Granted Patent B2

US 12,731,152 · App. 18/316,381 · Granted Sep 8, 2026

Inventors: William H. Cohn (Lexington, MA); Sayid Shabeer (Ashland, MA); Ned Canning (Boston, MA)

Assignee: Worldpay, LLC

G06Q20/409G06Q20/4018

Abstract

Claims (57)

1 . A method for optimizing transaction authorization conversion rates, comprising:

retrieving, by one or more processors, a plurality of payment transaction parameters and factor success data from a database of payment transaction processing results;

generating, by the one or more processors via a machine learning model, a plurality of authorization success factors for the plurality of payment transaction parameters, wherein the machine learning model is configured to analyze factor success data, the plurality of payment transaction parameters, and the payment transaction processing results to generate the plurality of authorization success factors, wherein the factor success data includes a plurality of weights to apply to the plurality of authorization success factors to optimize the machine learning model;

receiving, by one or more processors, a payment transaction including transaction data from a merchant device;

modifying, by the one or more processors, one or more transaction parameters of the transaction data based on the plurality of authorization success factors;

generating, by the one or more processors, a modified payment transaction based on modifying the one or more transaction parameters;

submitting, by the one or more processors, the modified payment transaction to a financial institution for processing;

receiving, by the one or more processors, a payment transaction authorization result for the modified payment transaction submitted;

analyzing, by the one or more processors via the machine learning model, the payment authorization result to automatically calibrate one or more optimization factors based on the factor success data and the modified payment transaction and the payment transaction authorization result, wherein automatically calibrating the one or more optimization factors optimizes the machine learning model for generating a plurality of subsequent authorization success factors for a subsequent payment transaction; and

adding, by the one or more processors, the payment transaction authorization result and the automatically calibrated factor success data to the database of payment transaction processing results.

2 . The method of claim 1 , wherein the modifying further comprises:

comparing, by the one or more processors, the one or more transaction parameters of the payment transaction to the authorization success factors; and

modifying, by the one or more processors, the one or more transaction parameters of the payment transaction where the authorization success factors indicate a greater likelihood of authorization of the payment transaction.

3 . The method of claim 1 , wherein the one or more transaction parameters comprise at least one of a billing address, a card verification value (CVV), a payment processing network, a payment vehicle expiration date, or a merchant classification code (MCC).

4 . The method of claim 1 , wherein:

a plurality of payment networks are available for submitting the modified payment transaction for processing, and

the authorization success factors indicate a likelihood of authorization of the payment transaction associated with each payment network among the plurality of payment networks.

5 . The method of claim 1 , further comprising:

providing, by the one or more processors, a payment vehicle issuer token.

6 . A device for optimizing transaction authorization conversion rates, comprising:

a memory configured to store instructions; and

one or more processors configured to execute the instructions to perform operations comprising:

retrieving a plurality of payment transaction parameters from and factor success data a database of payment transaction processing results;

generating, via a machine learning model, a plurality of authorization success factors for the plurality of payment transaction parameters, wherein the machine learning model is configured to analyze factor success data, the plurality of payment transaction parameters, and the payment transaction processing results to generate the plurality of authorization success factors, wherein the factor success data includes a plurality of weights to apply to the plurality of authorization success factors to optimize the machine learning model;

receiving a payment transaction including transaction data from a merchant device;

modifying one or more transaction parameters of the transaction data based on the plurality of authorization success factors;

generating a modified payment transaction based on modifying the one or more transaction parameters;

submitting the modified payment transaction to a financial institution for processing;

receiving a payment transaction authorization result for the modified payment transaction submitted;

analyzing, via the machine learning model, the payment authorization result to automatically calibrate one or more optimization factors based on the factor success data and the modified payment transaction and the payment transaction authorization result, wherein automatically calibrating the one or more optimization factors optimizes the machine learning model for generating a plurality of subsequent authorization success factors for a subsequent payment transaction; and

adding the payment transaction authorization result and the automatically calibrated factor success data to the database of payment transaction processing results.

7 . The device of claim 6 , wherein the modifying further comprises:

comparing the one or more transaction parameters of the payment transaction to the authorization success factors; and

modifying the one or more transaction parameters of the payment transaction where the authorization success factors indicate a greater likelihood of authorization of the payment transaction.

8 . The device of claim 6 , wherein the one or more transaction parameters comprise at least one of a billing address, a card verification value (CVV), a payment processing network, a payment vehicle expiration date, or a merchant classification code (MCC).

9 . The device of claim 6 , wherein:

a plurality of payment networks are available for submitting the modified payment transaction for processing, and

the authorization success factors indicate a likelihood of authorization of the payment transaction associated with each payment network among the plurality of payment networks.

10 . The device of claim 6 , wherein the operations further comprise:

providing a payment vehicle issuer token.

11 . A non-transitory computer readable medium storing instructions that, when executed by a processor for optimizing transaction authorization conversion rates, cause the processor to perform operations comprising:

retrieving a plurality of payment transaction parameters and factor success data from a database of payment transaction processing results;

generating, via a machine learning model, a plurality of authorization success factors for the plurality of payment transaction parameters, wherein the machine learning model is configured to analyze factor success data, the plurality of payment transaction parameters, and the payment transaction processing results to generate the plurality of authorization success factors, wherein the factor success data includes a plurality of weights to apply to the plurality of authorization success factors to optimize the machine learning model;

receiving a payment transaction including transaction data from a merchant device;

modifying one or more transaction parameters of the transaction data based on the plurality of authorization success factors;

generating a modified payment transaction based on modifying the one or more transaction parameters;

submitting the modified payment transaction to a financial institution for processing;

receiving a payment transaction authorization result for the modified payment transaction submitted;

analyzing, via the machine learning model, the payment authorization result to automatically calibrate one or more optimization factors based on the factor success data and the modified payment transaction and the payment transaction authorization result, wherein automatically calibrating the one or more optimization factors the optimizes the machine learning model for generating a plurality of subsequent authorization success factors for a subsequent payment transaction; and

adding the payment transaction authorization result and the automatically calibrated factor success data to the database of payment transaction processing results.

12 . The non-transitory computer readable medium of claim 11 , wherein the modifying further comprises:

comparing the one or more transaction parameters of the payment transaction to the authorization success factors; and

modifying the one or more transaction parameters of the payment transaction where the authorization success factors indicate a greater likelihood of authorization of the payment transaction.

13 . The non-transitory computer readable medium of claim 11 , wherein the one or more transaction parameters comprise at least one of a billing address, a card verification value (CVV), a payment processing network, a payment vehicle expiration date, or a merchant classification code (MCC).

14 . The non-transitory computer readable medium of claim 11 , wherein:

a plurality of payment networks are available for submitting the modified payment transaction for processing, and

the authorization success factors indicate a likelihood of authorization of the payment transaction associated with each payment network among the plurality of payment networks.

Assignments (6)

Continuity (4)

References Cited (24)