Methods and systems for defining targeted marketing campaigns using embedded models and historical data

• US 7,003,476 B1
• Filed: 12/29/1999
• Issued: 02/21/2006
• Est. Priority Date: 12/29/1999
• Status: Expired due to Fees

• Current Assignee: General Electric Capital Corporation (General Electric Company)
• Original Assignee: General Electric Capital Corporation (General Electric Company)
• Inventors: Nabe, Oumar, Samra, Balwinder S.
• Primary Examiner(s): Diaz, Susanna M.
• Assistant Examiner(s): BOSWELL, BETH V
• Application Number:
  US09/474,974
• Time in Patent Office: 2,246 Days
• Field of Search: 705/10, 705/14, 705/7, 705/8
• US Class Current: 705/7.28
• CPC Class Codes: G06Q 10/0635 Risk analysis of enterprise or organisation activities
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0204 Market segmentation

Abstract

Methods and systems for increasing the efficiency of marketing campaigns are disclosed. A targeting engine is used for analyzing data input and generating data output. The method includes the steps of using historical data to determine a target group based upon a plurality of embedded models and directing the marketing campaign towards the target groups flagged by the models.

Claims

1. A method for increasing the efficiency of marketing campaigns using a targeting engine for analyzing data input and generating data output, said method including the steps of:

using the targeting engine to determine a sequential order for combining a plurality of models embedded within and executed by the targeting engine to define a target group, wherein each model is a predicted customer profile based on historical data and each model is a statistical analysis for predicting a behavior of a prospective customer, wherein the plurality of models include risk models and marketing models, and wherein a risk model predicts a likelihood of whether the prospective customer will at least one of pay on time, be delinquent with a payment, and declare bankruptcy, the marketing models include a net present value/profitability model, a prospect pool model, a net conversion model, an attrition model, a response model, a revolver model, a balance transfer model, and a reactivation model;

combining the plurality of models in the determined sequential order to determine an initial customer group for defining the target group, wherein the initial customer group includes a list of customers satisfying each of the combined models and rank ordered by projected profitability, projected profitability is based on at least one of a probable response by a customer to the marketing campaign, attrition of the customer, and risk associated with the customer, and the list includes a high profit end, a moderate profit section, and a low profit end, wherein the high profit end includes customers having a highest projected profitability, the low profit end includes customers having a lowest projected profitability, and the moderate profit section includes a profitability baseline, wherein the determined sequential order maximizes a number of customers included between the high profit end and the profitability baseline, and wherein the target group includes the customers included between the high profit end of the list and the profitability baseline;

using the targeting engine to determine the profitability baseline for the marketing campaign wherein the profitability baseline defines marginal returns for a customer equal to zero; and

directing the marketing campaign towards the target group determined by the plurality of models.

2. A method according to claim 1 wherein said step of combining the plurality of models further comprises the step of combining the plurality of models to determine a depth of a targeted mailing that includes the target group.

3. A method according to claim 1 wherein said step of combining the plurality of models further comprises the step of combining the plurality of models to determine a likelihood of a customer response.

4. A method according to claim 1 wherein said step of combining the plurality of models further comprises the step of combining the plurality of models to generate a potential customer list.

5. A method according to claim 1 wherein said step combining the plurality of models further comprises the step of combining the plurality of models to determine expected profitability per customer of a marketing campaign.

6. A method according to claim 1 wherein said step of combining the plurality of models further comprises the step of combining the plurality of models to determine expected profitability per product of a marketing campaign.

7. A method according to claim 1 wherein said step of directing the marketing campaign towards the target group determined by the plurality of models further comprises the step of rank ordering accounts.

8. A method according to claim 1 wherein said step of directing the marketing campaign towards the target group determined by the plurality of models further comprises the step of segmenting accounts based on customer demographics.

9. A method according to claim 1 wherein said step of directing the marketing campaign towards the target group determined by the plurality of models further comprises the step of identifying cross-sell targets.

10. A method according to claim 1 wherein said step of combining the plurality of models further comprises using the targeting engine to determine a risk factor for the target group after combining each model.

11. A method according to claim 1 wherein said step of combining the plurality of models further comprises the step of:

storing in a database historical data for a plurality of potential customers including for each potential customer at least one of an age, a gender, a marital status, an income, a transaction history, and a transaction measure; and

combining the plurality of models in the determined sequential order to define the initial customer group by applying a first model included in the determined sequential order to each of the plurality of potential customers included in the database to generate a first segment of only those potential customers satisfying the first model, applying a second model included in the determined sequential order to the first segment to generate a second segment of only those potential customers satisfying the combination of the first and second models, and then applying each subsequent model included in the determined sequential order to a segment generated by the combination of each prior model.

12. A method according to claim 11 wherein said step of combining the plurality of models in the determined sequential order to define the initial customer group further comprises combining the plurality of models in the determined sequential order to determine a risk factor for each potential customer within the initial customer group.

13. A system configured to increase efficiency of marketing campaigns, said system comprising:

a customer database which includes customer demographics and historical data;

a targeting engine for analyzing data input and generating data output, said targeting engine having a plurality of models stored thereon wherein each model is a predicted customer profile based on said historical data and each model is a statistical analysis for predicting a behavior of a prospective customer, wherein the plurality of models include risk models, and marketing models, and wherein a risk model predicts a likelihood of whether the prospective customer will at least one of pay on time, be delinquent with a payment, and declare bankruptcy, and the marketing models include a net present value/profitability model, a prospect pool model, a net conversion model, an attrition model, a response model, a revolver model, a balance transfer model, and a reactivation model, said targeting engine configured to;

access said historical data,

determine a sequential order for combining said plurality of models to define a target group, and

combine said plurality of models in the determined sequential order to determine an initial customer group for defining the target group, wherein the initial customer group includes a list of customers satisfying each of said combined models and rank ordered by projected profitability, projected profitability is based on at least one of a probable response by a customer to the marketing campaign, attrition of the customer, and risk associated with the customer, and the list includes a high profit end, a moderate profit section, and a low profit end, wherein the high profit end includes customers having a highest projected profitability, the low profit end includes customers having a lowest projected profitability, and the moderate profit section includes a profitability baseline, wherein the determined sequential order maximizes a number of customers included between the high profit end and the profitability baseline, and wherein the target group includes the customers included between the high profit end of the list and the profitability baseline, said targeting engine further configured to determine the profitability baseline for the marketing campaign wherein the profitability baseline defines marginal returns for a customer equal to zero; and

a graphical user interface for accessing customer database and displaying data output including the target group.

14. A system according to claim 13 further configured to use historical data stored in said customer database to direct a marketing campaign towards the target group determined by the plurality of models.

15. A system according to claim 13 wherein the targeting engine is further configured to combine the plurality of models to determine a depth of a targeted mailing that includes the target group.

16. A system according to claim 13 wherein the targeting engine is further configured to combine the plurality of models to determine a likelihood of a customer response.

17. A system according to claim 13 wherein the targeting engine is further configured to combine the plurality of models to generate a potential customer list.

18. A system according to claim 13 wherein the targeting engine is further configured to combine the plurality of models to determine expected profitability per customer of a marketing campaign.

19. A system according to claim 13 wherein the targeting engine is further configured to combine the plurality of models to determine expected profitability per product of a marketing campaign.

20. A system according to claim 13 wherein the targeting engine is further configured to rank order accounts.

21. A system according to claim 13 wherein the targeting engine is further configured to segment accounts based on customer demographics.

22. A system according to claim 13 wherein said targeting engine is further configured to determine a risk factor for the target group after combining each model.

23. A system according to claim 13 wherein said customer database further includes historical data for a plurality of potential customers including for each potential customer at least one of an age, a gender, a marital status, an income, a transaction history, and a transaction measure, and wherein said targeting engine further configured to combine the plurality of models in the determined sequential order to define the initial customer group by applying a first model included in the determined sequential order to each of the plurality of potential customers included in said customer database to generate a first segment of only those potential customers satisfying the first model, applying a second model included in the determined sequential order to the first segment to generate a second segment of only those potential customers satisfying the combination of the first and second models, and then applying each subsequent model included in the determined sequential order to a segment generated by the combination of each prior model.

24. A system according to claim 23 wherein said targeting engine is further configured to combine the plurality of models in the determined sequential order to determine a risk factor for each potential customer within the initial customer group.