System and method for assessing demographic data accuracy

• US 20030046138A1
• Filed: 08/30/2001
• Published: 03/06/2003
• Est. Priority Date: 08/30/2001
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Fogarty, Bruce William, Cary, Steven Harold
• Granted Patent: US 7,197,471 B2
• Time in Patent Office: Days
• US Class Current: 705/10
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

A system and method for assessing demographic data accuracy from third party data vendors is provided. Third party demographic data is compared to self-reported demographic data; hence compared to data presumed to be accurate. Analysis is done on the comparison to determine the accuracy of the data and if bias exists in the results for a particular demographic population or geographic region. Demographic data from many third parties can be analyzed in the same way, and the results can be compared to each other to determine which third party has the most accurate demographic data elements.

Claims

1. A method of analyzing a data source, said method comprising:

comparing the data source to a reference file;

determining whether the data source is balanced in response to the comparing; and

adjusting the data source based on the determining, wherein the adjusting results in a more balanced data source.

2. The method as described in claim 1 further comprising:

matching one or more records from the data source to one or more reference file records;

generating a comparison master file based on the matching; and

assigning an index number to each record in the comparison master file.

3. The method as described in claim 1 further comprising:

retrieving a rule corresponding to an element in the data source;

determining whether the element in the data source approximates a corresponding value in the reference file based on the retrieved rule; and

assigning a match to the element in response to the determination.

4. The method as described in claim 1 further comprising:

matching one or more records from the data source to one or more reference file records; and

calculating a first bias value based upon the matching.

5. The method as described in claim 4 further comprising:

matching one or more records from a second data source to one or more reference file records;

calculating a second bias value based upon the matching; and

comparing the first bias value to the second bias value.

6. The method as described in claim 1 further comprising:

identifying a first data source sample size;

comparing a first data source sample corresponding to the first data source sample size to the reference file;

determining a match percentage based on the comparing; and

calculating a second data source sample size by dividing the first data source sample size by the match percentage.

7. The method as described in claim 6 further comprising:

identifying a second data source corresponding to the second data source sample size;

matching one or more records from the second data source to one or more reference file records; and

calculating a second match percentage based on the matching.

8. An information handling system comprising:

one or more processors;

a memory accessible by the processors;

one or more nonvolatile storage devices accessible by the processors;

a data source handling tool to manage a data source stored on one of the nonvolatile storage devices, the data source handling tool including;

means for comparing the data source to a reference file stored on one of the nonvolatile storage devices;

means for determining whether the data source is balanced in response to the comparing; and

means for adjusting the data source based on the determining, wherein the adjusting results in a more balanced data source.

9. The information handling system as described in claim 8 further comprising:

means for matching one or more records from the data source to one or more reference file records;

means for generating a comparison master file based on the matching; and

means for assigning an index number to each record in the comparison master file.

10. The information handling system as described in claim 8 further comprising:

means for retrieving a rule corresponding to an element in the data source from one of the nonvolatile storage devices;

means for determining whether the element in the data source approximates a corresponding value in the reference file based on the retrieved rule; and

means for assigning a match to the element in response to the determination.

11. The information handling system as described in claim 8 further comprising:

means for matching one or more records from the data source to one or more reference file records; and

means for calculating a first bias value based upon the matching.

12. The information handling system as described in claim 8 further comprising:

means for matching one or more records from a second data source to one or more reference file records;

means for calculating a second bias value based upon the matching; and

means for comparing the first bias value to the second bias value.

13. The information handling system as described in claim 8 further comprising:

means for identifying a first data source sample size;

means for comparing a first data source sample corresponding to the first data source sample size to the reference file;

means for determining a match percentage based on the comparing; and

means for calculating a second data source sample size by dividing the first data source sample size by the match percentage.

14. The information handling system as described in claim 13 further comprising:

means for identifying a second data source corresponding to the second data source sample size;

means for matching one or more records from the second data source to one or more reference file records; and

means for calculating a second match percentage based on the matching.

15. A computer program product stored in a computer operable media for managing a data source, said computer program product comprising:

means for comparing the data source to a reference file;

means for determining whether the data source is balanced in response to the comparing; and

means for adjusting the data source based on the determining, wherein the adjusting results in a more balanced data source.

16. The computer program product described in claim 15 further comprising:

means for matching one or more records from the data source to one or more reference file records;

means for generating a comparison master file based on the matching; and

means for assigning an index number to each record in the comparison master file.

17. The computer program product described in claim 15 further comprising:

means for retrieving a rule corresponding to an element in the data source from the nonvolatile storage area;

means for determining whether the element in the data source approximates a corresponding value in the reference file based on the retrieved rule; and

means for assigning a match to the element in response to the determination.

18. The computer program product described in claim 15 further comprising:

means for matching one or more records from the data source to one or more reference file records; and

means for calculating a first bias value based upon the matching.

19. The computer program product described in claim 15 further comprising:

means for matching one or more records from a second data source to one or more reference file records;

means for calculating a second bias value based upon the matching; and

means for comparing the first bias value to the second bias value.

20. The computer program product described in claim 15 further comprising:

means for identifying a first data source sample size;

means for comparing a first data source sample corresponding to the first data source sample size to the reference file;

means for determining a match percentage based on the comparing; and

means for calculating a second data source sample size by dividing the first data source sample size by the match percentage.