Credit portfolio benchmarking system and method

• US 7,676,418 B1
• Filed: 06/26/2006
• Issued: 03/09/2010
• Est. Priority Date: 06/24/2005
• Status: Active Grant

• Current Assignee: Experian Information Solutions Incorporated (Experian plc)
• Original Assignee: Experian Information Solutions Incorporated (Experian plc)
• Inventors: Haran, Linda A., Lassen, Patricia Cheryl, Chung, Charles S., Granger, Angela
• Primary Examiner(s): Cheung; Mary
• Assistant Examiner(s): OJIAKU, CHIKAODINAKA
• Application Number:
  US11/475,428
• Time in Patent Office: 1,352 Days
• Field of Search: 703/1, 702/57, 702185-186, 707 1- 5, 707200-201, 705/4, 706/12
• US Class Current: 705/36.00R
• CPC Class Codes: G06Q 10/06393 Score-carding, benchmarking or key performance indicator [KPI] analysis
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/03 Credit; Loans; Processing thereof
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A portfolio benchmarking system comprises a repository of trade data, a repository of consumer data, a build computer, and a benchmarking query application. The repository of trade data comprises a plurality of data items regarding trade lines. The repository of consumer data comprises a plurality of data items regarding consumers, wherein at least some information in the consumer data is not in the trade data and at least some information in the trade data is not in the consumer data. The build computer periodically generates at least one data file comprising a plurality of data items, each data item combining information from the trade data and the consumer data, such that searches can be performed on the combined data without joining trade data and consumer data at query run time. The benchmarking query application executes queries on the data file generated by the build computer.

Claims

1. A credit portfolio benchmarking system comprising:

a repository of trade data comprising a plurality of data items regarding trade lines including data for one or more loans;

a repository of consumer data comprising a plurality of data items regarding consumers including one or more names, addresses, and credit scores, wherein at least some information in the consumer data is private data that is confidential to the consumers and not in the trade data and at least some information in the trade data is not in the consumer data;

a build computer programmed to periodically generate at least one data file comprising a plurality of data items, each data item combining information from the trade data and the consumer data by merging trade line data with associated consumer data so that the trade line data and consumer data are in a same table and the merged data includes data that categorizes the data into one or more peer groups of lending institutions; and

a benchmarking query application programmed to execute queries in real time or near real time for information about a first lending institution, determine peers of the first lending institution based on information in the at least one data file generated by the build computer, determine respective credit portfolios of the first lending institution and its peers based on a current mixture of trade data indicated in the merged trade line data and consumer data for the first lending institution and its peers, and generate an anonymized report that shows the credit portfolio of the first lending institution benchmarked against its peers.

2. The system of claim 1, wherein the benchmarking application is programmed to execute queries that take into account at least a population definition.

3. The system of claim 2, wherein the benchmarking application is programmed to execute queries that also take into account at least an attribute selection.

4. The system of claim 3, wherein the benchmarking application is programmed to execute queries that also take into account at least a population segmentation.

5. The system of claim 4, wherein the benchmarking application comprises a user input component that receives user-entered parameter values related to the population definition, the attribute selection, and the population segmentation.

6. The system of claim 5, wherein the user input component of the benchmarking application comprises an active query build portion comprising a portion of a display screen that remains visible during user entry of a query.

7. The system of claim 6, wherein the active query build portion further comprises hypertext links associated with parameter values that have been entered, wherein a user may invoke one of the hypertext links in order to edit an entered parameter value.

8. A computer-implemented method of providing credit portfolio benchmarking reports, the method comprising:

generating by a computer a data file that comprises information combined from trade data including data from one or more loans, and consumer data including one or more names, addresses, and credit scores, wherein at least some information in the consumer data is private data that is confidential to the consumers, the combined data file including a single table that merges trade data with consumer data and categorizes merged trade data and consumer data into one or more peer groups of lending institutions;

populating by the computer a benchmarking database that comprises at least part of the data file combined from the trade data and the consumer data;

running a query by the computer on the benchmarking database in real time or near real time for gathering information about a first lending institution, determining peers of the first lending institution based on information in the combined data file, determining respective credit portfolios of the first lending institution and its peers based on a current mixture of trade data indicated in the merged trade line data and consumer data for the first lending institution and its peers; and

generating by the computer an anonymized credit portfolio benchmarking report at least in part from results of the query that shows a credit portfolio of the first lending institution benchmarked against at least one of its peers.

9. The method of claim 8, further comprising receiving a user selection of a portfolio benchmarking report service level, wherein the generating by the computer a credit portfolio benchmarking report provides differing levels of information depending on the selected service level.

10. The method of claim 8, wherein generating by the computer a credit portfolio benchmarking report comprises providing a report that includes a list of top peers competing for accounts of a particular type.

11. The method of claim 10, wherein the list of top peers includes a minimum number of peers to make it difficult to determine portfolio characteristics regarding a specific peer from the credit portfolio benchmarking report.

12. The method of claim 8, further comprising storing a current month data file and a plurality of archive data files for data from different time periods, such that queries can be run on different time periods in order to determine trends related to credit portfolio benchmarking.

13. The method of claim 12, wherein storing a current month data file and a plurality of archive data files comprises storing at least 24 monthly archive data files.

14. The method of claim 8, wherein generating a data file comprises taking a statistical sample of at least 20% of total available data items in the trade data and the consumer data.

15. A computer executable code recorded in a computer readable medium, the computer executable code configured to cause a general purpose computer to:

receive user input regarding query parameters for querying a credit portfolio benchmarking database comprising trade data including one or more loans, and consumer data including one or more consumer names, addresses, and credit scores, wherein at least some information in the consumer data is private data that is confidential to the consumers, that are merged into a single table, and data that categorizes the merged data into one or more peer groups of lending institutions and generating a query report, the parameters relating to defining a query population, segmenting the population, and selecting attributes;

query the credit portfolio benchmarking database and select peer institutions for a first lending institution in real time or near real time; and

generate an anonymized credit portfolio benchmarking report based on results of the query operation that shows a credit portfolio of the first lending institution benchmarked against the selected peer institutions, wherein the credit portfolio benchmarking report is derived at least in part from both trade data and consumer data.

16. The computer executable code of claim 15, wherein the user input received regarding query parameters includes at least a parameter for specifying a time period for the credit portfolio benchmarking report.

17. The computer executable code of claim 16, wherein the user input received regarding query parameters further includes at least a parameter for specifying one or more account types.

18. The computer executable code of claim 17, wherein the user input received regarding query parameters further includes at least a parameter for specifying a peer group.

19. The computer executable code of claim 18, wherein the user input received regarding query parameters further includes at least a parameter for specifying one or more geographical areas.