System, method and computer program for forecasting residual values of a durable good over time

• US 9,607,310 B2
• Filed: 08/14/2013
• Issued: 03/28/2017
• Est. Priority Date: 08/15/2012
• Status: Active Grant

• Current Assignee: J.D. Power
• Original Assignee: ALG, Inc. (TrueCar, Inc.)
• Inventors: Strauss, Oliver Thomas, Hansen, Morgan Scott
• Primary Examiner(s): Miller, Alan S
• Application Number:
  US13/967,148
• Publication Number:
  US 20140058795A1
• Time in Patent Office: 1,322 Days
• Field of Search: 705 711- 742
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration
• CPC Class Codes: G06Q 30/0206 Price or cost determination based on market factors

Abstract

Systems, methods and computer program products for forecasting future values of an item, where an initial value for the item is determined, and then a baseline forecast for a future reference period is computed based on factors that include microeconomic data which is specific to an industry of the item and macroeconomic data which is non-specific to the industry of the item. The forecast may also be adjusted based on data for a set of competitive items. The forecast for the item is stored and is then made available to clients that can access the forecast to determine the expected future value of the item at some point in the future.

Claims

1. A system for forecasting future values of an item, the system comprising:

a server computer coupled to a network; and

a local data storage device coupled to the server computer;

wherein the server computer is configured to;

receive or collect different types of data over the network from data sources external to the system, the different types of data including modifications, locality, depreciation, microeconomic data, macroeconomic data, and competitive sets;

wherein the server computer has one or more crawlers configured to query at least one or more of the data sources external to the system;

wherein the modifications reflect any changes to an item that affect a value thereof at any time point;

wherein the locality represents valuation differences in an industry that vary geographically;

wherein the depreciation represents a natural change in value that occurs as the item is used over time;

wherein the microeconomic data comprises information that is specific to an industry of the item;

wherein the macroeconomic data comprises information that is nonspecific to the item and the industry of the item; and

wherein the competitive set relates to a set of items that compete with the item in the industry of the item;

store the different types of data received or collected by the server computer in the local data storage device;

identify portions of the different types of data stored in the local data storage device for generation of a residual value forecast for an item of interest;

perform a scrubbing process to scrub the identified portions of the different types of data to improve data quality of the data by and provide an improved basis for the forecast, the scrubbing process comprising identifying and removing erroneous data from the identified portions of the different types of data and removing outlying data points from the identified portions of the different types of data, the scrubbing process generating a modified data set;

store the modified data set in the local data storage device, the modified data set comprising past sales of a plurality of items in the industry;

determine an initial value for the item of interest based on the past sales of the item of interest or items that are similar to the item of interest;

determine an item value adjusted from the initial value to account for modifications to the item of interest and locality of the item of interest;

determine one or more future values for the item of interest utilizing the item value of the item of interest and based at least in part on a rate of depreciation of the item of interest over time, microeconomic data specific to the industry of the item of interest, and macroeconomic data non-specific to the item of interest and the industry of the item of interest, the macroeconomic data including economic information relating to the overall economy including consumer wage information and prices of goods unrelated to the plurality of items in the industry, the one or more future values forming a residual value curve and representing the residual value forecast for the item of interest;

store the one or more future values in the local data storage device;

provide the one or more future values to a client device over the network for display on the client device via a user interface;

receive editorial input over the network via the user interface displayed on the client device;

modify the one or more future values stored in the local data storage device based on the editorial input to account for factors that affect the one or more future values that have since changed or were not accounted for in the determining of the one or more future values;

automatically modify the one or more future values at regular intervals without user intervention, based at least on competitive set information relating to a set of items that compete with the item of interest in the industry of the item of interest;

store the one or more modified future values in the local data storage device; and

responsive to a request from a client device to view the residual value forecast for the item of interest, provide the one or more modified future values to the client device over the network.

2. The system of claim 1, wherein the one or more crawlers are further configured to query at least one data source of the data sources external to the system via the network and to obtain data from the queried at least one data source responsive to the queries.

3. The system of claim 1, wherein the server computer is further configured to determine one or more update intervals, to update the future values at the determined intervals, and to store the updated future values.

4. The system of claim 1, further comprising a workbench configured for providing a user interface which enables a user to access the one or more future values, wherein the server computer modifies the one or more future values based on input provided by the user through the workbench.

5. A method for forecasting future values of an item, the method comprising:

receiving or collecting different types of data over the network from data sources external to the system, the different types of data including modifications, locality, depreciation, microeconomic data, macroeconomic data, and competitive sets;

wherein the server computer has one or more crawlers configured to query at least one or more of the data sources communicatively connected to the server computer via the network;

wherein the modifications reflect any changes to an item that affect a value thereof at any time point;

wherein the locality represents valuation differences in an industry that vary geographically;

wherein the depreciation represents a natural change in value that occurs as the item is used over time;

wherein the microeconomic data comprises information that is specific to an industry of the item;

wherein the macroeconomic data comprises information that is nonspecific to the item and the industry of the item; and

wherein the competitive set relates to a set of items that compete with the item in the industry of the item;

storing the different types of data received or collected by the server computer in the local data storage device;

identifying portions of the different types of data stored in the local data storage device for generation of a residual value forecast for an item of interest;

performing a scrubbing process to scrub the identified portions of the different types of data to improve data quality of the data by and provide an improved basis for the forecast, the scrubbing process comprising identifying and removing erroneous data from the identified portions of the different types of data and removing outlying data points from the identified portions of the different types of data, the scrubbing process generating a modified data set;

storing the modified data set in the local data storage device, the modified data set comprising past sales of a plurality of items in the industry;

determining, by the server computer, an initial value for the item of interest based on the past sales of the item of interest or items that are similar to the item of interest;

determining an item value adjusted from the initial value to account for modifications to the item of interest and locality of the item of interest;

determining, by the sever computer, one or more future values for the item of interest utilizing the item value of the item of interest and based at least in part on a rate of depreciation of the item of interest over time, microeconomic data specific to the industry of the item of interest, and macroeconomic data non-specific to the item of interest and the industry of the item of interest, the macroeconomic data including economic information relating to the overall economy including consumer wage information and prices of goods unrelated to the plurality of items in the industry, the one or more future values forming a residual value curve and representing the residual value forecast for the item of interest;

storing, by the server computer, the one or more future values in the local data storage device;

providing, by the server computer, the one or more future values to a client device over the network for display on the client device via a user interface;

receiving editorial input over the network via the user interface displayed on the client device;

modifying, by the server computer, the one or more future values stored in the local data storage device based on the editorial input to account for factors that affect the one or more future values that have since changed or were not accounted for in the determining of the one or more future values;

automatically modifying, by the server computer, the one or more future values at regular intervals without user intervention, based at least on competitive set information relating to a set of items that compete with the item of interest in the industry of the item of interest;

storing, by the server computer, the one or more modified future values in the local data storage device; and

responsive to a request from a client device to view the residual value forecast for the item of interest, providing the one or more modified future values to the client device over the network.

6. The method of claim 5, further comprising:

querying at least one data source of the data sources using a crawler of the one or more crawlers; and

obtaining data from the queried at least one data source responsive to the queries.

7. The method of claim 5, further comprising:

determining one or more update intervals;

updating the future values at the determined intervals; and

storing the updated future values.

8. The method of claim 5, further comprising:

enabling a user to access the one or more future values through a workbench module; and

modifying the one or more future values based on input provided by the user through the workbench module.

9. A computer program product comprising at least one non-transitory computer-readable storage medium storing computer instructions that are translatable by a processor of a server computer to perform:

receiving or collecting different types of data over the network from data sources external to the system, the different types of data including modifications, locality, depreciation, microeconomic data, macroeconomic data, and competitive sets;

wherein the server computer has one or more crawlers configured to query at least one or more of the data sources via the network;

wherein the modifications reflect any changes to an item that affect a value thereof at any time point;

wherein the locality represents valuation differences in an industry that vary geographically;

wherein the depreciation represents a natural change in value that occurs as the item is used over time;

wherein the microeconomic data comprises information that is specific to an industry of the item;

wherein the macroeconomic data comprises information that is nonspecific to the item and the industry of the item; and

wherein the competitive set relates to a set of items that compete with the item in the industry of the item;

storing the different types of data received or collected by the server computer in the local data storage device;

identifying portions of the different types of data stored in the local data storage device for generation of a residual value forecast for an item of interest;

performing a scrubbing process to scrub the identified portions of the different types of data to improve data quality of the data by and provide an improved basis for the forecast, the scrubbing process comprising identifying and removing erroneous data from the identified portions of the different types of data and removing outlying data points from the identified portions of the different types of data, the scrubbing process generating a modified data set;

storing the modified data set in the local data storage device, the modified data set comprising past sales of a plurality of items in the industry;

determining an initial value for the item of interest based on the past sales of the item of interest or items that are similar to the item of interest;

determining an item value adjusted from the initial value to account for modifications to the item of interest and locality of the item of interest;

determining one or more future values for the item of interest utilizing the item value of the item of interest and based at least in part on a rate of depreciation of the item of interest over time, microeconomic data specific to the industry of the item of interest, and macroeconomic data non-specific to the item of interest and the industry of the item of interest, the macroeconomic data including economic information relating to the overall economy including consumer wage information and prices of goods unrelated to the plurality of items in the industry, the one or more future values forming a residual value curve and representing the residual value forecast for the item of interest;

storing the one or more future values in the local data storage device;

providing the one or more future values to a client device over the network for display on the client device via a user interface;

receiving editorial input over the network via the user interface displayed on the client device;

modifying the one or more future values stored in the local data storage device based on the editorial input to account for factors that affect the one or more future values that have since changed or were not accounted for in the determining of the one or more future values;

automatically modifying the one or more future values at regular intervals without user intervention, based at least on competitive set information relating to a set of items that compete with the item of interest in the industry of the item of interest;

storing the one or more modified future values in the local data storage device; and

responsive to a request from a client device to view the residual value forecast for the item of interest, providing the one or more modified future values to the client device over the network.

10. The computer program product of claim 9, wherein the computer instructions are further translatable to by the processor to perform:

querying at least one data source of the data sources using a crawler of the one or more crawlers; and

obtaining data from the queried at least one data source responsive to the queries.

11. The computer program product of claim 9, wherein the computer instructions are further translatable by the processor to perform:

determining one or more update intervals;

updating the future values at the determined intervals; and

storing the updated future values.

12. The computer program product of claim 9, wherein the computer instructions are further translatable by the processor to perform:

enabling a user to access the one or more future values through a workbench module; and

modifying the one or more future values based on input provided by the user through the workbench module.