# US 2022/0277334 A1 · Dynamic population adjustments for a group

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

- Number: US 2022/0277334 A1
- Document ID: US20220277334A1
- Status: Published application
- Kind: A1
- Application number: 17/186,492
- Filed: 2021-02-26
- Published: 2022-09-01
- Earliest claimed: 2021-02-26
- Assignees: NCR Corporation
- Applicants: NCR Corporation
- Inventors: Claudio Cifarelli; Diego De Cao
- Web page: https://patentgrep.com/patent/US20220277334A1

## CPC

- G06Q 30/0211: Determining the effectiveness of discounts or incentives
- G06Q 10/067: Enterprise or organisation modelling
- G06Q 30/02: Marketing; Price estimation or determination; Fundraising
- 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

## Abstract

An initial small group of customers are randomly selected for participation in a campaign associated with a promotion. Transactions of the group are monitored for a redemption of the promotion. A redeeming member's transaction is modeled and mapped into a multidimensional space and transactions for customers not included in the group are modeled and mapped into the space. A neighborhood of the redeeming member and select ones of the customers not included in the group are detected as emerging from the space. Most similar customers to the redeeming member are determined from the neighborhood and a preconfigured number of the most similar customers are selected for inclusion within the group for the campaign. This process continues until a goal of the campaign is reached or the campaign is ended.

## Claims

### Claim 1

A method, comprising:
determining a group of customers for a campaign associated with a promotion;
monitoring transactions of the customers for a redeeming customer that redeems the promotion in a redeeming transaction;
modeling the redeeming transaction in multidimensional space;
monitoring other transactions of other customers that are not part of the group;
modeling the other transactions in the multidimensional space;
identifying a select number of the other customers for inclusion in the group based on the modeling of the redeeming transaction and the modeling of the other transactions; and
providing customer identifiers for the select number of other customers for inclusion in the campaign.

### Claim 2 (depends on 1)

The method of claim 1 further comprising iterating back to the monitoring of the transactions with the group including the customers and the select number of the other customers until the campaign concludes.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining further includes randomly selecting the customers from available customers.

### Claim 4 (depends on 1)

The method of claim 1, wherein determining further includes randomly selecting the customers from a predefined cluster of available customers.

### Claim 5 (depends on 1)

The method of claim 1, wherein modeling the redeeming transaction further includes plotting the redeeming transaction into the multidimensional space, each item of the redeeming transaction associated with a unique dimension of the multidimensional space.

### Claim 6 (depends on 5)

The method of claim 5, wherein modeling the other transactions further includes plotting each of the other transactions into the multidimensional space.

### Claim 7 (depends on 6)

The method of claim 6, wherein identifying further includes determining the select number of the other customers based on computed distances between the redeeming transaction plotted in the multidimensional space and each of the other transactions that are associated with the select number of other customers plotted in the multidimensional space.

### Claim 8 (depends on 1)

The method of claim 1, wherein identifying further includes processing a similarity algorithm on the redeeming transactions modeled in the multidimensional space and the other transactions modeled in the multidimensional space to identify candidate customers for the select number of the other customers.

### Claim 9 (depends on 8)

The method of claim 8, wherein processing further includes processing a most frequent statistical algorithm against the redeeming transaction and the other transactions associated with the candidate customer to identify the select number of the other customers.

### Claim 10 (depends on 8)

The method of claim 8, wherein processing further includes selecting the select number of the other customers from the candidate customers based on similarity scores provided by the similarity algorithm for each of the other transactions that are associated with the select number of the other customers.

### Claim 11 (depends on 1)

The method of claim 1, wherein identifying further includes identifying the select number of the other customers based on a preconfigured percentage or a preconfigured number of top similarity scores assigned to the other transactions relative to the redeeming transaction.

### Claim 12

A method, comprising:
receiving a promotion identifier for a promotion from a campaign manager;
selecting a group of first customers for receiving the promotion on behalf of the campaign manager;
monitoring transactions of the first customers for a redemption transaction that included a redemption of the promotion;
modeling items of the redemption transaction;
modeling other items of other transactions from second customers for a preconfigured similarity value to the redemption transaction;
identifying third customers from the second customers associated with the other transactions that are within the preconfigured similarity value; and
providing customer identifiers for the third customers to the campaign manager for adding the third customer to the group with the first customers and for receiving the promotion.

### Claim 13 (depends on 12)

The method of claim 12 further comprising, iterating back to the monitoring the transactions and monitoring additional transactions associated with the third customers for a second redemption transaction that included a second redemption for the promotion until the promotion is terminated or expires.

### Claim 14 (depends on 13)

The method of claim 13 further comprising, controlling a size of the group and membership of the group that receives the promotion on behalf of the campaign manager

### Claim 15 (depends on 12)

The method of claim 12, wherein selecting further includes randomly selecting a preconfigured number of available customers as the first customers of the group.

### Claim 16 (depends on 12)

The method of claim 12, wherein modeling the items further includes modeling loyalty data associated with the first customer who performed the redemption transaction with the items of the redemption transaction.

### Claim 17 (depends on 16)

The method of claim 16, wherein modeling the other items further includes modeling additional loyalty data associated with the second customers with the other items of the other transactions.

### Claim 18 (depends on 12)

The method of claim 12, wherein identifying the third customers further includes selecting the third customers based on a preconfigured number of top computed similarity values from available computed similarity values that are within the preconfigured similarity value.

### Claim 19

A system, comprising:
a cloud processing environment comprising at least one processor and a non-transitory computer-readable storage medium;
the non-transitory computer-readable storage medium comprises executable instructions;
the executable instructions when executed by the at least one processor from the non-transitory computer-readable storage medium cause the at least one processor to perform operations comprising:
defining a size of a group and first members of the group for a campaign associated with a promotion;
monitoring transactions of the group for a redemption of the transaction associated with a redemption transaction;
modeling the redemption transaction based on a basket of items comprised in the transaction;
monitoring other transactions associated with non-members of the group;
modeling other transaction based on other baskets of items comprised in the other transactions;
identifying similarities between select ones of the other transactions and the redemption transaction based on the modeling of the redemption transaction and the other transactions;
selecting a preconfigured number of the select ones of the other transactions based on the corresponding similarities;
identifying member identifiers associated with the preconfigured number of the other transactions, wherein the member identifiers associated with second members;
adding the second members to the group increasing the size of the group by the preconfigured number; and
iterating back to the monitoring of the transactions with the second members added to the group until the campaign or the promotion ends or is terminated.

### Claim 20 (depends on 19)

The system of claim 19, wherein the transaction and the other transactions are processed on transaction terminals, and wherein the transaction terminals are Self-Service Terminals (SSTs), Point-Of-Sale (POS) terminals, kiosks, tablets, laptops, phones, and wearable processing devices.
