Systems, methods, and devices for identifying and presenting identifications of significant attributes of unique items

• US 9,690,857 B1
• Filed: 08/31/2016
• Issued: 06/27/2017
• Est. Priority Date: 03/07/2013
• Status: Active Grant

• Current Assignee: Vast.com, Inc. (Vroom, Inc.)
• Original Assignee: Vast.com, Inc. (Vroom, Inc.)
• Inventors: Franke, David Wayne, Wilbur, Thomas Wyatt
• Primary Examiner(s): Miller, Alan S
• Application Number:
  US15/253,007
• Time in Patent Office: 300 Days
• Field of Search: 705 711- 742
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0206 Price or cost determination based on market factors
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy

Abstract

The disclosure herein provides systems, methods, and devices for identifying and presenting identifications of significant attributes of unique items. A significant attributes system for identifying and presenting identifications of significant attributes of unique items comprises an item analysis engine, at least one driver models database, and a model building engine, wherein the item analysis engine comprises an item description receiver and one or more driver calculators.

Claims

1. A system for monitoring electronic interactions with unique items and identifying and analyzing significant attributes of the unique items, the system comprising:

one or more computer readable storage devices configured to store a plurality of computer executable instructions; and

one or more hardware computer processors in communication with the one or more computer readable storage devices and configured to execute the plurality of computer executable instructions in order to cause the system to;

electronically monitor, over a computer network, user interactions with unique items displayed by user interfaces of a plurality of user devices,

wherein the electronic monitoring comprises detecting a position of a unique item displayed by a user interface at a time of the user interaction;

generate user activity data based at least partially on the electronic monitoring of user interactions;

apply one or more model specifications to the user activity data to generate one or more driver models, the one or more driver models configured to enable identification of which of a plurality of attributes of a selected unique item are driver attributes and to enable determination of values associated with the driver attributes, the plurality of attributes comprising at least a condition attribute and a feature attribute,

wherein the applying one or more model specifications comprises using detected positions to reduce any position bias present in the user activity data, and

wherein the applying one or more model specifications comprises using one or more of the following methods;

linear regression, non-linear regression, model trees, nearest neighbor analysis;

receive selected item data, the selected item data being related to the plurality of attributes of the selected unique item; and

apply one or more of the generated driver models to the selected item data to identify which of the plurality of attributes of the selected unique item are driver attributes and to determine values associated with the driver attributes.

2. The system of claim 1, wherein the selected unique item comprises one of the following types of items:

used automobiles, existing homes, real estate, household goods, customized electronics, customized goods.

3. The system of claim 1, wherein the one or more driver models comprises at least one price driver model and at least one demand driver model, the at least one price driver model configured to enable identification of which of the plurality of attributes of the selected unique item are price driver attributes, the at least one demand driver model configured to enable identification of which of the plurality of attributes of the selected unique item are demand driver attributes.

4. The system of claim 1, wherein the determined values associated with the driver attributes of the selected unique item describe at least one of the following:

an estimated price contribution of a driver attribute to an overall price of the selected unique item, a perceived value of a driver attribute, a level of desirability of a driver attribute.

5. The system of claim 1, wherein the one or more hardware computer processors are further configured to execute the plurality of computer executable instructions in order to cause the system to:

electronically present the identification of which of the plurality of attributes of the selected unique item are driver attributes.

6. The system of claim 1, wherein the one or more hardware computer processors are further configured to execute the plurality of computer executable instructions in order to cause the system to:

electronically present one or more determined values associated with the driver attributes.

7. The system of claim 1, wherein the electronically monitored user interactions comprises at least one of the following:

a number of clicks on a hyperlink related to a specific unique item, a number of views of a webpage comprising information related to a specific unique item, a position of a specific unique item in a list of a plurality of specific unique items when a user interacts with the specific unique item, an amount of time a user spends viewing a webpage comprising information related to a specific unique item, a purchase by a user of a specific unique item, information submitted by a user to an advertiser relating to a specific unique item.

8. A computer-implemented method for monitoring electronic interactions with unique items and identifying and analyzing significant attributes of the unique items, the computer-implemented method comprising:

electronically monitoring, by a computer system, over a computer network, user interactions with unique items displayed by user interfaces of a plurality of user devices,

wherein the electronic monitoring comprises detecting a position of a unique item displayed by a user interface at a time of the user interaction;

generating, using the computer system, user activity data based at least partially on the electronic monitoring of user interactions;

applying, using the computer system, one or more model specifications to the user activity data to generate one or more driver models, the one or more driver models configured to enable identification of which of a plurality of attributes of a selected unique item are driver attributes and to enable determination of values associated with the driver attributes, the plurality of attributes comprising at least a condition attribute and a feature attribute,

wherein the applying one or more model specifications comprises using detected positions to reduce any position bias present in the user activity data, and

wherein the applying one or more model specifications comprises using one or more of the following methods;

linear regression, non-linear regression, model trees, nearest neighbor analysis;

receiving, using the computer system, selected item data, the selected item data being related to the plurality of attributes of the selected unique item; and

applying, using the computer system, one or more of the generated driver models to the selected item data to identify which of the plurality of attributes of the selected unique item are driver attributes and to determine values associated with the driver attributes,

wherein the computer system comprises a computer processor and electronic memory.

9. The computer-implemented method of claim 8, wherein the selected unique item comprises one of the following types of items:

used automobiles, existing homes, real estate, household goods, customized electronics, customized goods.

10. The computer-implemented method of claim 8, wherein the one or more driver models comprises at least one price driver model and at least one demand driver model, the at least one price driver model configured to enable identification of which of the plurality of attributes of the selected unique item are price driver attributes, the at least one demand driver model configured to enable identification of which of the plurality of attributes of the selected unique item are demand driver attributes.

11. The computer-implemented method of claim 8, wherein the determined values associated with the driver attributes of the selected unique item describe at least one of the following:

an estimated price contribution of a driver attribute to an overall price of the selected unique item, a perceived value of a driver attribute, a level of desirability of a driver attribute.

12. The computer-implemented method of claim 8, further comprising:

electronically presenting the identification of which of the plurality of attributes of the selected unique item are driver attributes.

13. The computer-implemented method of claim 8, further comprising:

electronically presenting one or more determined values associated with the driver attributes.

14. The computer-implemented method of claim 8, wherein the electronically monitored user interactions comprises at least one of the following:

a number of clicks on a hyperlink related to a specific unique item, a number of views of a webpage comprising information related to a specific unique item, a position of a specific unique item in a list of a plurality of specific unique items when a user interacts with the specific unique item, an amount of time a user spends viewing a webpage comprising information related to a specific unique item, a purchase by a user of a specific unique item, information submitted by a user to an advertiser relating to a specific unique item.

15. A computer readable, non-transitory storage medium having a computer program stored thereon for causing a suitably programmed computer system to process by one or more processors computer-program code by performing a method for monitoring electronic interactions with unique items and identifying and analyzing significant attributes of the unique items when the computer program is executed on the suitably programmed computer system, the method comprising:

electronically monitoring, by a computer system, over a computer network, user interactions with unique items displayed by user interfaces of a plurality of user devices,

wherein the electronic monitoring comprises detecting a position of a unique item displayed by a user interface at a time of the user interaction;

generating, using the computer system, user activity data based at least partially on the electronic monitoring of user interactions;

applying, using the computer system, one or more model specifications to the user activity data to generate one or more driver models, the one or more driver models configured to enable identification of which of a plurality of attributes of a selected unique item are driver attributes and to enable determination of values associated with the driver attributes, the plurality of attributes comprising at least a condition attribute and a feature attribute,

wherein the applying one or more model specifications comprises using detected positions to reduce any position bias present in the user activity data, and

wherein the applying one or more model specifications comprises using one or more of the following methods;

linear regression, non-linear regression, model trees, nearest neighbor analysis;

receiving, using the computer system, selected item data, the selected item data being related to the plurality of attributes of the selected unique item; and

applying, using the computer system, one or more of the generated driver models to the selected item data to identify which of the plurality of attributes of the selected unique item are driver attributes and to determine values associated with the driver attributes,

wherein the computer system comprises a computer processor and electronic memory.

16. The computer readable, non-transitory storage medium of claim 15, wherein the selected unique item comprises one of the following types of items:

used automobiles, existing homes, real estate, household goods, customized electronics, customized goods.

17. The computer readable, non-transitory storage medium of claim 15, wherein the one or more driver models comprises at least one price driver model and at least one demand driver model, the at least one price driver model configured to enable identification of which of the plurality of attributes of the selected unique item are price driver attributes, the at least one demand driver model configured to enable identification of which of the plurality of attributes of the selected unique item are demand driver attributes.

18. The computer readable, non-transitory storage medium of claim 15, wherein the determined values associated with the driver attributes of the selected unique item describe at least one of the following:

an estimated price contribution of a driver attribute to an overall price of the selected unique item, a perceived value of a driver attribute, a level of desirability of a driver attribute.

19. The computer readable, non-transitory storage medium of claim 15, the method further comprising:

electronically presenting the identification of which of the plurality of attributes of the selected unique item are driver attributes.

20. The computer readable, non-transitory storage medium of claim 15, the method further comprising:

electronically presenting one or more determined values associated with the driver attributes.