US 12,190,373 B2
Multi-computer system for fail-safe event processing
Pratap Dande, Saint Johns, FL (US); Erik Dahl, Newark, DE (US); Rahul Yaksh, Austin, TX (US); Tileshia Brenda Alford, Charlotte, NC (US); Steven Allan Reich, Manalapan, NJ (US); Vishwanath Prasad Karra, Mckinney, TX (US); and Sailesh Vezzu, Hillsborough, NJ (US)
Assigned to Bank of American Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Dec. 7, 2022, as Appl. No. 18/076,710.
Prior Publication US 2024/0193680 A1, Jun. 13, 2024
Int. Cl. G06Q 40/03 (2023.01)
CPC G06Q 40/03 (2023.01) 15 Claims
OG exemplary drawing
 
1. A computing platform, comprising:
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
a memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
train a machine learning model, wherein training the machine learning model includes using historical creditworthiness data and user factor data to identify patterns or sequences in subsequent user factor data to determine a current creditworthiness of a user;
receive, by an enterprise organization and from a user, a request to register, the request to register including a request to open an account;
responsive to receiving the request to register, generate an account for the user, generating the account including generating a first account number associated with the account and provided to the user and a second, virtual account number, different from the first account number and associated with the account and not provided to the user;
transmit, to the user, the first account number, wherein the first account number is associated with a payment device of the account;
store, by the enterprise organization, the second, virtual account number in a deactivated state;
receive, via a user portal, a request to initiate a recurring payment from the account, the request to initiate the recurring payment including the first account number;
process a first instance of the recurring payment using the first account number;
detect an issue with at least one of: the payment device associated with the account or the first account number;
responsive to detecting the issue:
execute, in real-time, the machine learning model using, as inputs, current user factor data, to output the current creditworthiness score associated with the user;
store the determined current creditworthiness score associated with the user, wherein storing the determined current creditworthiness score associated with the user includes overwriting a previous creditworthiness score associated with the user; and
compare the current creditworthiness score to a creditworthiness threshold;
responsive to determining that the current creditworthiness score meets or exceeds the creditworthiness threshold:
activate the second, virtual account number;
process a second, subsequent instance of the recurring payment using the activated second, virtual account number;
generate a first notification indicating that the second, subsequent instance of the recurring payment was processed;
transmit the generated first notification to a computing device of the user, wherein transmitting the generated first notification causes the first notification to be displayed on a display of the computing device of the user; and
update, based on the processing the second, subsequent instance of the recurring payment using the activated second, virtual account number, the machine learning model;
responsive to determining that the current creditworthiness score does not meet or exceed the creditworthiness threshold:
generate a second notification indicating that the issue was detected and requesting user input; and
transmit the second notification to the computing device of the user, wherein transmitting the second notification causes the second notification to be displayed on the display of the computing device of the user.