System and method for analysis and presentation of used vehicle pricing data

• US 10,733,639 B2
• Filed: 10/01/2018
• Issued: 08/04/2020
• Est. Priority Date: 07/28/2011
• Status: Active Grant

• Current Assignee: TrueCar, Inc.
• Original Assignee: TrueCar, Inc.
• Inventors: Swinson, Michael D., Laughlin, Isaac Lemon, Ramanuja, Meghashyam Grama, Semeniuk, Mikhail, Liu, Xingchu
• Primary Examiner(s): Yesildag, Mehmet
• Application Number:
  US16/148,695
• Publication Number:
  US 20190034983A1
• Time in Patent Office: 673 Days
• Field of Search: None
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0206 Price or cost determination based on market factors
• CPC Class Codes: G06Q 30/0278 Product appraisal

Abstract

To increase the efficiency of a used vehicle data processing process while still tailoring to an individual user'"'"'s unique specifications on a used vehicle, at least some pre-calculations are performed by a backend process before a request for data for a specified vehicle is received through a web site or a web server on the Internet. A user can be presented with an interface where the user can make a variety of determinations. After the user requests data on a specific vehicle configuration, a frontend process handles user-provided data in conjunction with the data calculated in the backend process to ensure that the results are better tailored to the user'"'"'s specific vehicle attributes. The results can include pricing data such as a trade-in price, a list price, an expected sale price or range of sale prices, market low sale price, market average sale price, market high sale price, etc.

Claims

1. A computer-implemented method of used vehicle data processing, the method comprising:

receiving, from disparate data sources over a network by a backend process as inputs, vehicle trim data on vehicles over a past time period, vehicle manufacturer data on the vehicles when new, depreciation data on the vehicles or similar vehicle models, and vehicle transaction data on the vehicles, the backend process executing on a processor of a vehicle data system, the vehicle data system having a server computer that provides a web site or web service on Internet;

computing, by the backend process, current retail values of the vehicles using a linear function, the computing comprising generating estimates for parameters of the linear function;

determining, by the backend process, residual values of the vehicles utilizing the current retail values of the vehicles and the vehicle transaction data on the vehicles;

appending, by the backend process, a used vehicle research dataset with the residual values of the vehicles;

updating, by the backend process, the estimates for the parameters of the linear function at a time interval;

receiving, by the server computer through the web site or web service on the Internet, user input data comprising a zip code and vehicle year, make, model, trim, condition, and mileage of a used vehicle;

responsive to the user input data, constructing, by a frontend process based on the user input data, sets of regression variables including a set of regression variables constructed based on vehicle attributes of the used vehicle, a set of regression variables constructed based on the condition and mileage of the used vehicle, and a set of regression variables constructed based on the zip code, the frontend process operated by the vehicle data system;

determining, by the frontend process using the zip code and the vehicle year, make, and model of the used vehicle, a set of vehicles in a bin from the used vehicle research dataset, wherein each vehicle of the set of vehicles in the bin has same vehicle year, make, and model as the used vehicle and wherein each vehicle of the set of vehicles in the bin is in a geographic region inclusive of the zip code of the used vehicle;

determining, by the frontend process using residual values of the set of vehicles in the bin from the used vehicle research dataset, an average price for the used vehicle;

determining, by the frontend process using the sets of regression variables constructed by the frontend process and the estimates for the parameters updated by the backend process, a depreciated value of the used vehicle;

determining, by the frontend process using the average price for the used vehicle and the depreciated value of the used vehicle, an expected price of the used vehicle in the zip code; and

presenting the expected price of the used vehicle in the zip code on a user device over the Internet.

2. The computer-implemented method according to claim 1, wherein the presenting comprises presenting the expected price of the used vehicle in the zip code within a range of prices.

3. The computer-implemented method according to claim 1, wherein the expected price of the used vehicle in the zip code is associated with a number of average days to sale such that the expected price of the used vehicle in the zip code and the number of average days to sale are interdependent.

4. The computer-implemented method according to claim 3, further comprising:

presenting a user interface element on the user device for adjusting the number of average days to sale.

5. The computer-implemented method according to claim 4, further comprising:

receiving, by the frontend process from the user device, an adjustment to the number of average days to sale through the user interface element; and

in response to the adjustment to the number of average days to sale, adjusting, by the frontend process, the expected price of the used vehicle in the zip code presented on the user device.

6. The computer-implemented method according to claim 1, wherein the expected price of the used vehicle in the zip code determined by the frontend process comprises a listing price of the used vehicle in the zip code, a sale price of the used vehicle in the zip code, or a trade-in price of the used vehicle in the zip code.

7. The computer-implemented method according to claim 1, further comprising:

prior to determining the bin containing the set of vehicles from the used vehicle research dataset, determining, by the backend process, whether sufficient transactions for the vehicle year, make, model of the used vehicle within a distance of the zip code exist in the used vehicle research dataset; and

responsive to insufficient transactions for the vehicle year, make, model of the used vehicle within the distance of the zip code in the used vehicle research dataset, performing, by the backend process, a clustering process to include in the bin additional historical transactions involving vehicle models in the used vehicle research dataset that are most similar to the used vehicle in the zip code.

8. A vehicle data system for used vehicle data processing, the vehicle data system comprising:

a server computer that provides a web site or web service on Internet, the server computer having a processor and a non-transitory computer-readable medium storing instructions translatable by the processor for;

operating a backend process, comprising;

receiving, from disparate data sources over a network as inputs, vehicle trim data on vehicles over a past time period, vehicle manufacturer data on the vehicles when new, depreciation data on the vehicles or similar vehicle models, and vehicle transaction data on the vehicles;

computing current retail values of the vehicles using a linear function, the computing comprising generating estimates for parameters of the linear function;

determining residual values of the vehicles utilizing the current retail values of the vehicles and the vehicle transaction data on the vehicles;

appending a used vehicle research dataset with the residual values of the vehicles; and

updating the estimates for the parameters of the linear function at a time interval;

receiving, through the web site or web service on the Internet, user input data comprising a zip code and vehicle year, make, model, trim, condition, and mileage of a used vehicle; and

operating a frontend process comprising;

responsive to the user input data, constructing, based on the user input data, sets of regression variables including a set of regression variables constructed based on vehicle attributes of the used vehicle, a set of regression variables constructed based on the condition and mileage of the used vehicle, and a set of regression variables constructed based on the zip code, the frontend process operated by the vehicle data system;

determining, using the zip code and the vehicle year, make, and model of the used vehicle, a set of vehicles in a bin from the used vehicle research dataset, wherein each vehicle of the set of vehicles in the bin has same vehicle year, make, and model as the used vehicle and wherein each vehicle of the set of vehicles in the bin is in a geographic region inclusive of the zip code of the used vehicle;

determining, using residual values of the set of vehicles in the bin from the used vehicle research dataset, an average price for the used vehicle;

determining, using the sets of regression variables constructed by the frontend process and the estimates for the parameters updated by the backend process, a depreciated value of the used vehicle;

determining, using the average price for the used vehicle and the depreciated value of the used vehicle, an expected price of the used vehicle in the zip code; and

presenting the expected price of the used vehicle in the zip code on a user device over the Internet.

9. The vehicle data system of claim 8, wherein the presenting comprises presenting the expected price of the used vehicle in the zip code within a range of prices.

10. The vehicle data system of claim 8, wherein the expected price of the used vehicle in the zip code is associated with a number of average days to sale such that the expected price of the used vehicle in the zip code and the number of average days to sale are interdependent.

11. The vehicle data system of claim 8, wherein the frontend process further comprises:

presenting a user interface element on the user device for adjusting the number of average days to sale.

12. The vehicle data system of claim 11, wherein the frontend process further comprises:

receiving, from the user device, an adjustment to the number of average days to sale through the user interface element; and

in response to the adjustment to the number of average days to sale, adjusting the expected price of the used vehicle in the zip code presented on the user device.

13. The vehicle data system of claim 8, wherein the expected price of the used vehicle in the zip code determined by the frontend process comprises a listing price of the used vehicle in the zip code, a sale price of the used vehicle in the zip code, or a trade-in price of the used vehicle in the zip code.

14. The vehicle data system of claim 8, wherein the backend process further comprises:

prior to determining the bin containing the set of vehicles from the used vehicle research dataset, determining whether sufficient transactions for the vehicle year, make, model of the used vehicle within a distance of the zip code exist in the used vehicle research dataset; and

responsive to insufficient transactions for the vehicle year, make, model of the used vehicle within the distance of the zip code in the used vehicle research dataset, performing a clustering process to include in the bin additional historical transactions involving vehicle models in the used vehicle research dataset that are most similar to the used vehicle in the zip code.

15. A computer program product for used vehicle data processing, the computer program product comprising a non-transitory computer-readable medium storing instructions translatable by a server computer that provides a web site or web service on Internet, the instructions when translated by the server computer perform:

operating a backend process, comprising;

receiving, from disparate data sources over a network as inputs, vehicle trim data on vehicles over a past time period, vehicle manufacturer data on the vehicles when new, depreciation data on the vehicles or similar vehicle models, and vehicle transaction data on the vehicles;

computing current retail values of the vehicles using a linear function, the computing comprising generating estimates for parameters of the linear function;

determining residual values of the vehicles utilizing the current retail values of the vehicles and the vehicle transaction data on the vehicles;

appending a used vehicle research dataset with the residual values of the vehicles; and

updating the estimates for the parameters of the linear function at a time interval;

receiving, through the web site or web service on the Internet, user input data comprising a zip code and vehicle year, make, model, trim, condition, and mileage of a used vehicle; and

operating a frontend process comprising;

responsive to the user input data, constructing, based on the user input data, sets of regression variables including a set of regression variables constructed based on vehicle attributes of the used vehicle, a set of regression variables constructed based on the condition and mileage of the used vehicle, and a set of regression variables constructed based on the zip code, the frontend process operated by the vehicle data system;

determining, using the zip code and the vehicle year, make, and model of the used vehicle, a set of vehicles in a bin from the used vehicle research dataset, wherein each vehicle of the set of vehicles in the bin has same vehicle year, make, and model as the used vehicle and wherein each vehicle of the set of vehicles in the bin is in a geographic region inclusive of the zip code of the used vehicle;

determining, using residual values of the set of vehicles in the bin from the used vehicle research dataset, an average price for the used vehicle;

determining, using the sets of regression variables constructed by the frontend process and the estimates for the parameters updated by the backend process, a depreciated value of the used vehicle;

determining, using the average price for the used vehicle and the depreciated value of the used vehicle, an expected price of the used vehicle in the zip code; and

presenting the expected price of the used vehicle in the zip code on a user device over the Internet.

16. The computer program product of claim 15, wherein the presenting comprises presenting the expected price of the used vehicle in the zip code within a range of prices.

17. The computer program product of claim 15, wherein the expected price of the used vehicle in the zip code is associated with a number of average days to sale such that the expected price of the used vehicle in the zip code and the number of average days to sale are interdependent.

18. The computer program product of claim 15, wherein the frontend process further comprises:

presenting a user interface element on the user device for adjusting the number of average days to sale.

19. The computer program product of claim 18, wherein the frontend process further comprises:

receiving, from the user device, an adjustment to the number of average days to sale through the user interface element; and

in response to the adjustment to the number of average days to sale, adjusting the expected price of the used vehicle in the zip code presented on the user device.

20. The computer program product of claim 15, wherein the backend process further comprises:

prior to determining the bin containing the set of vehicles from the used vehicle research dataset, determining whether sufficient transactions for the vehicle year, make, model of the used vehicle within a distance of the zip code exist in the used vehicle research dataset; and

responsive to insufficient transactions for the vehicle year, make, model of the used vehicle within the distance of the zip code in the used vehicle research dataset, performing a clustering process to include in the bin additional historical transactions involving vehicle models in the used vehicle research dataset that are most similar to the used vehicle in the zip code.