Methods and systems for predicting business behavior from profiling consumer card transactions

• US 20050197954A1
• Filed: 08/23/2004
• Published: 09/08/2005
• Est. Priority Date: 08/22/2003
• Status: Active Grant

• Current Assignee: Mastercard International Incorporated (MasterCard Incorporated)
• Original Assignee: Mastercard International Incorporated (MasterCard Incorporated)
• Inventors: Murly, Tatiana, Rademaker, Jennifer Riddell, Walker, Denise A., Maitland, Jill
• Granted Patent: US 7,853,469 B2
• Time in Patent Office: Days
• US Class Current: 705/39
• CPC Class Codes: G06Q 10/0631 Resource planning, allocation, distributing or scheduling for enterprises or organisations
• CPC Class Codes: G06Q 20/10 specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03

Abstract

A system and method are provided for predicting small business behavior by analysis of consumer payment card transaction data. Transaction and amount velocity analysis of industry categories and/or real-time transaction-based profiling is employed to identify those consumer payment card accounts that are being inappropriately used to make small business purchases. A small business behavior predictor model is used to score transaction data and update cardholder profiles according to the likelihood that the transaction data represents small business activity.

Claims

1. A method for predicting business behavior of a consumer by analysis of said consumer'"'"'s payment card transactions, the method comprising:

preparing a transaction data batch file that includes consumer payment card transaction data records obtained from a transaction data warehouse; and

processing said transaction data batch file and a behavior model to generate a score based on said consumer payment card transaction data records, wherein said score is a measure of a likelihood that said consumer is conducting business transactions with said consumer payment card.

2. The method of claim 1 wherein preparing the transaction data batch file comprises augmenting said consumer payment card transaction data records with merchant information retrieved from an merchant data warehouse.

3. The method of claim 1 further comprising:

processing a customer profile retrieved from a profile data warehouse; and

assigning said score to said customer profile.

4. The method of claim 3 wherein said processing a customer profile further comprises processing a cardholder account data file retrieved from an account data warehouse.

5. The method of claim 1 further comprising retrieving said behavior model from a model data warehouse.

6. The method of claim 1 wherein said behavior model uses transaction volume and dollar volume to discriminate between business and personal spending.

7. The method of claim 1 wherein the behavior model characterizes a payment card transaction data report as a business spending transaction or a consumer spending transaction according to a merchant category associated with the transaction data report.

8. The method of claim 7 wherein the behavior model characterizes a payment card transaction data report as a consumer spending transaction when the payment card transaction data report is associated with any one of the following merchant categories:

Department Stores, Books, Movies, Videos, Optometry, Groceries, Apparel, Jewelry and Sporting Goods.

9. The method of claim 7 wherein the behavior model characterizes a payment card transaction data report as a business spending transaction when the payment card transaction data report is associated with any one of the following merchant categories:

Office Supplies;

Home Improvement, Travel, Hotel, Airfare, Car Rental, Non-Store Spending, Computers/Software, Couriers and Auto Retail.

10. The method of claim 7 wherein the behavior model is function whose independent variable is a transaction velocity,

11. The method of claim 7 wherein the behavior model is function whose independent variable is a dollar velocity.

12. The method of claim 7 wherein the behavior model is function whose independent variables are a transaction velocity and a dollar velocity.

13. A system for predicting business behavior of a consumer by analysis of said consumer'"'"'s payment card transactions, the system comprising a processing arrangement configured to perform the steps of:

preparing a transaction data batch file that includes consumer payment card transaction data records obtained from a transaction data warehouse; and

processing said transaction data batch file and a behavior model to generate a score based on said consumer payment card transaction data records, wherein said score is a measure of a likelihood that said consumer is conducting business transactions with said consumer payment card.

14. The system of claim 13 wherein the processing arrangement is further configured to prepare the transaction data batch file by augmenting said consumer payment card transaction data records with merchant information retrieved from a merchant data warehouse.

15. The system of claim 13 wherein the processing arrangement is further configured to process a customer profile retrieved from a profile data warehouse;

and assign said score to said customer profile.

16. The system of claim 15 wherein said processing of a customer profile further comprises processing a cardholder account data file retrieved from an account data warehouse.

17. The system of claim 13 wherein the said behavior model is retrieved from a model data warehouse.

18. The system of claim 13 wherein said behavior model uses transaction volume and dollar volume to discriminate between business and personal spending.

19. The system of claim 13 wherein said behavior model characterizes a payment card transaction data report as a business spending transaction or a consumer spending transaction according to a merchant category associated with the transaction data report.

20. The system of claim 19 wherein said behavior model characterizes a payment card transaction data report as a consumer spending transaction when the payment card transaction data report is associated with any one of the following merchant categories:

Department Stores, Books, Movies, Videos, Optometry, Groceries, Apparel, Jewelry and Sporting Goods.

21. The system of claim 19 wherein the behavior model characterizes a payment card transaction data report as a business spending transaction when the payment card transaction data report is associated with any one of the following merchant categories:

Office Supplies;

Home Improvement, Travel, Hotel, Airfare, Car Rental, Non-Store Spending, Computers/Software, Couriers and Auto Retail.

22. The system of claim 19 wherein the behavior model is a function whose independent variable is a transaction velocity,

23. The system of claim 19 wherein the behavior model is a function whose independent variable is a dollar velocity.

24. The system of claim 19 wherein the behavior model is a function whose independent variables are a transaction velocity and a dollar velocity.

25. A computer-readable medium for predicting business behavior of a consumer by analysis of said consumer'"'"'s payment card transactions, the computer-readable medium having a set of instructions operable to direct a processing system to perform the steps of:

preparing a transaction data batch file that includes consumer payment card transaction data records obtained from a transaction data warehouse; and

processing said transaction data batch file and a behavior model to generate a score based on said consumer payment card transaction data records, wherein said score is a measure of a likelihood that said consumer is conducting business transactions with said consumer payment card.

26. The computer-readable medium of claim 25 further comprising instructions operable to direct the processing system to prepare the transaction data batch file by augmenting said consumer payment card transaction data records with merchant information retrieved from a merchant data warehouse.

27. The computer-readable medium of claim 25 further comprising instructions operable to direct the processing system to process a customer profile retrieved from a profile data warehouse and assign said score to said customer profile.

28. The computer-readable medium of claim 27 further comprising instructions operable to direct the processing system to process said customer profile using a cardholder account data file retrieved from an account data warehouse.

29. The computer-readable medium of claim 25 further comprising instructions operable to direct the processing system to retrieve said behavior model from a model data warehouse.

30. The computer-readable medium of claim 25 wherein said behavior model uses transaction volume and dollar volume to discriminate between business and personal spending.

31. The computer-readable medium of claim 25 wherein the behavior model characterizes a payment card transaction data report as a business spending transaction or a consumer spending transaction according to a merchant category associated with the transaction data report.

32. The computer-readable medium of claim 25 wherein the behavior model characterizes a payment card transaction data report as a consumer spending transaction when the payment card transaction data report is associated with any one of the following merchant categories:

Department Stores, Books, Movies, Videos, Optometry, Groceries, Apparel, Jewelry and Sporting Goods.

33. The computer-readable medium of claim 25 wherein the behavior model characterizes a payment card transaction data report as a business spending transaction when the payment card transaction data report is associated with any one of the following merchant categories:

Office Supplies;

Home Improvement, Travel, Hotel, Airfare, Car Rental, Non-Store Spending, Computers/Software, Couriers and Auto Retail.

34. The computer-readable medium of claim 33 wherein the behavior model is function whose independent variable is a transaction velocity,

35. The computer-readable medium of claim 33 wherein the behavior model is function whose independent variable is a dollar velocity.

36. The computer-readable medium of claim 33 wherein the behavior model is function whose independent variables are a transaction velocity and a dollar velocity.

37. A method for predicting business behavior of a consumer from a sample of said consumer'"'"'s payment card transactions, the method comprising:

performing velocity analysis on said sample for a select set of industry categories; and

indicating the business behavior of said consumer according to results of the velocity analysis.

38. The method of claim 37 wherein an industry category in the select set of industry categories is selected from the group consisting of CEA, CSV, TEA−

T+E, TER−

T+E, TEH−

T+E, Office Supplies, Home Improvement, Travel, Hotel, Airfare, Car Rental, Non-Store Spending, Computers/Software, Couriers and Auto Retail and any combination thereof, and wherein indicating the business behavior of said consumer comprises assigning a positive indicator when a velocity in the selected industry category is higher than a threshold.

39. The method of claim 37 wherein an industry category in the select set of industry categories is selected from the group consisting of AAX, INV, Department Stores, Books, Movies, Videos, Optometry, Groceries, Apparel, Jewelry and Sporting Goods, and any combination thereof, and wherein indicating the business behavior of said consumer comprises assigning a negative indicator when a velocity in the selected inudstry category is higher than a threshold.

40. The method of claim 37 wherein the velocity analysis comprises transaction and amount velocity analysis.

41. A system for predicting business behavior of a consumer by analysis of said consumer'"'"'s payment card transactions, the system comprising a processing arrangement configured to perform the steps of:

performing velocity analysis on said sample for a select set of industry categories; and

indicating the business behavior of said consumer according to results of the velocity analysis.

42. The System of claim 41 wherein an industry category in the select set of industry categories is selected from the group consisting of CEA, CSV, TEA−

T+E, TER−

T+E, TEH−

T+E, Office Supplies, Home Improvement, Travel, Hotel, Airfare, Car Rental, Non-Store Spending, Computers/Software, Couriers and Auto Retail and any combination thereof, and wherein indicating the business behavior of said consumer comprises assigning a positive indicator when a velocity in the selected industry category is higher than a threshold.

43. The System of claim 41 wherein an industry category in the select set of industry categories is selected from the group consisting of AAX, INV, Department Stores, Books, Movies, Videos, Optometry, Groceries, Apparel, Jewelry and Sporting Goods, and any combination thereof, and wherein indicating the business behavior of said consumer comprises assigning a negative indicator when a velocity in the selected inudstry category is higher than a threshold.

44. The system of claim 41 wherein the velocity analysis comprises transaction and amount velocity analysis.

45. A computer-readable medium for predicting business behavior of a consumer by analysis of said consumer'"'"'s payment card transactions, the computer-readable medium having a set of instructions operable to direct a processing system to perform the steps of:

performing velocity analysis on said sample for a select set of industry categories; and

indicating the business behavior of said consumer according to results of the velocity analysis.

46. The computer-readable medium of claim 45 wherein an industry category in the select set of industry categories is selected from the group consisting of CEA, CSV, TEA−

T+E, TER−

T+E, TEH−

T+E, Office Supplies, Home Improvement, Travel, Hotel, Airfare, Car Rental, Non-Store Spending, Computers/Software, Couriers and Auto Retail and any combination thereof, and wherein indicating the business behavior of said consumer comprises assigning a positive indicator when a velocity in the selected industry category is higher than a threshold.

47. The computer-readable medium of claim 45 wherein an industry category in the select set of industry categories is selected from the group consisting of AAX, INV, Department Stores, Books, Movies, Videos, Optometry, Groceries, Apparel, Jewelry and Sporting Goods, and any combination thereof, and wherein indicating the business behavior of said consumer comprises assigning a negative indicator when a velocity in the selected inudstry category is higher than a threshold.

48. The computer-readable medium of claim 45 wherein the velocity analysis comprises transaction and amount velocity analysis.