Patent US8935198B1 successfully refreshed from Google Patents.
US8935198B1
Active / In Force
US
⏱️ 4.9 years remaining
Analysis and prediction of data using clusterization
Assignee: C4cast com Inc
•
Filing: 2011-09-20
•
Granted: 2015-01-13
•
Expires: 2031-09-20
Abstract
Abstract Provided are, among other things, systems, methods and techniques for forecasting information. One representative embodiment involves obtaining data that has been provided by each of a number of individual people; dividing the people into clusters by utilizing a statistical clustering technique; calculating statistics of the data in each of at least some of the clusters; and combining the statistics for such clusters so as to obtain a combination forecast.
Inventors
- 👤 G. Michael Phillips
- 👤 William P. Jennings
- 👤 Stephen A. Klein
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 18:11
CPC Classifications
G; G06; G06Q; G06Q40/00; G06Q10/00; G06Q10/04
Claims Analysis
Total Claims: 31
Claim 1
Independent Claim
125 words
A non-transitory computer-readable medium storing computer-executable process steps for forecasting information, said process steps comprising: obtaining data that has been provided by each of a plurality of individual people; dividing the people into clusters by utilizing a statistical clustering technique; calculating statistics of the data in each of a plurality of the clusters; and combining the statistics for the plurality of the clusters so as to obtain a combination forecast, wherein said statistics include a cluster statistic for each corresponding cluster, wherein each said cluster statistic, for a particular cluster, is weighted based on at least one of dispersion within said particular cluster or historical accuracy of said particular cluster, and wherein said cluster statistics are combined using said weightings to produce the combination forecast.
Claim 2
Dependent Claim
125 words
A non-transitory computer-readable medium storing computer-executable process steps for forecasting information, said process steps comprising: obtaining data that has been provided by each of a plurality of individual people; dividing the people into clusters by utilizing a statistical clustering technique; calculating statistics of the data in each of a plurality of the clusters; and combining the statistics for the plurality of the clusters so as to obtain a combination forecast, wherein said statistics include a cluster statistic for each corresponding cluster, wherein each said cluster statistic, for a particular cluster, is weighted based on at least one of dispersion within said particular cluster or historical accuracy of said particular cluster, and wherein said cluster statistics are combined using said weightings to produce the combination forecast.
Claim 3
Dependent Claim
28 words
A non-transitory computer-readable medium according to claim 1 , wherein the data has been obtained from the people through at least one of a survey or a poll.
Claim 4
Dependent Claim
17 words
A non-transitory computer-readable medium according to claim 1 , wherein the combination forecast pertains to consumer sentiment.
Claim 5
Dependent Claim
18 words
A non-transitory computer-readable medium according to claim 1 , wherein the combination forecast pertains to a consumer trend.
Claim 6
Dependent Claim
18 words
A non-transitory computer-readable medium according to claim 1 , wherein the combination forecast pertains to a societal trend.
Claim 7
Dependent Claim
29 words
A non-transitory computer-readable medium according to claim 1 , wherein the data obtained from the people comprises click-through information indicating whether the people clicked on at least one link.
Claim 8
Dependent Claim
25 words
A non-transitory computer-readable medium according to claim 6 , wherein the click-through information comprises at least one of click-through rates or changes in click-through rates.
Claim 9
Dependent Claim
22 words
A non-transitory computer-readable medium according to claim 1 , wherein the data obtained from the people comprises reaction to a new product.
Claim 10
Dependent Claim
19 words
A non-transitory computer-readable medium according to claim 1 , wherein the data obtained from the people comprises personal preferences.
Claim 11
Dependent Claim
26 words
A non-transitory computer-readable medium according to claim 1 , wherein the clusters have been defined based on a comparison of previous data obtained from the people.
Claim 12
Dependent Claim
21 words
A non-transitory computer-readable medium according to claim 1 , wherein the clusters have been defined by utilizing a statistical clustering technique.
Claim 13
Dependent Claim
70 words
A non-transitory computer-readable medium according to claim 1 , wherein said process steps further comprise a step of utilizing the clusters to produce combination forecasts for a variety of time periods, wherein at least some of the people participate inconsistently, and wherein for a given time period the statistics for the clusters are calculated only with respect to the people who have participated with respect to said given time period.
Claim 14
Dependent Claim
16 words
A non-transitory computer-readable medium according to claim 1 , wherein the people comprise thousands of individuals.
Claim 15
Dependent Claim
22 words
A non-transitory computer-readable medium according to claim 1 , wherein the clusters are formed simultaneously with assigning the people to said clusters.
Claim 16
Dependent Claim
30 words
A non-transitory computer-readable medium according to claim 1 , wherein the statistics calculated for each of the plurality of the clusters includes a central tendency and a measure of dispersion.
Claim 17
Dependent Claim
39 words
A non-transitory computer-readable medium according to claim 15 , wherein when the statistics for the plurality of the clusters are combined, the central tendency for each said cluster is weighted according to the measure of dispersion for said cluster.
Claim 18
Dependent Claim
41 words
A non-transitory computer-readable medium according to claim 15 , wherein when the statistics for the plurality of the clusters are combined, the central tendency for each said cluster is weighted according to previous predictive accuracy of the data within said cluster.
Claim 19
Dependent Claim
45 words
A non-transitory computer-readable medium according to claim 17 , wherein when the statistics for the plurality of the clusters are combined, the central tendency for each said cluster is weighted according to a prediction accuracy of central tendencies of previous predictions originating from said cluster.
Claim 20
Dependent Claim
20 words
A non-transitory computer-readable medium according to claim 1 , wherein the clusters have been defined using a statistical regression technique.
Claim 21
Dependent Claim
38 words
A non-transitory computer-readable medium according to claim 1 , wherein said process steps further comprise a step of identifying an assignment formula for assigning a new person to a cluster based on personal characteristics of said new person.
Claim 22
Dependent Claim
35 words
A non-transitory computer-readable medium according to claim 20 , wherein said assignment formula minimizes a distance based on said personal characteristics between the new person and the cluster to which the new person is assigned.
Claim 23
Dependent Claim
52 words
A non-transitory computer-readable medium according to claim 20 , further comprising a step of repeating said dividing step by assigning a first subset of people to the clusters based on previous similarities in the data they provided and assigning a second subset of people to the clusters based on the assignment formula.
Claim 24
Dependent Claim
26 words
A non-transitory computer-readable medium according to claim 1 , wherein the clusters are defined based on a comparison of at least two different types of data.
Claim 25
Dependent Claim
29 words
A non-transitory computer-readable medium according to claim 1 , wherein said process steps further comprise a step of periodically re-clustering the people to obtain a new set of clusters.
Claim 26
Dependent Claim
34 words
A non-transitory computer-readable medium according to claim 1 , wherein the combination forecast is a forecast of a value of a variable representing a type of data that has been obtained from the people.
Claim 27
Dependent Claim
34 words
A non-transitory computer-readable medium according to claim 1 , wherein said process steps further comprise a step of utilizing the combination forecast in an interpolation model to predict a value of a different variable.
Claim 28
Independent Claim
124 words
An apparatus for forecasting information, comprising: means for obtaining data that has been provided by each of a plurality of individual people; means for dividing the people into clusters by utilizing a statistical clustering technique; means for calculating statistics of the data in each of a plurality of the clusters; and means for combining the statistics for the plurality of the clusters so as to obtain a combination forecast, wherein said statistics include a cluster statistic for each corresponding cluster, wherein each said cluster statistic, for a particular cluster, is weighted based on at least one of dispersion within said particular cluster or historical accuracy of said particular cluster, and wherein said cluster statistics are combined using said weightings to produce the combination forecast.
Claim 29
Independent Claim
124 words
An apparatus for forecasting information, comprising: means for obtaining data that has been provided by each of a plurality of individual people; means for dividing the people into clusters by utilizing a statistical clustering technique; means for calculating statistics of the data in each of a plurality of the clusters; and means for combining the statistics for the plurality of the clusters so as to obtain a combination forecast, wherein said statistics include a cluster statistic for each corresponding cluster, wherein each said cluster statistic, for a particular cluster, is weighted based on at least one of dispersion within said particular cluster or historical accuracy of said particular cluster, and wherein said cluster statistics are combined using said weightings to produce the combination forecast.
Claim 30
Independent Claim
118 words
A method of forecasting information, said method comprising: obtaining data that has been provided by each of a plurality of individual people; dividing the people into clusters by utilizing a statistical clustering technique; calculating statistics of the data in each of a plurality of the clusters; and combining the statistics for the plurality of the clusters so as to obtain a combination forecast, wherein said statistics include a cluster statistic for each corresponding cluster, wherein each said cluster statistic, for a particular cluster, is weighted based on at least one of dispersion within said particular cluster or historical accuracy of said particular cluster, and wherein said cluster statistics are combined using said weightings to produce the combination forecast.
Claim 31
Independent Claim
118 words
A method of forecasting information, said method comprising: obtaining data that has been provided by each of a plurality of individual people; dividing the people into clusters by utilizing a statistical clustering technique; calculating statistics of the data in each of a plurality of the clusters; and combining the statistics for the plurality of the clusters so as to obtain a combination forecast, wherein said statistics include a cluster statistic for each corresponding cluster, wherein each said cluster statistic, for a particular cluster, is weighted based on at least one of dispersion within said particular cluster or historical accuracy of said particular cluster, and wherein said cluster statistics are combined using said weightings to produce the combination forecast.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2018-01-12 | 2018-07-14 | 2019-01-13 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2022-01-12 | 2022-07-14 | 2023-01-13 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2026-01-12 | 2026-07-14 | 2027-01-13 | $7700.00 | Surcharge Window Open |