Attribute combination discovery

1. A computer based method for attribute combination discovery, comprising:

a) receiving a query attribute which identifies, within a first computer memory, a set of query-attribute-positive attribute profiles associated with query-attribute-positive individuals and a set of query-attribute-negative attribute profiles associated with query-attribute-negative individuals;

b) selecting a query-attribute-positive attribute profile from the set of query-attribute-positive attribute profiles a subset of query-attribute-negative attribute profiles from the set of query-attribute-negative attribute profiles;

c) determining a set of candidate attributes by selecting attributes from the query-attribute-positive attribute profile that do not occur in at least a predetermined percentage of the subset of query-attribute-negative attribute profiles;

d) computing the frequencies of occurrence of combinations of the candidate attributes in the set of query-attribute-positive attribute profiles and in the set of query-attribute-negative attribute profiles;

e) computing, based on the frequencies of occurrence, statistical results indicating strength of association of at least some of the attribute combinations with the query attribute; and

f) storing, within a second computer memory, the combinations of candidate attributes having higher frequencies of occurrence in the set of query-attribute-positive attribute profiles than in the set of query-attribute-negative attribute profiles to generate a compilation of attribute combinations that co-occur with the query attribute;

g) tabulating, based on the strength of association, those attribute combinations from the compilation that are most likely to co-occur with the query attribute;

h) applying a threshold that specifies the maximum number of attribute combinations from each tabulation to be transmitted as output; and

h) transmitting at least a portion of the tabulation that is above the threshold as output.

2. The computer based method of claim 1 ,

wherein the transmitting in step (h) is to at least one destination selected from the group consisting of a user, a computer readable memory, a computer readable medium, a printout device, a visual display, and a wireless receiver.

3. The computer based method of claim 1 , wherein tabulating those attribute combinations that are most likely to co-occur with the query attribute comprises:

i) computing, based on the frequencies of occurrence, statistical results indicating strength of association of each of the attribute combinations with the query attribute;

ii) tabulating those attribute combinations that meet one or more statistical requirements with respect to their strength of association with the query attribute; and

iii) including the statistical results in the tabulation.

4. The computer based method of claim 1 , further comprising:

h) repeating steps (a)-(h) for a succession of query attributes.

5. The computer based method of claim 1 , further comprising:

i) associating one or more of the tabulation, the attribute combinations, and the query attribute with an individual and storing the association.

6. The computer based method of claim 5 , wherein storing the association comprises storing a link to one or more of: an identifier of the individual, an attribute profile of the individual, and a record of the individual.

7. The computer based method of claim 1 , wherein the attribute combinations are required to lack one or more specified attributes.

8. The computer based method of claim 1 , wherein the attribute combinations are required to contain one or more specified attributes.

9. The computer based method of claim 1 , wherein the query attribute can be a query attribute combination consisting of two or more attributes.

10. A computer based system, including a data entry device, a display device, a memory, a central processor, and software for operating a machine for attribute combination discovery, comprising:

a) data receiving subsystem means for receiving a query attribute;

b) data accessing subsystem means, operatively connected to said data receiving means, for accessing one or more databases containing attribute profiles for query-attribute-positive individuals and query-attribute-negative individuals; and

c) data tabulating subsystem means, operatively connected to said data accessing subsystem, for selecting a query-attribute-positive attribute profile from the set of query-attribute-positive attribute profiles and a subset of query-attribute-negative attribute profiles from the set of query-attribute-negative attribute profiles, determining a set of candidate attributes by selecting attributes from the query-attribute-positive attribute profile that do not occur in at least a predetermined percentage of the subset of query-attribute-negative attribute profiles; computing the frequencies of occurrence of combinations of the candidate attributes in the set of query-attribute-positive attribute profiles and in the set of query-attribute-negative attribute profiles; computing, based on the frequencies of occurrence, statistical results indicating strength of association of at least some of the attribute combinations with the query attribute; storing the combinations of candidate attributes having higher frequencies of occurrence in the set of query-attribute-positive attribute profiles than in the set of query-attribute-negative attribute profiles to generate a compilation of attribute combinations that co-occur with the query attribute; tabulating attribute combinations that are most likely to co-occur with the query attribute based on the strength of association; and, applying a threshold that specifies the maximum number of attribute combinations from each tabulation to be transmitted as output;

d) statistical computing subsystem means for calculating, based on the frequencies of occurrence, statistical results indicating strength of association of the attribute combinations with one or more query attributes.

11. The computer based system of claim 10 , further comprising:

d) data ranking subsystem means for ranking the attribute combinations based on at least the frequencies of occurrence or the statistical results.

12. The computer based system of claim 10 , further comprising:

d) data storage subsystem means for storing tabulations of attribute combinations, frequencies of occurrence and statistical results.

13. The computer based system of claim 10 , further comprising:

d) communications subsystem means for transmitting one or more attributes, attribute combinations, frequencies of occurrence, statistical results and tabulations as output.