SYSTEM AND METHOD FOR CLUSTERING A POPULATION USING SPEND LEVEL DATA

• US 20110178841A1
• Filed: 01/20/2010
• Published: 07/21/2011
• Est. Priority Date: 01/20/2010
• Status: Abandoned Application

• Current Assignee: Liberty Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: American Express Travel Related Services Company, Inc. (American Express Company)
• Inventors: Schwartz, Melissa, Rane, Rajendra R.
• Application Number:
  US12/690,669
• Publication Number:
  US 20110178841A1
• Time in Patent Office: Days
• US Class Current: 705/7.31
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

The present invention improves upon existing systems and methods by providing a passive profile creation method. The data accessible to a financial processor, such as spend level data, is leveraged using sophisticated data clustering and/or data appending techniques. Associations are established among entities (e.g., consumers), among merchants, and between entities and merchants. In one embodiment, a system and method for passively collecting spend level data for a transaction of a first entity, aggregating the collected spend level data for a plurality of entities; and clustering the first entity with a subset of the plurality of entities, based on aggregated spend level data of the first entity is provided.

Claims

1. A method comprising:

passively collecting spend level data for a transaction of a first entity;

aggregating the collected spend level data for a plurality of entities; and

clustering the first entity with a subset of the plurality of entities, based on aggregated spend level data of the first entity.

2. The method of claim 1, wherein the clustering comprises,

assigning a weighted percentile to the spend level data of the first entity within merchant category codes for a plurality of merchant category codes;

selecting a weight percentile across a merchant category codes; and

grouping a first entity with other entities based upon the selecting.

3. The method of claim 2, wherein the selected weight percentile is the median percentile of each cluster.

4. The method of claim 2, wherein the weighted percentile is a function of the total value of payments by a first entity to the merchants assigned a merchant category code as compared to other the total value of payments by other entities to merchants with the same assigned merchant category code.

5. The method of claim 1, wherein the spend level data comprises at least one of transaction data, or consumer account data.

6. The method of claim 1, wherein the passively collecting spend level data of the first entity includes acquiring the spend level data from a merchant.

7. The method of claim 1, wherein the passively collecting the spend level data of a first entity includes collecting the spend level data from a transaction database.

8. The method of claim 1, wherein the passively collecting spend level data of the first entity includes acquiring the spend level data in response to a transaction by the first entity with a merchant.

9. The method of claim 1, wherein the passively collecting spend level data of the first entity comprises at least one of reconciling the spend level data, transferring the spend level data to a host, organizing spend level data into a format, saving the spend level data to a memory, gathering the spend level data from the memory, or saving the spend level data to a database.

10. The method of claim 1, wherein the aggregating the collected spend level data comprises combining a selectable range of collected spend level data.

11. The method of claim 1, wherein the aggregating the collected spend level data comprises combining a selectable time range of collected spend level data.

12. The method of claim 11, wherein the selectable time range is 12 months.

13. The method of claim 1, wherein the clustering the entity based on the aggregated spend level data of a first entity comprises using a computer implemented statistical analysis algorithm to:

assign a weighted percentile to the spend level data of the first entity for spend level data assigned a merchant category code for a plurality of merchant category codes;

select a weight percentile across a merchant category codes; and

group a first entity with other entities based upon the selecting.

14. The method of claim 1, wherein the attributes of the first entity within a first cluster are as similar to the aggregate attributes of other first cluster members as possible.

15. The method of claim 1, wherein the aggregate attributes of the members of a first cluster are as dissimilar to the aggregate attributes the members of a second cluster as possible.

16. The method of claim 1, further comprising using a cluster for at least one of advertising, market research, media planning, public relations, product pricing, product distribution, consumer support, sales strategy, community involvement, marketing, directing an entity to goods, directing an entity to services, drawing inferences about a cluster, directing the first entity to a second entity, or research.

17. The method of claim 1, further comprising comparing a first aggregated range of the spend level data of a first entity to a second aggregated range of the spend level data of a first entity.

18. The method of claim 17, wherein the comparing may be for at least one of tracking the effectiveness of marketing, identifying changes in the spend level data of a first entity, or reassigning the cluster of the first entity.

19. A system configured to:

passively collect spend level data for a transaction of a first entity;

aggregate the collected spend level data for a plurality of entities; and

cluster the first entity with a subset of the plurality of entities, based on the aggregated spend level data of the first entity.

20. A computer readable medium having instructions stored thereon that, if executed by a computing device, cause the computing device to perform a method comprising:

passively collect spend level data for a transaction of a first entity;

aggregate the collected spend level data for a plurality of entities; and

cluster the first entity with a subset of the plurality of entities, based on the aggregated spend level data of the first entity.