Multi-dimensional segmentation for use in a customer interaction

• US 7,698,163 B2
• Filed: 11/22/2002
• Issued: 04/13/2010
• Est. Priority Date: 11/22/2002
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services GmbH (Accenture PLC)
• Inventors: Saito, Michiko, Reed, Kenneth L., Hariharan, Hari S.
• Primary Examiner(s): Boswell; Beth V
• Assistant Examiner(s): PATS, JUSTIN
• Application Number:
  US10/302,418
• Publication Number:
  US 20040103051A1
• Time in Patent Office: 2,699 Days
• Field of Search: 705/10
• US Class Current: 705/7.33
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis

Abstract

A system and method for segmenting customer data that represents a plurality of customers for use in a customer interaction. The segmentation process groups customers with similar characteristics into segments. The segments may be used to classify customers according to a likelihood of the customers to accept a particular marketing offer. The segments may also be used as an analytic framework for customer portfolio management, product development, marketing strategy, and customer interaction capabilities. A multi-dimensional segmentation approach may be used to cross-segment a plurality of customers so that the customers included in the crossed segments can be profiled for more precise targeting of marketing offers. Customers may be segmented according to one or more data types stored in a data warehouse. The multi-dimensional segmentation approach may be applied to relationships between and among the data types to obtain a holistic view of what drives customer value. The segmentations may be driven by a business objective. This enables the segment analysis to be calibrated in the context of the stated business objective.

Claims

1. A computer-implemented method for segmenting data representing a plurality of customers, comprising the computer-implemented steps of:

choosing, using a data type choosing module, at least four different data types stored in a data warehouse on a computer platform,

wherein the at least four different data types comprise a first data type containing customer behavior data, a second data type containing customer value data, a third data type, and a fourth data type; and

wherein the third and fourth data types are chosen from a group comprising attitude, satisfaction, brand experience, brand attachment, brand utility, lifestyle, life-stage, and category involvement;

segmenting, using at least one software module, a subset of the plurality of customers by each of the at least four different data types to produce a corresponding plurality of segmentation results;

generating a multi-dimensional hypercube, for cross-segmenting the subset of the plurality of customers, and combining the at least four different data types by overlaying the plurality of segmentation results within the multi-dimensional hypercube;

profiling the plurality of segmentation results overlaid within the multi-dimensional hypercube, wherein profiling includes cross-segmenting the subset of the plurality of customers to produce a joint view of relationships among the at least four different data types, and to identify the relationships among the at least four data types;

associating the identified relationships to a superset of the plurality of customers; and

updating a customer record stored in the data warehouse on the computer platform for each of the superset of the plurality of customers to reflect the identified relationships.

2. The computer-implemented method of claim 1, wherein the computer-implemented step of segmenting, using the at least one software module, the plurality of customers comprises employing a cluster analysis algorithm to identify clusters in the data, and wherein distance metrics utilized within the cluster analysis algorithm to cluster the customers are calculated based on a business objective.

3. The computer-implemented method of claim 1, wherein the computer-implemented step of segmenting, using the at least one software module, the plurality of customers comprises excluding demographic variables from a segmentation decision.

4. The computer-implemented method of claim 1, wherein the customer behavior data comprises purchase pattern data.

5. The computer-implemented method of claim 1, wherein the customer behavior data comprises preferences data.

6. The computer-implemented method of claim 1, wherein the customer behavior data comprises support needs data.

7. The computer-implemented method of claim 1, wherein the customer value data comprises cost data.

8. The computer-implemented method of claim 1, wherein the customer value data comprises customer lifetime value data.

9. The computer-implemented method of claim 1, wherein the customer value data comprises revenue data.

10. The computer-implemented method of claim 1, wherein the computer-implemented method for segmenting is used in at least one of a customer interaction, customer portfolio management, marketing strategy, and product development.

11. A computer-implemented method for segmenting data representing a plurality of customers, the method comprising the computer-implemented steps of:

choosing, using a characteristic choosing module, at least four different characteristics stored in a data warehouse on a computer platform,

wherein the at least four different characteristics are chosen from a group comprising attitude, behavior, value, satisfaction, brand experience, brand attachment, brand utility, lifestyle, life-stage, and category involvement;

segmenting, using at least one software module, a subset of the plurality of customers by each of the at least four different characteristics to produce a corresponding plurality of segmentation results;

generating a matrix multi-dimensional hypercube for cross-segmenting the subset of the plurality of customers and combining the at least four different characteristics by overlaying the plurality of segmentation results within the multi-dimensional hypercube;

profiling the plurality of segmentation results overlaid within the multi-dimensional hypercube, wherein profiling includes cross-segmenting the subset of the plurality of customers to produce a joint view of relationships among the at least four different characteristics and to identify the relationships among the at least four different characteristics;

associating the identified relationships to a superset of the plurality of customers; and

updating a customer record stored in the data warehouse on the computer platform for each of the superset of the plurality of customers to reflect the identified relationships.

12. The computer-implemented method of claim 11, wherein identifying the relationships is performed according to defined characteristic relationships that comprise at least one of a group comprising:

the attitude driving the behavior;

the behavior driving the value;

a relationship experience felt by a customer impacting the satisfaction;

the satisfaction affecting the brand experience;

the brand experience affecting the brand attachment which is also being impacted by the advertising;

the life-stage and the lifestyle affecting the brand utility and the category involvement; and

the attitude being affected by the brand experience, the brand attachment, the brand utility, and the category involvement.

13. The computer-implemented method of claim 11, wherein the method for segmenting is used in at least one of a customer interaction, customer portfolio management, marketing strategy, and product development.

14. A system for segmenting data representing a plurality of customers, comprising:

a data type choosing module that chooses at least four different data types stored in a data warehouse on a computer platform,

wherein the at least four different data types comprise a first data type containing behavior data, a second data type containing value data, a third data type, and a fourth data type; and

wherein the third and fourth data types are chosen from a group comprising attitude, satisfaction, brand experience, brand attachment, brand utility, lifestyle, life-stage, and category involvement;

a data type segmenting module that segments a subset of the plurality of customers by each of the at least four different data types to produce a corresponding plurality of segmentation results;

and

a multi-dimensional hypercube generating module that generates a multi-dimensional hypercube for cross-segmenting the subset of a plurality of customers by the at least four different data types and that combines the at least four different data types by overlaying the plurality of segmentation results within the multi-dimensional hypercube;

a profiling module that profiles the segmentation results overlaid within the multi-dimensional hypercube by cross-segmenting the subset of the plurality of customers to produce a joint view of relationships among the at least four different data types, and to identify the relationships among the at least four different data types;

an associating module that associates the identified relationships to a superset of the plurality of customers; and

an updating module that updates a customer record stored in the data warehouse on the computer platform for each of the superset of the plurality of customers to reflect the identified relationships.

15. The system of claim 14, wherein the data type segmenting module employs a cluster analysis algorithm to identify clusters in the data, and wherein distance metrics utilized within the cluster analysis algorithm to cluster the customers are calculated based on a business objective.

16. The system of claim 14, further comprising:

an excluding module that excludes demographic variables from a segmentation decision.

17. The system of claim 14, wherein the data type segmenting module employs distance metrics driven by a business objective.

18. The system of claim 14, wherein the behavior data comprises purchase pattern data.

19. The system of claim 14, wherein the behavior data comprises preferences data.

20. The system of claim 14, wherein the behavior data comprises support needs data.

21. The system of claim 14, wherein the value data comprises cost data.

22. The system of claim 14, wherein the value data comprises customer lifetime value data.

23. The system of claim 14, wherein the value data comprises revenue data.

24. The system of claim 14, wherein the system for segmenting data is used in at least one of a customer interaction, customer portfolio management, marketing strategy, and product development.

25. A system for segmenting data representing a plurality of customers, the system comprising:

a characteristic choosing module that chooses at least four different characteristics stored in a data warehouse on a computer platform,

wherein the at least four different characteristics are chosen from a group comprising attitude, behavior, value, satisfaction, brand experience, brand attachment, brand utility, lifestyle, life-stage, and category involvement;

a characteristic segmenting module that segments a subset of the plurality of customers by each of the at least four different characteristics to produce a corresponding plurality of segmentation results;

a multi-dimensional hypercube generating module that generates a multi-dimensional hypercube for cross-segmenting the subset of a plurality of customers and that combines the at least four different characteristics by overlaying the plurality of segmentation results within the multi-dimensional hypercube;

a profiling module that profiles the plurality of segmentation results overlaid within the multi-dimensional hypercube by cross-segmenting the subset of the plurality of customers to produce a joint view of relationships among the at least four different characteristics and to identify the relationships among the at least four different characteristics;

associating the identified relationships to a superset of the plurality of customers; and

an updating module that updates a customer record stored in the data warehouse on the computer platform for each of the superset of the plurality of customers to reflect the identified relationships.

26. The system of claim 25, wherein identifying the relationships is performed according to defined characteristic relationships that comprise at least one of a group comprising:

the attitude driving the behavior;

the behavior driving the value;

a relationship experience felt by a customer impacting the satisfaction;

the satisfaction affecting the brand experience;

the brand experience affecting the brand attachment which is also being impacted by the advertising;

the life-stage and the lifestyle affecting the brand utility and the category involvement; and

the attitude being affected by the brand experience, the brand attachment, the brand utility, and the category involvement.

27. The system of claim 25, wherein the system for segmenting data is used in at least one of a customer interaction, customer portfolio management, marketing strategy, and product development.

28. A computer program product comprising a computer-readable medium having computer-executable instructions that control a computer to perform a method for segmenting data representing a plurality of customers, the method comprising the computer-implemented steps of:

choosing, using a data type choosing module, at least four different data types stored in a data warehouse on a computer platform,

wherein the at least four different data types comprise a first data type containing customer behavior data, a second data type containing customer value data, a third data type, and a fourth data type; and

wherein the third and fourth data types are chosen from a group comprising attitude, satisfaction, brand experience, brand attachment, brand utility, lifestyle, life-stage, and category involvement;

segmenting, using at least one software module, a subset of the plurality of customers by each of the at least four different data types to produce a corresponding plurality of segmentation results;

generating, using the at least one software module, a multi-dimensional hypercube for cross-segmenting the subset of the plurality of customers and combining the at least four different data types by overlaying the plurality of segmentation results within the multi-dimensional hypercube;

profiling the plurality of segmentation results within the multi-dimensional hypercube, wherein profiling includes cross-segmenting the subset of the plurality of customers to produce a joint view of relationships among the at least four different data types and to identify relationships among the at least four different data types;

associating the identified relationships to a superset of the plurality of customers; and

updating a customer record stored in the data warehouse on the computer platform for each of the superset of the plurality of customers to reflect the identified relationships.

29. A computer program product comprising a computer-readable medium having computer-executable instructions that control a computer to perform a method for segmenting data representing a plurality of customers, the method comprising:

choosing, using a characteristic choosing module, at least four different characteristics stored in a data warehouse on a computer platform,

wherein the at least four different characteristics are chosen from a group comprising attitude, behavior, value, satisfaction, brand experience, brand attachment, brand utility, lifestyle, life-stage, and category involvement;

segmenting, using a segmenting module, a subset of the plurality of customers by each of the at least four different characteristics to produce a corresponding plurality of segmentation results; and

generating, using a generating module, a multi-dimensional hypercube for cross-segmenting the subset of a plurality of customers and combining the at least four different characteristics by overlaying the plurality of segmentation results within the multi-dimensional hypercube;

profiling, using a profiling module, the plurality of segmentation results within the multi-dimensional hypercube by cross-segmenting the subset of the plurality of customers to produce a joint view of relationships among the at least four different characteristics and to identify the relationships among the at least four different characteristics;

associating, using an association module, the identified relationships to a superset of the plurality of customers; and

updating, using an updating module, a customer record stored in the data warehouse on the computer platform for each of the superset of the plurality of customers to reflect the identified relationships.