card using NFC technology. Once appropriately authenticated, the system then allows the user to make a call to the call center and also sends a signal to the call center that the user has been previously authenticated.

Abstract: Methods, systems, and apparatuses are described herein for improving the accuracy of authentication questions using e-mail processing. A request for access to an account may be received from a user device. A plurality of organizations may be identified. One or more e-mail associated with the account may be identified. The e-mails may be processed to identify one or more organizations that correspond to transactions conducted by a user. A modified plurality of organizations may be generated by removing, from the plurality of organizations, the one or more organizations. An authentication question may be generated and provided to the user device. A response to the authentication question may be received, and the user device may be provided access based on the response.

Abstract: Aspects discussed herein may relate to techniques for authenticating a user using transaction-based authentication questions. The transaction-based authentication questions may be provided to the user. The user may provide audible responses to the transaction-based authentication questions that may be captured by a smart device, such as an always on listening device. Authentication of the user may be based on voice analysis of the audible responses to the transaction-based authentication questions and/or based on the answers to the transaction-based authentication questions.

Abstract: Methods, systems, and apparatuses are described herein for authenticating access to an account using questions which allow users to provide textual information about transactions conducted by an account. A machine learning model may be trained to predict the guessability of merchants. A request for access to an account may be received, and transaction data for that account may be received. An authentication question may be presented. For example, a user may be prompted to list places they have shopped recently. A user response comprising text data may be received. The text data may be processed to identify one or more merchants. If the one or more merchant(s) are represented in the transaction data, the machine learning model may be used to determine the guessability of the one or more merchants. An authentication score may be determined based on the guessability, and access to the account may be provided.

Abstract: Systems and methods for granting smart contracts is disclosed. A first plurality of tokens representing a vote for a plurality of smart contract validators can be received from a first cryptographic address. The method can include receiving, from each smart contract validator of the plurality of smart contract validators, validation credentials. Each of the plurality of smart contract validators can be validated based on the validation credentials and the first plurality of tokens. a first smart contract and a second plurality of tokens can be received from a second cryptographic address. The first smart contract can be transmitted to at least one smart contract validator of the plurality of smart contract validators. The first smart contract can be validated by the at least one smart contract validator. At least a portion of the second plurality of tokens can be transmitted to the at least one smart contract validator.

Abstract: Systems and methods for identifying malicious cryptographic wallet addresses are disclosed. The systems and methods can receive a first plurality of tokens and an indication of a potentially malicious cryptographic wallet address from a requesting user. The system can identify a plurality of associated wallet addresses, and compare the associated wallet addresses to a stored list of malicious cryptographic wallet addresses. The system can determine a subset of the identified associated cryptographic wallet addresses that are malicious and assign a maliciousness rating to the potentially malicious cryptographic wallet address. The system can provide the maliciousness rating to the requesting user.

Abstract: The disclosed technology relates to blockchain asset transfer destination verification to reduce fraudulent activity and increase confidence in digital asset transfers. An exemplary oracle device may apply a machine learning model to transaction context data received from a source device to generate a confidence score informed based on transaction pattern data for the destination address. The transaction context data may include a destination address and may be associated with a transfer of an asset via a blockchain network. The generated confidence score may then be sent by the oracle device to the source device to facilitate an informed decision by a user of the source device as to whether to proceed with the transaction. The machine learning model may then be updated based on the transaction context data and a completion indication received from the source device and indicative of whether the asset was transferred via the destination address.