System and method for classifying relevant competitors

• US 10,504,127 B2
• Filed: 03/15/2013
• Issued: 12/10/2019
• Est. Priority Date: 11/15/2012
• Status: Active Grant

• Current Assignee: Home Depot Product Authority, LLC (The Home Depot, Inc.)
• Original Assignee: Home Depot Product Authority, LLC (The Home Depot, Inc.)
• Inventors: Carvalho, Rodrigo Pierzchalski
• Primary Examiner(s): Gart, Matthew S
• Assistant Examiner(s): Obaid, Hamzeh M
• Application Number:
  US13/841,487
• Publication Number:
  US 20140136285A1
• Time in Patent Office: 2,461 Days
• CPC Class Codes: G06Q 30/0204 Market segmentation

Abstract

Competitors are classified in terms of products the competitors offer. A product set is generated from product information received from a user. Also, a competitor set is generated, where the competitor set comprises at least one competitor determined to be relevant to one or more products in the product set. A target price rule is generated that is operative to change a price offered by the user for the at least one product. A competitors relevancy can be determined by considering factors such as: (1) unique visitors to the competitor'"'"'s website, (2) reviews on the competitor'"'"'s website (3), ratings on the competitor'"'"'s website, (4) absolute number of products common to the user'"'"'s website and the competitor'"'"'s website, (5) percentage number of products common to the user'"'"'s website and the competitor'"'"'s website, and (6) number of products offered by the competitor that comprise the product set.

Claims

1. A system for classifying competitors of a user of the system, the system comprising:

a website crawler that runs on a processor, the website crawler operable to obtain raw data from a plurality of Internet domains associated with a plurality of potential competitors'"'"' websites, wherein one or more wrappers is applied to the raw data to extract competitor product information from the raw data;

a competitor classifier that runs on the processor, the competitor classifier operable to;

determine respective relevancy scores of a plurality of potential competitors to at least one product in a product set by assigning a value to a first variable, the first variable comprising at least one of;

an absolute number of products common to the user'"'"'s website and the potential competitor'"'"'s web site, or

a percentage of products common to the user'"'"'s web site and the potential competitor'"'"'s website,

wherein the absolute number or the percentage is determined at least in part based on the competitor product information extracted from the raw data;

the competitor classifier operable to determine the respective relevancy scores further by assigning a value to a second variable, the second variable comprising at least one of;

unique visitors to the potential competitor'"'"'s website;

reviews on the potential competitor'"'"'s website;

ratings on the potential competitor'"'"'s web site;

or

number of products offered by the potential competitor that comprise the product set;

determine, for each potential competitor, if the computed relevancy score is greater than a threshold value; and

add each competitor having a computed relevancy score greater than the threshold value to a competitor set;

a user interface coupled to the competitor classifier, the processor operable to cause the user interface to display product set information and competitor set information to a user;

wherein the product set information comprises, for the at least one product in the set, at least one of;

product SKU;

product category;

or

product brand;

and the competitor set information comprises, for each competitor in the competitor set, the first variable and the second variable.

2. The system of claim 1, wherein the respective values assigned to the first variable and the second variable are weighted.

3. The system of claim 2, wherein the respective values assigned to the first and second variables are weighted differently.

4. The system of claim 3, wherein the competitor classifier is further operable to:

find the sum of the weighted values; and

compare the sum to the threshold.

5. The system of claim 1, wherein the competitor classifier is further operable to:

identify if a potential competitor having a computed relevancy score greater than the threshold value is associated with a disqualifying variable; and

exclude the competitor associated with the disqualifying variable from the competitor set.

21. The system of claim 1, wherein the plurality of potential competitors are discovered from an unbounded number of Internet domains.

22. The system of claim 5, wherein the competitor classifier is further operable to:

identify if a potential competitor having a computed relevancy score greater than the threshold value is associated with a disqualifying variable by comparing a value of a third variable with a disqualifying threshold; and

determine that the potential competitor is associated with a disqualifying variable when the value of the third variable is below the disqualifying threshold;

the third variable comprising at least one of;

an absolute number of products common to the user'"'"'s website and the potential competitor'"'"'s website,

a percentage of products common to the user'"'"'s website and the potential competitor'"'"'s website;

a number of unique visitors to the potential competitor'"'"'s website in a period of time;

reviews on the potential competitor'"'"'s website;

ratings on the potential competitor'"'"'s web site;

or

a number of products offered by the potential competitor that comprise the product set.

29. The system of claim 1, wherein at least one of the unique visitors to the potential competitor'"'"'s website, the reviews on the potential competitor'"'"'s website, the ratings on the potential competitor'"'"'s website, or the number of products offered by the potential competitor is determined at least in part based on the competitor product information extracted from the raw data.

6. A method for classifying competitors, the method comprising:

obtaining, by a website crawler run on a processor, raw data from a plurality of Internet domains associated with a plurality of potential competitors'"'"' websites;

applying, by the processor, one or more wrappers to the raw data to extract competitor product information from the raw data;

using the processor, determining respective relevancy scores of a plurality of potential competitors to at least one product in a product set by;

assigning a value to a first variable, the first variable comprising at least one of;

an absolute number of products common to the user'"'"'s website and the potential competitor'"'"'s website, or

a percentage of products common to the user'"'"'s website and the potential competitor'"'"'s website,

wherein the absolute number or the percentage is determined at least in part based on the competitor product information extracted from the raw data; and

assigning a value to a second variable, the second variable comprising at least one of;

unique visitors to the potential competitor'"'"'s website;

reviews on the potential competitor'"'"'s website;

ratings on the potential competitor'"'"'s web site;

or

number of products offered by the potential competitor that comprise the product set;

determining, by the processor, for each potential competitor, if the computed relevancy score is greater than a threshold value; and

adding, by the processor, each competitor having a computed relevancy score greater than the threshold value to a competitor set;

using the processor, displaying product set information and competitor set information to a user, wherein the product set information comprises, for the at least one product in the set, at least one of;

product SKU;

product category; and

product brand;

and the competitor set information comprises, for each competitor in the competitor set, the first variable and the second variable.

7. The method of claim 6, wherein the respective values assigned to the first variable and the second variable are weighted.

8. The method of claim 7, wherein the respective values assigned to the first and second variables are weighted differently.

9. The method of claim 8, wherein computing a relevancy score further comprises:

finding the sum of the weighted values; and

comparing the sum to the threshold.

10. The method of claim 6, further comprising:

identifying if a potential competitor having a computed relevancy score greater than the threshold value is associated with a disqualifying variable; and

excluding the potential competitor associated with the disqualifying variable from the competitor set.

23. The method of claim 6, further comprising discovering the plurality of potential competitors from an unbounded number of Internet domains.

24. The method of claim 10, wherein identifying if a potential competitor having a computed relevancy score greater than the threshold value is associated with a disqualifying variable comprises:

comparing a value of a third variable with a disqualifying threshold; and

determining that the potential competitor is associated with a disqualifying variable when the value of the third variable is below the disqualifying threshold;

the third variable comprising at least one of;

an absolute number of products common to the user'"'"'s website and the potential competitor'"'"'s website,

a percentage of products common to the user'"'"'s website and the potential competitor'"'"'s website;

a number of unique visitors to the potential competitor'"'"'s website in a period of time;

reviews on the potential competitor'"'"'s website;

ratings on the potential competitor'"'"'s web site;

or

a number of products offered by the potential competitor that comprise the product set.

11. An apparatus for classifying competitors, the apparatus comprising:

a memory; and

a processor coupled to the memory, the processor operable to;

generate a product set from product information received from a user;

generate a competitor set, the competitor set comprising at least one competitor determined to be relevant to at least one product in the product set, the processor operable to generate the competitor set by determining respective relevancy scores of a plurality of potential competitors by;

obtaining, by a website crawler run on a processor, raw data from a plurality of Internet domains associated with a plurality of potential competitors'"'"' websites;

applying one or more wrappers to the raw data to extract competitor product information from the raw data;

assigning a value to a first variable, the first variable comprising at least one of;

an absolute number of products common to the user'"'"'s website and the potential competitor'"'"'s website, or

a percentage of products common to the user'"'"'s web site and the potential competitor'"'"'s website,

wherein the absolute number or the percentage is determined at least in part based on the product information extracted from the raw data; and

assigning a value to a second variable, the second variable comprising at least one of;

unique visitors to the potential competitor'"'"'s website;

reviews on the potential competitor'"'"'s web site;

ratings on the potential competitor'"'"'s web site;

or

number of products offered by the potential competitor that comprise the product set;

determining, by a processor, for each potential competitor, if the computed relevancy score is greater than a threshold value; and

adding, by a processor, each competitor having a computed relevancy score greater than the threshold value to a competitor set; and

generate a target price rule for the at least one product, wherein the target price rule is operative to change a price offered by the user for the at least one product.

12. The apparatus of claim 11, wherein the respective values assigned to the first variable and the second variable are weighted.

13. The apparatus of claim 12, wherein the respective values assigned to the first and second variables are weighted differently.

14. The apparatus of claim 13, wherein the processor is further operable to:

find the sum of the weighted values; and

compare the sum to the threshold.

15. The apparatus of claim 11, wherein the processor is further operable to:

identify if a potential competitor having a computed relevancy score greater than the threshold value is associated with a disqualifying variable; and

exclude the potential competitor associated with the disqualifying variable from the competitor set.

25. The apparatus of claim 11, wherein the plurality of potential competitors are discovered from an unbounded number of Internet domains.

26. The apparatus of claim 15, wherein the processor is further operable to:

identify if a potential competitor having a computed relevancy score greater than the threshold value is associated with a disqualifying variable by comparing a value of a third variable with a disqualifying threshold; and

determine that the potential competitor is associated with a disqualifying variable when the value of the third variable is below the disqualifying threshold;

the third variable comprising at least one of;

an absolute number of products common to the user'"'"'s website and the potential competitor'"'"'s website,

a percentage of products common to the user'"'"'s website and the potential competitor'"'"'s website;

a number of unique visitors to the potential competitor'"'"'s website in a period of time;

reviews on the potential competitor'"'"'s website;

ratings on the potential competitor'"'"'s web site;

or

a number of products offered by the potential competitor that comprise the product set.

16. A method for classifying competitors, the method comprising:

using a processor, generating a product set from product information received from a user;

using the processor, generating a competitor set, the competitor set comprising at least one competitor determined to be relevant to at least one product in the product set, by determining respective relevancy scores of a plurality of potential competitors by;

obtaining, by a website crawler run on a processor, raw data from a plurality of Internet domains associated with a plurality of potential competitors'"'"' web sites;

applying, by the processor, one or more wrappers to the raw data to extract competitor product information from the raw data;

assigning a value to a first variable, the first variable comprising at least one of;

an absolute number of products common to the user'"'"'s website and the potential competitor'"'"'s web site, or

a percentage of products common to the user'"'"'s web site and the potential competitor'"'"'s website,

wherein the absolute number or the percentage is determined at least in part based on the product information extracted from the raw data; and

assigning a value to a second variable, the second variable comprising at least one of;

unique visitors to the potential competitor'"'"'s website;

reviews on the potential competitor'"'"'s website;

ratings on the potential competitor'"'"'s web site;

or

number of products offered by the potential competitor that comprise the product set;

determining, by the processor, for each potential competitor, if the computed relevancy score is greater than a threshold value; and

adding, by the processor, each competitor having a computed relevancy score greater than the threshold value to a competitor set; and

using the processor, generating a target price rule for the at least one product, wherein the target price rule is operative to change a price offered by the user for the at least one product.

17. The method of claim 16, wherein the respective values assigned to the first variable and the second variable are weighted.

18. The method of claim 17, wherein the respective values assigned to the first and second variables are weighted differently.

19. The method of claim 18, wherein computing a relevancy score further comprises:

finding the sum of the weighted values; and

comparing the sum to the threshold.

20. The method of claim 16, wherein generating a competitor set further comprises:

identifying if a potential competitor having a computed relevancy score greater than the threshold value is associated with a disqualifying variable; and

excluding the potential competitor associated with the disqualifying variable from the competitor set.

27. The method of claim 16, further comprising discovering the plurality of potential competitors from an unbounded number of Internet domains.

28. The method of claim 20, wherein identifying if a potential competitor having a computed relevancy score greater than the threshold value is associated with a disqualifying variable comprises:

comparing a value of a third variable with a disqualifying threshold; and

determining that the potential competitor is associated with a disqualifying variable when the value of the third variable is below the disqualifying threshold;

the third variable comprising at least one of;

an absolute number of products common to the user'"'"'s website and the potential competitor'"'"'s website,

a percentage of products common to the user'"'"'s website and the potential competitor'"'"'s website;

a number of unique visitors to the potential competitor'"'"'s website in a period of time;

reviews on the potential competitor'"'"'s website;

ratings on the potential competitor'"'"'s web site;

or

a number of products offered by the potential competitor that comprise the product set.