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

• US 10,685,363 B2
• Filed: 07/25/2019
• Issued: 06/16/2020
• 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:
  US16/522,447
• Publication Number:
  US 20190347676A1
• Time in Patent Office: 327 Days
• Field of Search: 705 711- 742
• 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 method, comprising:

receiving or obtaining, by a computer, auction data from one or more data sources communicatively connected to the computer via a network;

determining or obtaining directly, by the computer from the auction data, an initial value of an item having a configuration at a first time period;

determining, by the computer at the first time period utilizing a set of constraints or consideration, a second time period at which adjustments are made to the item, the set of constraints or consideration including an expected lifespan for the item;

determining, by the computer, a number of forecasts between the first time period and the second time period, the number of forecasts corresponding to a time interval at which a forecast of a residual value of the item is to be generated by the computer;

if the initial value of the item varies across localities in which the item is available, determining, by the computer, a locality adjustment for each of the localities in which the item is available, the determining the locality adjustment including computing a ratio between an average cost of items in the industry in a locality at a time point and a local cost of items in the industry across the localities at the time point;

determining or obtaining, by the computer, any incremental values of modifications to the configuration of the item;

determining, by the computer, an adjusted value of the item at the second time period based at least on the initial value of the item and any incremental values determined or obtained by the computer for the item;

computing, by the computer, a residual value of the item at the second time period based at least on the adjusted value of the item at the second time period, depreciation of the item over time, macroeconomic factors not specific to the industry, and microeconomic factors specific to the industry;

determining, by the computer, an adjustment value for the residual value of the item at the second time period, the determining including comparing the residual value of the item at the second time period with a set of reference values, the adjustment value minimizing a weighted average error indicated by the set of reference values;

generating, by the computer, a final forecasted residual value for the item by adjusting the residual value of the item at the second time period with the adjustment value; and

communicating, by the computer, the final forecasted residual value of the item to a graphical user interface on a client device.

2. The method according to claim 1, further comprising:

responsive to the computer unable to determine or obtain directly from the auction data the initial value of the item having the configuration at the first time period, constructing a competitive set of similar or substitute items in the industry, selecting a similar or substitute item from the competitive set of similar or substitute items in the industry that is most similar to the item having the configuration, and using a value of the similar or substitute item selected from the competitive set of similar or substitute items in the industry as the initial value of the item having the configuration at the first time period.

3. The method according to claim 1, wherein the set of constraints or consideration further includes at least a purpose for obtaining the residual value of the item at the second time period or an update frequency indicating how often input data to the computer is updated.

4. The method according to claim 3, wherein the time interval at which a forecast of a residual value of the item is to be generated by the computer is same or more than the update frequency indicating how often input data to the computer is updated.

5. The method according to claim 1, wherein the modifications to the configuration of the item are observable at a particular time and are expected to retain value after the particular time.

6. The method according to claim 1, wherein the modifications to the configuration of the item are not observable at a particular time or are not expected to retain value after the particular time.

7. The method according to claim 1, wherein the determining the locality adjustment further includes utilizing a consumer price index in determining the average cost of items in the industry in the locality at the time point or the local cost of items in the industry across the localities at the time point.

8. A system, comprising:

a processor;

a non-transitory computer-readable medium; and

stored instructions translatable by the processor for;

receiving or obtaining auction data from one or more data sources communicatively connected to the system via a network;

determining or obtaining directly, from the auction data, an initial value of an item having a configuration at a first time period;

determining, at the first time period utilizing a set of constraints or consideration, a second time period at which adjustments are made to the item, the set of constraints or consideration including an expected lifespan for the item;

determining a number of forecasts between the first time period and the second time period, the number of forecasts corresponding to a time interval at which a forecast of a residual value of the item is to be generated by the system;

if the initial value of the item varies across localities in which the item is available, determining a locality adjustment for each of the localities in which the item is available, the determining the locality adjustment including computing a ratio between an average cost of items in the industry in a locality at a time point and a local cost of items in the industry across the localities at the time point;

determining or obtaining any incremental values of modifications to the configuration of the item;

determining an adjusted value of the item at the second time period based at least on the initial value of the item and any incremental values determined or obtained for the item;

computing a residual value of the item at the second time period based at least on the adjusted value of the item at the second time period, depreciation of the item over time, macroeconomic factors not specific to the industry, and microeconomic factors specific to the industry;

determining an adjustment value for the residual value of the item at the second time period, the determining including comparing the residual value of the item at the second time period with a set of reference values, the adjustment value minimizing a weighted average error indicated by the set of reference values;

generating a final forecasted residual value for the item by adjusting the residual value of the item at the second time period with the adjustment value; and

communicating the final forecasted residual value of the item to a graphical user interface on a client device.

9. The system of claim 8, wherein the stored instructions are further translatable by the processor for:

responsive to the system unable to determine or obtain directly from the auction data the initial value of the item having the configuration at the first time period, constructing a competitive set of similar or substitute items in the industry, selecting a similar or substitute item from the competitive set of similar or substitute items in the industry that is most similar to the item having the configuration, and using a value of the similar or substitute item selected from the competitive set of similar or substitute items in the industry as the initial value of the item having the configuration at the first time period.

10. The system of claim 8, wherein the set of constraints or consideration further includes at least a purpose for obtaining the residual value of the item at the second time period or an update frequency indicating how often input data to the system is updated.

11. The system of claim 10, wherein the time interval at which a forecast of a residual value of the item is to be generated by the system is same or more than the update frequency indicating how often input data to the system is updated.

12. The system of claim 8, wherein the modifications to the configuration of the item are observable at a particular time and are expected to retain value after the particular time.

13. The system of claim 8, wherein the modifications to the configuration of the item are not observable at a particular time or are not expected to retain value after the particular time.

14. The system of claim 8, wherein the determining the locality adjustment further includes utilizing a consumer price index in determining the average cost of items in the industry in the locality at the time point or the local cost of items in the industry across the localities at the time point.

15. A computer program product comprising a non-transitory computer-readable medium storing instructions translatable by a computer for:

receiving or obtaining auction data from one or more data sources communicatively connected to the computer via a network;

determining or obtaining directly, from the auction data, an initial value of an item having a configuration at a first time period;

determining, at the first time period utilizing a set of constraints or consideration, a second time period at which adjustments are made to the item, the set of constraints or consideration including an expected lifespan for the item;

determining a number of forecasts between the first time period and the second time period, the number of forecasts corresponding to a time interval at which a forecast of a residual value of the item is to be generated by the computer;

if the initial value of the item varies across localities in which the item is available, determining a locality adjustment for each of the localities in which the item is available, the determining the locality adjustment including computing a ratio between an average cost of items in the industry in a locality at a time point and a local cost of items in the industry across the localities at the time point;

determining or obtaining any incremental values of modifications to the configuration of the item;

determining an adjusted value of the item at the second time period based at least on the initial value of the item and any incremental values determined or obtained for the item;

computing a residual value of the item at the second time period based at least on the adjusted value of the item at the second time period, depreciation of the item over time, macroeconomic factors not specific to the industry, and microeconomic factors specific to the industry;

determining an adjustment value for the residual value of the item at the second time period, the determining including comparing the residual value of the item at the second time period with a set of reference values, the adjustment value minimizing a weighted average error indicated by the set of reference values;

generating a final forecasted residual value for the item by adjusting the residual value of the item at the second time period with the adjustment value; and

communicating the final forecasted residual value of the item to a graphical user interface on a client device.

16. The computer program product of claim 15, wherein the instructions are further translatable by the computer for:

responsive to the computer unable to determine or obtain directly from the auction data the initial value of the item having the configuration at the first time period, constructing a competitive set of similar or substitute items in the industry, selecting a similar or substitute item from the competitive set of similar or substitute items in the industry that is most similar to the item having the configuration, and using a value of the similar or substitute item selected from the competitive set of similar or substitute items in the industry as the initial value of the item having the configuration at the first time period.

17. The computer program product of claim 15, wherein the set of constraints or consideration further includes at least a purpose for obtaining the residual value of the item at the second time period or an update frequency indicating how often input data to the computer is updated.

18. The computer program product of claim 17, wherein the time interval at which a forecast of a residual value of the item is to be generated by the computer is same or more than the update frequency indicating how often input data to the computer is updated.

19. The computer program product of claim 15, wherein the modifications to the configuration of the item are observable at a particular time and are expected to retain value after the particular time.

20. The computer program product of claim 15, wherein the modifications to the configuration of the item are not observable at a particular time or are not expected to retain value after the particular time.