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

• US 9,465,873 B1
• Filed: 06/21/2013
• Issued: 10/11/2016
• Est. Priority Date: 03/07/2013
• Status: Active Grant

• Current Assignee: Vast.com, Inc. (Vroom, Inc.)
• Original Assignee: Vast.com, Inc. (Vroom, Inc.)
• Inventors: Wilbur, Thomas Wyatt, Franke, David Wayne
• Primary Examiner(s): Miller, Alan S
• Application Number:
  US13/924,375
• Time in Patent Office: 1,208 Days
• Field of Search: 705 711- 742
• US Class Current: 1/1
• 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 significant attributes system for identifying and presenting identifications of significant attributes of unique items, the significant attributes system comprising:

an item analysis engine configured to determine which of a plurality of attributes of a selected unique item are driver attributes, the plurality of attributes comprising at least a condition attribute and a feature attribute, the item analysis engine comprising;

an item description receiver configured to electronically receive item data, the item data being related to the plurality of attributes of the selected unique item; and

one or more driver calculators configured to apply one or more driver models to the plurality of attributes to identify which of the plurality of attributes of the selected unique item are driver attributes;

wherein the item analysis engine is configured to electronically present the identification of which of the plurality of attributes of the selected unique item are driver attributes;

at least one driver models database configured to electronically store information relating to the one or more driver models and to electronically communicate with the item analysis engine;

a model building engine configured to generate the one or more driver models by applying one or more model specifications to data relating to user activity,

wherein the one or more model specifications comprise instructions to generate a driver model using one or more of the following methods;

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

wherein the data relating to user activity comprises logged interactions of users with a plurality of unique items;

a data collection engine configured to generate the data relating to user activity by electronically monitoring, over a computer network, user interactions with items displayed by user interfaces of a plurality of user devices,

wherein the electronic monitoring comprises detecting a position of an item displayed by the user interface at a time of the user interaction, and the model building engine is further configured to use the detected positions to reduce any position bias present in the logged interactions of users; and

one or more computers configured to operate the item analysis engine, wherein the one or more computers comprises a computer processor and an electronic storage medium.

2. The significant attributes system of claim 1, further comprising an item attributes database configured to store attribute data relating to attributes of a plurality of selectable items and to associate each of the plurality of selectable items with a unique identifier;

wherein the item data comprises a unique identifier of the selected unique item, the unique identifier of the selected unique item configured to enable the item attributes receiver to retrieve attribute data from the items attribute database.

3. The significant attributes 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 significant attributes system of claim 1, wherein the one or more driver calculators are further configured to identify a relative significance of each of the driver attributes.

5. The significant attributes system of claim 4, wherein the relative significance describes at least one of the following:

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

6. The significant attributes system of claim 1, wherein the item analysis engine is further configured to electronically present an identification of which of the plurality of attributes of the selected item are not driver attributes.

7. The significant attributes system of claim 1, wherein the logged 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. The significant attributes system of claim 1, wherein the significant attributes system is configured to generate user interface data and transmit the user interface data to a user access point system configured to use the user interface data to display a user interface containing information for the selected unique item, wherein the user interface data comprises data for one or more of the determined driver attributes and a popularity indication for at least one of the determined driver attributes, wherein the user interface displayed by the user access point system comprises a popular feature indicator based on the popularity indication, and wherein the popular feature indicator comprises a star.

9. A computer-implemented method for identifying and presenting identifications of significant attributes of unique items, the computer-implemented method comprising:

logging, using a computer system, interactions of users with a plurality of unique items, wherein the logging comprises electronically monitoring, over a computer network, actions of the users interacting with user interfaces generated by one or more item listing systems presenting for sale the plurality of unique items,

wherein the electronic monitoring comprises detecting positions of items displayed by the user interfaces at a time of the user interactions;

generating, using the computer system, one or more driver models by applying one or more model specifications to data relating to the logged interactions of the users with the plurality of unique items,

wherein the one or more model specifications comprise instructions to generate a driver model using one or more of the following methods;

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

wherein generating the one or more driver models comprises using the detected positions to reduce any position bias present in the logged interactions of users;

storing the one or more driver models in an electronic driver models database;

receiving, using the computer system, electronic item data relating to a plurality of attributes of a selected unique item;

applying, using the computer system, the one or more driver models stored in the electronic driver models database to the plurality of attributes of the selected unique item to identify which of the plurality of attributes of the selected unique item are driver attributes; and

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

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

10. The computer-implemented method of claim 9, wherein the logging interactions of users with the plurality of unique items is performed substantially in real time.

11. The computer-implemented method of claim 9, wherein the one or more item listing systems comprises a plurality of item listing systems.

12. The computer-implemented method of claim 9, wherein the electronic item data comprises a unique identifier, and the computer-implemented method further comprises:

accessing, using the unique identifier, stored data relating to the plurality of attributes of the selected unique item, the stored data being stored in an item attributes database.

13. The computer-implemented method of claim 9, 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.

14. The computer-implemented method of claim 9, wherein the actions of the users interacting with the one or more computer systems 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 identifying and presenting identifications of significant attributes of unique items when the computer program is executed on the suitably programmed computer system, the method comprising:

logging, using a computer system, interactions of users with a plurality of unique items, wherein the logging comprises electronically monitoring, over a computer network, actions of the users interacting with user interfaces generated by one or more item listing systems presenting for sale the plurality of unique items,

wherein the electronic monitoring comprises detecting positions of items displayed by the user interfaces at a time of the user interactions;

generating, using the computer system, one or more driver models by applying one or more model specifications to data relating to the logged interactions of the users with the plurality of unique items,

wherein the one or more model specifications comprise instructions to generate a driver model using one or more of the following methods;

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

wherein generating the one or more driver models comprises using the detected positions to reduce any position bias present in the logged interactions of users;

storing the one or more driver models in an electronic driver models database;

receiving, using the computer system, electronic item data relating to a plurality of attributes of a selected unique item;

applying, using the computer system, the one or more driver models stored in the electronic driver models database to the plurality of attributes of the selected unique item to identify which of the plurality of attributes of the selected unique item are driver attributes; and

presenting electronically the identification of which of the plurality of attributes of the selected unique item are 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 and plurality of unique items comprise one of the following types of items:

used automobiles, existing homes, real estate.

17. The computer readable, non-transitory storage medium of claim 15, wherein the electronic item data comprises the plurality of attributes of the selected unique item.

18. The computer readable, non-transitory storage medium of claim 15, wherein the electronic item data comprises a unique identifier, and the computer-implemented method further comprises:

accessing, using the unique identifier, stored data relating to the plurality of attributes of the selected unique item, the stored data being stored in an item attributes database.

19. 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.

20. The computer readable, non-transitory storage medium of claim 15,

further comprising identifying a relative significance of each of the driver attributes.