# US 11,443,359 B2 · System, method, and computer program product for segmenting users in a region based on predicted activity

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,443,359 B2
- Document ID: US11443359B2
- Status: Granted
- Kind: B2
- Application number: 16/629,707
- Filed: 2017-07-10
- Published: 2021-05-20
- Granted: 2022-09-13
- Earliest claimed: 2017-07-10
- Assignees: Visa International Service Association
- Applicants: Visa International Service Association
- Inventors: Keyuan Wu; Dhirender Singh Rathore; Vivek Narayanan Nair
- Web page: https://patentgrep.com/patent/US11443359B2

## CPC

- G06Q 30/0185: {Product, service or business identity fraud}
- G06Q 30/0631: {Recommending goods or services}
- G06N 20/00: Machine learning
- G06Q 30/0609: {Qualifying participants for shopping transactions (payment transaction verification G06Q20/401)}
- G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method of segmenting a plurality of users in a first region based on predicted activity external to the first region. A system and computer program product are also provided.

## Claims

### Claim 1

A method of segmenting a plurality of users in a first region comprising at least one country in which the plurality of users reside, the segmenting based on predicted activity external to the first region, the method comprising:
determining, with at least one processor, a first subset of users consisting essentially of a first plurality of users from the plurality of users that have previously used a portable device in at least one second region to initiate a transaction at least a predetermined number of times, wherein the at least one second region is external to the first region;
determining, with at least one processor, a second subset of users consisting essentially of a second plurality of users from the plurality of users that have not previously used a portable device to initiate a transaction in the at least one second region or have used a portable device to initiate a transaction in the at least one second region less than the predetermined number of times;
generating, with at least one processor, a first activation metric for each user of the first subset of users by applying a first algorithm to transaction data from portable financial device transactions initiated by each user of the first subset of users, the first algorithm based on a first plurality of transaction parameters, each transaction parameter of the first plurality of transaction parameters having an associated weight, wherein the first activation metric represents a determined propensity of a user from the first subset of users to initiate future transaction activity in the at least one second region;
generating, with at least one processor, a second activation metric for each user of the second subset of users by applying a second algorithm different from the first algorithm to transaction data from portable financial device transactions initiated by each user of the second subset of users, the second algorithm based on a second plurality of transaction parameters, each transaction parameter of the second plurality of transaction parameters having an associated weight, wherein the second activation metric represents a determined propensity of a user from the second subset of users to initiate future transaction activity in the at least one second region, wherein the second algorithm is not applied to the portable financial device transactions initiated by each user of the first subset of users;
determining, with at least one processor, a plurality of target users from the first subset of users and the second subset of users based at least partially on the first and second activation metrics, the plurality of target users having a determined higher propensity for initiating future transaction activity in the at least one second region compared to non-target users from the first subset of users and the second subset of users; and
in response to determining the plurality of target users, automatically initiating, with at least one processor, at least one target action for each user of the plurality of target users,
wherein the first plurality of transaction parameters and the second plurality of transaction parameters comprise at least one of: a frequency of transactions, a transaction spend, a consistency of usage, a frequency or amount of electronic commerce transactions, a frequency or amount of airline transactions, a frequency or amount of travel service transactions, a frequency or amount of lodging transactions, a frequency or amount of retail transactions, a frequency or amount of restaurant transactions, a frequency or amount of general retail transactions, a frequency or amount of apparel retail transactions, a frequency of transactions in the at least one second region, a transaction spend in the at least one second region, a consistency of transactions in the at least one second region, past travel behavior, merchant preferences, amount or frequency of seasonal purchases, number of channels though which user has initiated a transaction, spend behavior, or any combination thereof,
wherein the associated weight of each transaction parameter of the first and second plurality of transaction parameters is based on a predicted reliability of the transaction parameter to determine the propensity of a user from the first and/or second subset of users to initiate future transaction activity in the at least one second region.

### Claim 2 (depends on 1)

The method of claim 1, wherein at least one of the first algorithm and the second algorithm comprises a machine learning algorithm configured to apply at least one predictive model to the transaction data for at least one of each user of the first subset of users and each user of the second subset of users.

### Claim 3 (depends on 1)

The method of claim 1, wherein the at least one target action comprises:
identifying at least one offer for each user of the plurality of target users; and
communicating the at least one offer to each user of the plurality of target users.

### Claim 4 (depends on 1)

The method of claim 1, wherein the at least one target action comprises approving a user of the plurality of target users for transactions in the at least one second region.

### Claim 5 (depends on 1)

The method of claim 1, wherein the at least one target action comprises:
generating at least one list of at least a portion of the plurality of target users associated with a first issuing institution; and
communicating the at least one list to the first issuing institution.

### Claim 6 (depends on 1)

The method of claim 1, wherein the at least one second region comprises all countries external to the first region.

### Claim 7 (depends on 1)

The method of claim 1, wherein at least one of the first plurality of transaction parameters and the second plurality of transaction parameters comprises at least one external parameter, the at least one external parameter comprising at least one of the following: a change in currency exchange, a holiday or event schedule in at least one of the first region and the at least one second region, a time of year, or any combination thereof.

### Claim 8

A system for segmenting a plurality of users in a first region comprising at least one country in which the plurality of users reside, the segmenting based on predicted activity external to the first region, the system comprising at least one server computer including at least one processor, the at least one server computer programmed or configured to:
determine a first subset of users consisting essentially of a first plurality of users from the plurality of users that have previously used a portable device in at least one second region to initiate a transaction at least a predetermined number of times, wherein the at least one second region is external to the first region;
determine a second subset of users consisting essentially of a second plurality of users from the plurality of users that have not previously used a portable device to initiate a transaction in the at least one second region or have used a portable device to initiate a transaction in the at least one second region less than the predetermined number of times;
generate a first activation metric for each user of the first subset of users by applying a first algorithm to transaction data from portable financial device transactions initiated by each user of the first subset of users, the first algorithm based on a first plurality of transaction parameters, each transaction parameter of the first plurality of transaction parameters having an associated weight, wherein the first activation metric represents a determined propensity of a user from the first subset of users to initiate future transaction activity in the at least one second region;
generate a second activation metric for each user of the second subset of users by applying a second algorithm different from the first algorithm to transaction data from portable financial device transactions initiated by each user of the second subset of users, the second algorithm based on a second plurality of transaction parameters, each transaction parameter of the second plurality of transaction parameters having an associated weight, wherein the second activation metric represents a determined propensity of a user from the second subset of users to initiate future transaction activity in the at least one second region, wherein the second algorithm is not applied to the portable financial device transactions initiated by each user of the first subset of users;
determine a plurality of target users from the first subset of users and the second subset of users based at least partially on the first and second activation metrics, the plurality of target users having a determined higher propensity for initiating future transaction activity in the at least one second region compared to non-target users from the first subset of users and the second subset of users; and
in response to determining the plurality of target users, automatically initiate at least one target action for each user of the plurality of target users,
wherein the first plurality of transaction parameters and the second plurality of transaction parameters comprise at least one of: a frequency of transactions, a transaction spend, a consistency of usage, a frequency or amount of electronic commerce transactions, a frequency or amount of airline transactions, a frequency or amount of travel service transactions, a frequency or amount of lodging transactions, a frequency or amount of retail transactions, a frequency or amount of restaurant transactions, a frequency or amount of general retail transactions, a frequency or amount of apparel retail transactions, a frequency of transactions in the at least one second region, a transaction spend in the at least one second region, a consistency of transactions in the at least one second region, past travel behavior, merchant preferences, amount or frequency of seasonal purchases, number of channels though which user has initiated a transaction, spend behavior, or any combination thereof,
wherein the associated weight of each transaction parameter of the first and second plurality of transaction parameters is based on a predicted reliability of the transaction parameter to determine the propensity of a user from the first and/or second subset of users to initiate future transaction activity in the at least one second region.

### Claim 9 (depends on 8)

The system of claim 8, further comprising at least one database in communication with the at least one server, the at least one database comprising the transaction data for the portable device transactions initiated by each user of the first subset of users and the second subset of users.

### Claim 10 (depends on 8)

The system of claim 8, wherein at least one of the first algorithm and the second algorithm comprises a machine learning algorithm configured to apply at least one predictive model to the transaction data for at least one of each user of the first subset of users and each user of the second subset of users.

### Claim 11 (depends on 8)

The system of claim 8, wherein the at least one target action comprises:
identifying at least one offer for each user of the plurality of target users; and
communicating the at least one offer to each user of the plurality of target users.

### Claim 12 (depends on 8)

The system of claim 8, wherein the at least one target action comprises approving a user of the plurality of target users for transactions in the at least one second region.

### Claim 13 (depends on 8)

The system of claim 8, wherein the at least one target action comprises:
generating at least one list of at least a portion of the plurality of target users associated with a first issuing institution; and
communicating the at least one list to the first issuing institution.

### Claim 14 (depends on 8)

The system of claim 8, wherein the at least one second region comprises all countries external to the first region.

### Claim 15 (depends on 8)

The system of claim 8, wherein at least one of the first plurality of transaction parameters and the second plurality of transaction parameters comprises at least one external parameter, the at least one external parameter comprising at least one of the following: a change in currency exchange, a holiday or event schedule in at least one of the first region and the at least one second region, a time of year, or any combination thereof.

### Claim 16

A computer program product for segmenting a plurality of users in a first region comprising at least one country in which the plurality of users reside, the segmenting based on predicted activity external to the first region, the computer program product comprising at least one non-transitory computer-readable medium including program instructions that, when executed by at least one computer comprising at least one processor, cause the at least one processor to:
determine a first subset of users consisting essentially of a first plurality of users from the plurality of users that have previously used a portable device in at least one second region to initiate a transaction at least a predetermined number of times, wherein the at least one second region is external to the first region;
determine a second subset of users consisting essentially of a second plurality of users from the plurality of users that have not previously used a portable device to initiate a transaction in the at least one second region or have used a portable device to initiate a transaction in the at least one second region less than the predetermined number of times;
generate a first activation metric for each user of the first subset of users by applying a first algorithm to transaction data from portable financial device transactions initiated by each user of the first subset of users, the first algorithm based on a first plurality of transaction parameters, each transaction parameter of the first plurality of transaction parameters having an associated weight, wherein the first activation metric represents a determined propensity of a user from the first subset of users to initiate future transaction activity in the at least one second region;
generate a second activation metric for each user of the second subset of users by applying a second algorithm different from the first algorithm to transaction data from portable financial device transactions initiated by each user of the second subset of users, the second algorithm based on a second plurality of transaction parameters, each transaction parameter of the second plurality of transaction parameters having an associated weight, wherein the second activation metric represents a determined propensity of a user from the second subset of users to initiate future transaction activity in the at least one second region, wherein the second algorithm is not applied to the portable financial device transactions initiated by each user of the first subset of users;
determine a plurality of target users from the first subset of users and the second subset of users based at least partially on the first and second activation metrics, the plurality of target users having a determined higher propensity for initiating future transaction activity in the at least one second region compared to non-target users from the first subset of users and the second subset of users; and
in response to determining the plurality of target users, automatically initiate at least one target action for each user of the plurality of target users,
wherein the first plurality of transaction parameters and the second plurality of transaction parameters comprise at least one of: a frequency of transactions, a transaction spend, a consistency of usage, a frequency or amount of electronic commerce transactions, a frequency or amount of airline transactions, a frequency or amount of travel service transactions, a frequency or amount of lodging transactions, a frequency or amount of retail transactions, a frequency or amount of restaurant transactions, a frequency or amount of general retail transactions, a frequency or amount of apparel retail transactions, a frequency of transactions in the at least one second region, a transaction spend in the at least one second region, a consistency of transactions in the at least one second region, past travel behavior, merchant preferences, amount or frequency of seasonal purchases, number of channels though which user has initiated a transaction, spend behavior, or any combination thereof,
wherein the associated weight of each transaction parameter of the first and second plurality of transaction parameters is based on a predicted reliability of the transaction parameter to determine the propensity of a user from the first and/or second subset of users to initiate future transaction activity in the at least one second region.

### Claim 17 (depends on 16)

The computer program product of claim 16, wherein at least one of the first algorithm and the second algorithm comprises a machine learning algorithm configured to apply at least one predictive model to the transaction data for at least one of each user of the first subset of users and each user of the second subset of users.

### Claim 18 (depends on 16)

The computer program product of claim 16, wherein the at least one target action comprises:
identifying at least one offer for each user of the plurality of target users; and
communicating the at least one offer to each user of the plurality of target users.