Methods and apparatus to facilitate dynamic classification for market research
Methods and apparatus to facilitate dynamic classification for market research are disclosed. Example disclosed methods include constructing, using a programmed processor based on data for a sample population and a first set of input variables, a self-organizing map classifying the sample population according to a plurality of classes defined in the map using fuzzy class membership. Example disclosed methods include extracting the fuzzy class membership for the sample population from the map. Example disclosed methods include correlating fuzzy class membership with behavior data for the sample population to determine a likely class behavior for the plurality of classes. Example disclosed methods include using fuzzy class membership and the likely class behavior to provide a predictive market output in response to a query.
1. A method to facilitate dynamic classification for market research, the method comprising:
constructing, using a programmed processor based on data for a sample population and a first set of input variables, a self-organizing map classifying the sample population according to a plurality of classes defined in the map using a first fuzzy class membership;
extracting, using the processor, the first fuzzy class membership for the sample population from the map;
correlating, using the processor, the first fuzzy class membership with behavior data for the sample population to determine a first likely class behavior for the sample population with respect to the plurality of classes;
extracting, using the first fuzzy class membership, a second fuzzy class membership for a universe of people from the map;
predicting a second likely class behavior for the universe of people using the second fuzzy class membership and the first likely class behavior; and
using the second fuzzy class membership and the second likely class behavior to provide, using the processor in response to a query, a predictive market output including a description of a subset of the plurality of classes identified from the map to answer the query.
2. The method of claim 1 , wherein the first fuzzy class membership classifies members of the sample population to be members in each of the plurality of classes.
3. The method of claim 1 , wherein the map classifies a member of the sample population with a primary class and a lesser percentage membership in the remaining plurality of classes.
4. The method of claim 1 , further including identifying similar classes based on an analysis of class characteristics from the map.
5. The method of claim 1 , further including constructing a plurality of self-organizing maps based on a plurality of input vectors.
6. The method of claim 1 , wherein the universe of people includes at least one of a population of a state, a population of a region, or a population of a country.
7. The method of claim 1 , further including re-constructing, based on data for a sample population and a second set of input variables, the self-organizing map classifying the sample population according to the plurality of classes defined in the map using at least one of the first fuzzy class membership or the second fuzzy class membership.
8. A tangible computer readable storage medium comprising instruction that, when executed, cause a machine to:
construct, based on data for a sample population and a first set of input variables, a self-organizing map classifying the sample population according to a plurality of classes defined in the map using a first fuzzy class membership;
extract the first fuzzy class membership for the sample population from the map;
correlate the first fuzzy class membership with behavior data for the sample population to determine a first likely class behavior for the sample population with respect to the plurality of classes;
extract, using the first fuzzy class membership, a second fuzzy class membership for a universe of people from the map;
predict a second likely class behavior for the universe of people using the second fuzzy class membership and the first likely class behavior; and
use the second fuzzy class membership and the second likely class behavior to provide in response to a query, a predictive market output including a description of a subset of the plurality of classes identified from the map to answer the query.
9. The computer readable storage medium of claim 8 , wherein the first fuzzy class membership classifies members of the sample population to be members in each of the plurality of classes.
10. The computer readable storage medium of claim 9 , wherein the map classifies a member of the sample population with a primary class and a lesser percentage membership in the remaining plurality of classes.
11. The computer readable storage medium of claim 8 , having instructions that, when executed, cause the machine to, identify similar classes based on an analysis of class characteristics from the map.
12. The computer readable storage medium of claim 8 , having instructions that, when executed, cause the machine to construct a plurality of self-organizing maps based on a plurality of input vectors.
13. The computer readable storage medium of claim 8 , wherein the universe of people includes at least one of a population of a state, a population of a region, or a population of a country.
14. The computer readable storage medium of claim 8 , having instructions that, when executed, cause the machine to re-construct, based on data for a sample population and a second set of input variables, the self-organizing map classifying the sample population according to the plurality of classes defined in the map using at least one of the first fuzzy class membership or the second fuzzy class membership.
15. An apparatus comprising:
memory; and
a processor particularly programmed to:
construct, based on data for a sample population and a first set of input variables, a self-organizing map classifying the sample population according to a plurality of classes defined in the map using a first fuzzy class membership;
extract the first fuzzy class membership for the sample population from the map;
correlate the first fuzzy class membership with behavior data for the sample population to determine a first likely class behavior for the plurality of classes;
extract, using the first fuzzy class membership, a second fuzzy class membership for a universe of people from the map;
predict a second likely class behavior for the universe of people using the second fuzzy class membership and the first likely class behavior; and
use the second fuzzy class membership and the second likely class behavior to provide in response to a query, a predictive market output including a description of a subset of the plurality of classes identified from the map to answer the query.
16. The apparatus of claim 15 , wherein the first fuzzy class membership classifies members of the sample population to be members in each of the plurality of classes.
17. The apparatus of claim 16 , wherein the map classifies a member of the sample population with a primary class and a lesser percentage membership in the remaining plurality of classes.
18. The apparatus of claim 15 , wherein the processor is to:
identify similar classes based on an analysis of class characteristics from the map.
19. The apparatus of claim 15 , wherein the processor is to:
construct a plurality of self-organizing maps based on a plurality of input vectors.
20. The apparatus of claim 15 , wherein the processor is to:
re-construct, based on data for a sample population and a second set of input variables, the self-organizing map classifying the sample population according to the plurality of classes defined in the map using at least one of the first fuzzy class membership or the second fuzzy class membership.
21. A method to cluster data into similar groups for market research, the method comprising:
constructing, based on data for a sample population and a first set of input variables, a self-organizing map classifying the sample population according to a plurality of classes defined in the map using a first fuzzy class membership;
extracting the first fuzzy class membership for the sample population from the map;
correlating the first fuzzy class membership with behavior data for the sample population to determine a first likely class behavior for the plurality of classes; and
extracting, using the first fuzzy class membership, a second fuzzy class membership for a universe of people from the map;
predicting a second likely class behavior for the universe of people using the second fuzzy class membership and the first likely class behavior; and
using the second fuzzy class membership and the second likely class behavior to provide, in response to a query, a predictive market output including a description of a subset of the plurality of classes identified from the map to answer the query.
22. A method comprising:
constructing a self-organizing map classifying respondents according to a first set of input variables defining parameters associated with the respondents, the self-organizing map clustering and distributing the respondents according to a plurality of classes defined in the self-organizing map using a respondent fuzzy class membership;
predicting, based on the respondent fuzzy class membership and respondent behavior data, a respondent class behavior;
extrapolating universe fuzzy class membership based on the respondent fuzzy class membership and the self-organizing map;
predicting a universe class behavior using the universe fuzzy class membership and the respondent class behavior; and
providing an output including at least one of the respondent class behavior or the universe class behavior, associated class characteristic, and class identification, the output to trigger action with respect to a population associated with the output in response to a query.
23. The method of claim 22 , wherein the self-organizing map includes a plurality of layers, each layer corresponding to an input variable in the set of input variables.
24. The method of claim 22 , wherein predicting a class behavior is triggered by a request for a market behavior prediction.
25. The method of claim 22 , further including constructing a second self-organizing map classifying respondents according to a second set of input variables defining parameters associated with the respondents.