SYSTEMS AND METHODS OF RANKING A PLURALITY OF CREDIT CARD OFFERS

• US 20080059352A1
• Filed: 08/30/2007
• Published: 03/06/2008
• Est. Priority Date: 08/31/2006
• Status: Active Grant

• Current Assignee: CPL Assets LLC
• Original Assignee: Experian Interactive Innovation Center, LLC (Experian plc)
• Inventors: Chandran, Rohan
• Granted Patent: US 8,799,148 B2
• Time in Patent Office: Days
• US Class Current: 705/35
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 20/354 Card activation or deactivation
• CPC Class Codes: G06Q 30/0246 Traffic
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof

Abstract

Prescreened credit card offers, such as offers for credit cards that a particular potential borrower is likely to be granted upon completion of a full application, are ranked based on expected values of respective prescreened offers. The expected value of a prescreened credit card offer may represent an expected monetary value to one or more referrers involved in providing the prescreened offer to the borrower. Thus, the referrer may present a highest ranked credit card offer to a potential borrower first in order to increase the likelihood that borrower applies for the credit card offer with the highest expected value to the referrer. Depending on the embodiment, the expected value of a credit card offer may be based on a combination of a bounty associated with the offer, a click-through-rate for the offer, and/or a conversion rate for the offer, for example.

Claims

1. A computerized system for presenting prescreened credit card offers to a borrower, the system comprising:

a prescreen module configured to receive an indication of one or more prescreened credit card offers for a borrower, wherein the borrower has at least about a 90% likelihood of being issued a credit card associated with each of the prescreened credit card offers after completing a corresponding full credit card application;

a ranking module configured to assign a unique rank to at least some of the prescreened credit card offers, wherein determination of respective ranks for the prescreened credit card offers is based on at least a bounty and a click-thru-rate associated with respective prescreened credit card offers;

a presentation module configured to generate a data structure comprising information regarding at least a highest ranked credit card offer.

2. The computerized system of claim 1, wherein the data structure comprises one of a text file, a spreadsheet file, a database file, an HTML file, and an XML file.

3. The computerized system of claim 1, further comprising a credit data store comprising credit data associated with the borrower, wherein the one or more prescreened offers are determined based at least partly on the credit data associated with the borrower.

4. The computerized system of claim 1, further comprising a credit issuer data store comprising indications of credit card qualification criteria for a plurality of credit cards, wherein the one or more prescreened credit card offers are determined based at least partly on comparison of respective credit card qualification criteria with characteristics of the borrower.

5. The computerized system of claim 1, wherein a name and an address of the borrower are entered by the borrower into a web interface and transmitted to the prescreen module via a network communication link.

6. The computerized system of claim 5, wherein software code for rendering the web interface is transmitted to a computing device used by the borrower.

7. The computerized system of claim 5, wherein software code for rendering the web interface is transmitted to a computing device used by the borrower from a third party website.

8. The computerized system of claim 1, wherein the determination of respective ranks for the prescreened credit card offers is further based on one or more of:

a historical click-through-rate, a historical conversion rate, a geographic location of the borrower, a click propensity of the borrower, a time of day, a day of week, and a desired display rate for respective prescreened credit card offers.

9. A method of determining an expected value for each of a plurality of credit card offers, the method comprising:

receiving an indication of a plurality of prescreened credit card offers associated with an individual;

receiving an indication of a plurality of attributes associated with each of the prescreened credit card offers; and

calculating an expected value for each of the prescreened credit card offers using at least two of the plurality of attributes for each respective prescreened credit card offer.

10. The method of claim 9, wherein the attributes comprise values representing one or more of:

a bounty, a historical click-through-rate, a historical conversion rate, a special interest of the borrower, a geographic location of the borrower, a click propensity of the borrower, a time of day, a day of week, and a desired display rate for respective prescreened credit card offers.

11. The method of claim 9, wherein the at least two of the plurality of attributes comprise a bounty value associated with a bounty for respective prescreened credit card offers and a click-though-rate value associated with a click-through-rate for respective prescreened credit card offers, wherein the respective expected values for the prescreened credit card offers are calculated by multiplying respective bounty values and click-through-rate values.

12. The method of claim 11, wherein the at least two of the plurality of attributes further comprises a conversion value associated with a historical conversion rate for respective prescreened credit card offers, wherein the respective expected values for the prescreened credit card offers are calculated by multiplying respective bounty values, click-through-rate values, and conversion values.

13. The method of claim 9, wherein respective expected values for the prescreened credit card offers are calculated by multiplying respective bounty values and respective values associated with one or more of the geographic location of the borrower, the time of day, the day of week, the click propensity, and the special interest.

14. The method of claim 9, wherein the at least two of the plurality of attributes comprise only a click-though-rate value associated with a click-through-rate for respective prescreened credit card offers and a conversion value associated with a historical conversion rate for respective prescreened credit card offers, wherein the respective expected values for the prescreened credit card offers are calculated by multiplying respective click-through-rate values and conversion values.

15. A method of determining prescreened credit card offers, the method comprising:

receiving information regarding a borrower from a referring website;

determining two or more prescreened credit card offers associated with the borrower;

determining ranking criteria associated with the referring website, the ranking criteria comprising an indication of attributes associated with one or more of the borrower and respective prescreened credit card offers;

calculating an expected value of the two or more prescreened credit card offers based at least on the attributes indicated in the ranking criteria; and

transmitting a data file to the referring website, the data file comprising an identifier of one of the prescreened credit card offers having an expected value higher than the expected values of the other prescreened credit card offers.

16. The method of claim 15, wherein the ranking criteria comprises a plurality of multipliers associated with respective of the attributes.

17. The method of claim 15, wherein the attributes comprise one or more of:

a bounty, a historical click-through-rate, a historical conversion rate, a geographic location of the borrower, a modeled overall click propensity for the borrower, a time of day, a day of week, and a desired display rate for respective prescreened credit card offers.

18. The method of claim 15, wherein the data file further comprises identifiers of one or more prescreened credit card offers having expected values lower than the prescreened credit card offer having the highest expected value.

19. The method of claim 15, further comprising:

receiving information regarding a second borrower from a second referring website;

determining two or more second prescreened credit card offers associated with the second borrower;

determining second ranking criteria associated with the second referring website, the second ranking criteria comprising an indication of second attributes associated with one or more of the second borrower and respective second prescreened credit card offers;

calculating a second expected value of the two or more second prescreened credit card offers based at least on the second attributes indicated in the second ranking criteria; and

transmitting a second data file to the second referring website, the second data file comprising a second identifier of one of the second prescreened credit card offers having a second expected value higher than the second expected values of the remaining second prescreened credit card offers.

20. A method of ranking a plurality of credit card offers that have been prescreened for presentation to a potential borrower, the method comprising:

receiving information regarding each of a plurality of prescreened credit card offers;

determining an expected value of each of the prescreened credit card offers, wherein the expected value for a particular credit card offer is based on at least (1) a money amount payable to a referrer if the potential borrower is issued a particular credit card associated with the particular credit card offer, (2) an expected ratio of potential borrowers that will apply for the particular credit card offer in response to being presented with the particular credit card offer, and (3) an expected ratio of potential borrowers that will be issued the particular credit card associated with the particular credit card offer; and

ranking the plurality of credit card offers based on the expected values for the respective credit card offers.

21. The method of claim 20, wherein only the credit card offer with the highest ranking is displayed to the potential borrower.

22. The method of claim 20, wherein two or more of the credit card offers are displayed to the potential borrower in an order based on their respective rankings.

23. The method of claim 22, wherein the two or more credit card offers are displayed in a user interface provided by a commercial website.

24. The method of claim 20, wherein the expected value for a particular credit card offer comprises the product of values representing (1) the money amount payable to the referrer if the potential borrower is issued the particular credit card, (2) the expected ratio of potential borrowers that will apply for the particular credit card offer in response to being presented with the particular credit card offer, and (3) the expected ratio of potential borrowers that will be issued the particular credit card associated with the particular credit card offer.