System and method for predicting demand for items

• US 7,885,849 B2
• Filed: 06/07/2004
• Issued: 02/08/2011
• Est. Priority Date: 06/05/2003
• Status: Active Grant

• Current Assignee: Xylon LLC (Intellectual Ventures LLC)
• Original Assignee: Hayley Logistics LLC (Intellectual Ventures LLC)
• Inventors: Gross, John N.
• Primary Examiner(s): Jeanty; Romain
• Assistant Examiner(s): Fleischer; Mark A
• Application Number:
  US10/862,931
• Publication Number:
  US 20040260600A1
• Time in Patent Office: 2,437 Days
• Field of Search: 705/10
• US Class Current: 1/1
• 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: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

A system and method for determining and identifying demand for items based on observing behavior of trendsetters within a member population, such as an online community. The trendsetters are determined by studying historical adoption behavior of a group within the member population.

Claims

1. A method of identifying demand by an online community for a particular item, comprising:

compiling, by way of a system network device, a set of N items {X₁, X₂, . . . , X_i, . . . , X_N},

wherein for each item X_i amongst the set of N items, a plurality of M early adopter members {Y[X_i]₁ . . . Y[X_i]_M} is determined resulting in N separate sets of M early adopter members, said M early adopter members being determined based on a time of adoption of said item X_i;

determining, by way of the system network device, a set K of the early adopter members that occur most frequently in the set {Y[X_i]_j} from N separate sets of M early adopter members, where 1≦

i≦

N and 1≦

j≦

M,

wherein said most frequently occurring early adopter members are classified as trend predictors;

introducing the particular item for adoption by the K early adopter members; and

measuring, by way of the system network device, an acceptance value for the particular item by the K early adopter members.

2. The method of claim 1, further comprising:

using, by way of the system network device, the acceptance value for the particular item by the K early adopter members to predict a demand of consumers outside of the online community for a related item.

3. A method of identifying demand by an online community for a particular item, comprising:

compiling, by way of a system network device, a set of N items {X₁, X₂, . . . , X_i, . . . , X_N},

wherein for each item X_i amongst the set of N items, a plurality of M late adopter members {Y[X_i]₁ . . . Y[X_i]_M} is determined resulting in N separate sets of M late adopter members, said M late adopter members being determined based on a time of adoption of said item X_i;

determining, by way of the system network device, a set K of the later adopter members that occur most frequently in the set {Y[X_i]_j} from N separate sets of M late adopter members, where 1≦

i≦

N and 1≦

j≦

M,

wherein said least frequently occurring late adopter members are classified as trend laggers;

introducing the particular item for adoption by the K late adopter members; and

measuring, by way of the system network device, an acceptance value for the particular item by the K late adopter members of the online community.

4. The method of claim 3, further comprising:

using, by way of the system network device, the acceptance value for the particular item by the K late adopter members to predict a demand of consumers outside of the online community for a related item.

5. A method of identifying predicted demand for an item, comprising:

identifying, by way of a system network device, a group of trend predictor members within an electronic online community,

wherein the group of trend predictor members are chosen from a group of early adopter members, which are characterized by a ranking of their time of adoption for an item that is among the first in the online community and the item is later adopted by other members of the online community;

identifying, by way of the system network device, one or more items rejected by said group of trend predictor members, by monitoring their activities during electronic data collection sessions; and

compiling, by way of the system network device, a list of the one or more rejected items.

6. The method of claim 5, further comprising:

identifying, by way of the system network device, a group of trend rejecter members within the electronic online community, the group of trend rejecter members being characterized as members who have adopted more than half of the one or more rejected items.

7. The method of claim 6, further comprising:

calculating, by way of the system network device, an item rejection prevalence rate among the trend predictor members for each of the one or more rejected items.

8. The method of claim 7, further comprising:

disseminating, by way of the system network device, advertising to the trend predictor members for at least one selected rejected item; and

measuring, by way of the system network device, any change in the item rejection prevalence rate for the at least one selected rejected item.

9. A method of identifying potential demand for at least one of a new product and a new service within a market, comprising:

identifying, by way of a system network device, at least one product or service which is characterized as being in demand by a majority of an electronic community;

identifying, by way of the system network device, early adopters of the at least one product or service within the electronic community,

wherein the early adopters are characterized by a ranking of their time of adoption for an item that is among the first in the online community and the item is later adopted by other members of the online community; and

monitoring, by way of the system network device, the activities of the early adopter members during a plurality of electronic data collection sessions, to determine a score for their collective impressions of the new product and/or new service.

10. The method of claim 9, wherein the monitoring is performed before the at least one of the new product and the new service is introduced into the market.

11. The method of claim 9, further comprising:

presenting, by way of the system network device, advertising materials to the early adopter members; and

measuring a change in the score for their collective impressions of the new products or new services.

12. A method of identifying trend predictor items within a set of items available to an online community, comprising:

identifying, by way of a system network device, a first item having an adoption rate above a first predetermined level;

calculating, by way of the system network device, a score reflecting the percentage of times the first item and one or more second items having an adoption rate below a second predetermined level are presented together;

identifying, by way of the system network device, at least one second item which has an upper-half score relative to the first item, and has a lower-half score relative to others of the one or more second items; and

repeating the calculating and the identifying to identify a first set of first items that each have adoption rates above the first predetermined level, and a second set of second items that have the correlation score relative to the first set of first items above a third predetermined level.

13. The method of claim 12, further comprising:

measuring, by way of the system network device, a new score of the second set of items relative to a newly introduced item to generate a prediction of a demand for the newly introduced item.

14. A system for identifying demand by an online community for a particular item, comprising:

a software module executing on a computing device, the software module being configured for;

compiling a set of N items {X₁, X₂, . . . , X_i, . . . , X_N},

wherein for each item X_i amongst the set of N items, a plurality of M early adopter members {Y[X_i]₁ . . . Y[X_i]_M} is determined resulting in N separate sets of M early adopter members, said M early adopter members being determined based on a time of adoption of said item X_i;

determining a set K of the early adopter members that occur most frequently in the set {Y[X_i]_j} from N separate sets of M early adopter members, where 1≦

i≦

N and 1≦

j≦

M,

wherein said most frequently occurring early adopter members are classified as trend predictors;

introducing the particular item for adoption by the K early adopter members;

storing profiles for the early adopter members in a trendsetter database; and

measuring an acceptance value for the particular item by the K early adopter members of the online community.

15. The system of claim 14, wherein said computing device is an Internet based sever supporting a website maintained by an e-commerce operator.

16. The system of claim 14, wherein the particular item is a product.

17. The system of claim 14, wherein the early adopter members are web pages.

18. The system of claim 14, wherein the early adopter members are extracted from purchasing records of individuals having a common geographic demographic.

19. The system of claim 14, wherein the members of the online community are ranked by adoption date for items to identify the early adopter members.

20. A tangible computer-readable storage medium having stored thereon in digital format, computer-executable instructions that, in response to execution by a computing device, cause the computing device to perform operations for identifying demand by an online community for a particular item, comprising:

compiling a set of N items {X₁, X₂, . . . , X_i, . . . , X_N},

wherein for each item X_i amongst the set of N items, a plurality of M early adopter members {Y[X_i]₁ . . . Y[X_i]_M} is determined resulting in N separate sets of M early adopter members, said M early adopter members being determined based on a time of adoption of said item X_i;

determining a set K of the early adopter members that occur most frequently in the set {Y[X_i]_j} from N separate sets of M early adopter members, where 1≦

i≦

N and 1≦

j≦

M,

wherein said most frequently occurring early adopter members are classified as trend predictors;

introducing the particular item for adoption by the K early adopter members; and

measuring an acceptance value for the particular item by the K early adopter members of the online community.

21. A tangible computer-readable storage medium having stored thereon in digital format, computer-executable instructions that, in response to execution by a computing device, cause the computing device to perform operations for identifying demand by an online community for a particular item, comprising:

compiling a set of N items {X₁, X₂, . . . , X_i, . . . , X_N},

wherein for each item X_i amongst the set of N items, a plurality of M late adopter members {Y[X_i]₁ . . . Y[X_i]_M} is determined resulting in N separate sets of M late adopter members, said M late adopter members being determined based on a time of adoption of said item X_i;

determining a set K of the late adopter members that occur least frequently in the set {Y[X_i]_j} from N separate sets of M late adopter members, where 1≦

i≦

N and 1≦

j≦

M,

wherein said least frequently occurring late adopter members are classified as trend laggers;

introducing the particular item for adoption by the K late adopter members;

measuring an acceptance value for the particular item by the K late adopter members of the online community; and

generating a demand score identifying a predicted overall demand remaining for the particular item.

22. A computer-readable storage medium having stored thereon, computer-executable instructions that, if executed by a computing device, cause the computing device to perform a method comprising:

identifying a first item having an adoption rate above a first predetermined level;

calculating a score reflecting the percentage of times the first item and one or more second items which have an adoption rate below a second predetermined level are presented together;

identifying at least one second item which has an upper-half score relative to the first item, and has a lower-half score relative to others of the one or more second items; and

repeating the calculating and the identifying to identify a first set of first items that each have adoption rates above the first predetermined level, and a second set of second items that have the correlation score relative to the first set of first items above a third predetermined level.

23. A demand identification system for identifying demand by an online community for a particular item, comprising:

means for compiling a set of N items {X₁, X₂, . . . , X_i, . . . , X_N},

wherein for each item X_i amongst the set of N items, a plurality of M adopter members {Y[X_i]₁ . . . Y[X_i]_M} is determined resulting in N separate sets of M adopter members, said M adopter members being determined based on a time of adoption of said item X_i;

means for determining a set K₁ of the adopter members that occur most frequently and a set K₂ of the adopter members that occur least frequently in the set {Y[X_i]_j} from N separate sets of M adopter members, where 1≦

i≦

N and 1≦

j≦

M,

wherein said most frequently occurring adopter members are classified as early adopter members and least frequently occurring adopter members are classified as late adopter members;

means for introducing the particular item for adoption by the K₁ early adopter members and that K₂ late adopter members;

means for measuring an acceptance value for the particular item by the K₁ early adopter members and the K₂ late adopter members of the online community; and

means for generating a demand score identifying a predicted overall demand remaining for the particular item.

24. A potential demand identification system for at least one of a new product and a new service, comprising:

means for identifying one or more products and/or services which are characterized as being in demand by a majority of an electronic community;

means for identifying early adopters of the one or more products and/or services within an electronic community,

wherein the early adopters are characterized by a ranking of their time of adoption for an item that is among the first in the online community and the item is later adopted by other members of the online community; and

means for monitoring the activities of the early adopter members during a plurality of electronic data collection sessions, to determine a score for their collective impressions of the new product or new service.

25. A system, comprising:

a communications network;

a plurality of customer network devices;

a plurality of software components; and

a plurality of electronic databases;

wherein the plurality of customer network devices is coupled to the plurality of software components and electronic databases by way of the communications network, and

wherein a demand identification system for identifying demand by an online community for a particular item is implemented by;

compiling a set of N items {X₁, X₂, . . . , X_i, . . . , X_N},

wherein for each item X_i amongst the set of N items, a plurality of M adopter members {Y[X_i]₁ . . . Y[X_i]_M} is determined resulting in N separate sets of M adopter members, said M adopter members being determined based on a time of adoption of said item X_i;

determining set K₁ of the adopter members that occur most frequently and to determine a set K₂ of the adopter members that occur least frequently in the set {Y[X_i]_j} from N separate sets of M adopter members, where 1≦

i≦

N and 1≦

j≦

M,

wherein said most frequently occurring adopter members are classified as early adopter members and least frequently occurring adopter members are classified as late adopter members;

introducing the particular item for adoption by the K₁ early adopter members and that K₂ late adopter members;

measuring, by use of one or more of the plurality of software components, an acceptance value for the particular item by the K₁ early adopter members and the K₂ late adopter members of the online community; and

generating, by use of one or more of the plurality of software components, a demand score identifying a predicted overall demand remaining for the particular item.