# US 2024/0005347 A1 · System and method for creating segmentation of a population

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

- Number: US 2024/0005347 A1
- Document ID: US20240005347A1
- Status: Published application
- Kind: A1
- Application number: 18/467,934
- Filed: 2023-09-15
- Published: 2024-01-04
- Earliest claimed: 2016-07-15
- Assignees: Merkle, Inc.
- Applicants: Merkle, Inc.
- Inventors: Robert Lee WOOD; Futoshi YUMOTO; Thomas D. LACKI
- Web page: https://patentgrep.com/patent/US20240005347A1

## CPC

- G06Q 30/0204: Market segmentation
- G06Q 10/067: Enterprise or organisation modelling
- G06Q 30/0203: Market surveys; Market polls
- 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

A system including a processor may filter a population to identify a group having members, and deliver, over an electronic network, a survey to members of the group to determine value preferences and value gaps. The survey may be made according to a set of paired comparisons or other related techniques. The system may generate vectors according to the determined value preferences and value gaps for members of the group, which may have lengths equal to numbers of determined values for the members. The system may cluster members of the group into segments by calculating patterns of differences between generated vectors. Results of this process enable the creation of a predictive model to estimate segment membership, which can be used in the generation of a promotion for display corresponding to a clustered segment, and deliver the promotion to a client device associated for display.

## Claims

### Claim 1

A system for creating a segmentation of a population, the system comprising:
a memory storing instructions; and
a processor configured to execute the instructions to:
filter a population to identify a group having members;
deliver, over an electronic network, a survey to a first set of members to determine value preferences and value gaps for the members;
receive, over an electronic network, results of the survey;
generate vectors according to the determined value preferences and value gaps, the vectors having lengths equal to numbers of determined values for the members;
cluster the first set of members into multiple segments by calculating differences between the vectors;
create a predictive model to estimate segment membership of a second set of the members using the results of the survey;
generate a promotion for display corresponding to a clustered segment using the predictive model; and
deliver the promotion to a client device associated for display.

### Claim 2 (depends on 1)

The system of claim 1, wherein the processor is further configured to execute the instructions to:
compare at least one vector to a predetermined threshold to determine if the value preference and value gap of the at least one vector are both positive; and
cluster into a segment at least two vectors whose value preferences and value gaps are both positive.

### Claim 3 (depends on 1)

The system of claim 1, wherein the processor is further configured to execute the instructions to:
generate a latent variable model to determine an interval nature and ranking of the value preferences and value gaps.

### Claim 4 (depends on 3)

The system of claim 3, wherein the processor is further configured to execute the instructions to:
generate a Bradley-Terry-Luce (BTL) model to analyze relative strengths of the value preferences and value gaps.

### Claim 5 (depends on 1)

The system of claim 1, wherein the processor is further configured to execute the instructions to:
cluster the first set of members into multiple consumer segments according to at least one of demographics, channel preferences, product experience, media usage, attitudes, behaviors, or psychographics.

### Claim 6 (depends on 1)

The system of claim 1, wherein filtering the population further comprises filtering the members based on at least one of age, gender, socio-economic status, or demographics.

### Claim 7 (depends on 1)

The system of claim 1, wherein the survey is directed to a set of paired comparisons, and the processor is further configured to execute the instructions to analyze relative strengths of the value preferences and value comparisons based on the set of paired comparisons.

### Claim 8

A method for creating segmentation of a population, comprising a memory and a processors configured to execute instructions, the method comprising:
filtering a population to identify a group having members;
delivering, over an electronic network, a survey to a first set the members to determine value preferences and value gaps for the members;
receiving, over an electronic network, results of the survey;
generating vectors according to the determined value preferences and value gaps, the vectors having lengths equal to numbers of determined values for each member;
clustering the first set of members into multiple segments by calculating differences between the vectors;
creating a predictive model to estimate segment membership of a second set of the members using the results of the survey;
generating a promotion for display corresponding to a clustered segment using the predictive model; and
delivering the promotion to a client device associated for display.

### Claim 9 (depends on 8)

The method according to claim 8, the method further comprising:
comparing at least one vector to a predetermined threshold to determine if the value preference and value gap of the at least one vector are both positive; and
cluster into a segment at least two vectors whose value preferences and value gaps are both positive.

### Claim 10 (depends on 8)

The method according to claim 8, the method further comprising:
generating a latent variable model to determine an interval nature and ranking of the value preferences and value gaps.

### Claim 11 (depends on 10)

The method according to claim 10, the method further comprising:
generating a Bradley-Terry-Luce (BTL) model to analyze relative strengths of the value preferences and value gaps.

### Claim 12 (depends on 8)

The method according to claim 8, the method further comprising:
clustering the first set of members into multiple consumer segments according to at least one of demographics, channel preferences, product experience, media usage, attitudes, behaviors, or psychographics.

### Claim 13 (depends on 8)

The method according to claim 8, wherein filtering the population further comprises filtering the members based on at least one of age, gender, socio-economic status, or demographics.

### Claim 14 (depends on 8)

The method according to claim 8, wherein the survey is directed to a set of paired comparisons, and the method further comprises analyzing relative strengths of the value preferences and value comparisons based on the set of paired comparisons.

### Claim 15

A non-transitory computer-readable medium storing instructions executable a processor to perform a method for creating a segmentation of a population, the method comprising:
filtering a population to identify a group having members;
delivering, over an electronic network, a survey to a first set of the members to determine value preferences and value gaps for the members;
receiving, over an electronic network, results of the survey;
generating vectors according to the determined value preferences and value gaps, the vectors having lengths equal to numbers of determined values for the members;
clustering the first set of members into multiple segments by calculating differences between the vectors;
creating a predictive model to estimate segment membership of a second set of members of the group using the results of the survey;
generating a promotion for display corresponding to a clustered segment using the predictive model; and
delivering the promotion to a client device associated for display.

### Claim 16 (depends on 15)

The non-transitory computer readable medium according to claim 15, further comprising:
comparing at least one vector to a predetermined threshold to determine if the value preference and value gap of the at least one vector are both positive; and
cluster into a segment at least two vectors whose value preferences and value gaps are both positive.

### Claim 17 (depends on 15)

The non-transitory computer readable medium according to claim 15, further comprising:
generating a latent variable model to determine an interval nature and ranking of the value preferences and value gaps.

### Claim 18 (depends on 17)

The non-transitory computer readable medium according to claim 17, further comprising:
generating a Bradley-Terry-Luce (BTL) model to analyze relative strengths of the value preferences and value gaps.

### Claim 19 (depends on 15)

The non-transitory computer readable medium according to claim 15, further comprising:
clustering the first set of members into multiple consumer segments according to at least one of demographics, channel preferences, product experience, media usage, attitudes, behaviors, or
psychographics.

### Claim 20 (depends on 15)

The non-transitory computer readable medium according to claim 15, wherein filtering the population further comprises filtering the members based on at least one of age, gender, socio-economic status, or demographics.
