IP Library Granted Patent US 10,055,788
Granted Patent B1
US 10,055,788 · App. 13/619,642 · Granted Aug 21, 2018

Systems, methods, and computer-readable storage media for calculating a housing volatility index

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,055,788
App. No.
13/619,642
Granted
Aug 21, 2018
Kind
B1
Abstract

Systems, methods, and computer-readable media are disclosed for calculating a housing volatility index. An exemplary embodiment includes accessing stored property value data reflecting first values of real estate properties during a first time period and second values of the real estate properties during a second time period. The second time period may be subsequent to the first time period. The property value data may be processed to identify the first values and the second values, and time intervals between dates of the first values and dates of the second values may be calculated. Value changes of the real estate properties over the time intervals may also be calculated, based on the first values and the second values. A volatility measure for the real estate properties may be determined based on the value changes of the real estate properties over the time intervals, and the volatility measure may be output to a user.

Claims (56)

1. A computer-implemented method, performed by a processor operably connected to a communication network over a first network connection, at least one database operably connected to the communication network over a second network connection, and a client terminal operably connected to the communication network over a third network connection, the method comprising:

receiving, from the client terminal connected to the processor over the communication network, a user request over the first and third network connections, to evaluate the performance of an automated valuation model;

identifying, by the processor, a target performance level for evaluating an automated valuation model, the target performance level corresponding to a target performance of the automated valuation model at estimating values of real estate properties, wherein the target performance of the automated valuation model is based on stored data including a percentage of property values estimated by the automated valuation model for a plurality of real estate properties that are within a pre-determined range of actual sales prices for the set of properties during a time period corresponding to a first level measurement of housing volatility stored in the at least one database, and wherein the first level measurement of housing volatility is derived from historical data of value changes of the plurality of real estate properties;

accessing, the at least one database, stored property values of the plurality of real estate properties over the first and second network connections;

identifying, for each of the plurality of real estate properties, a first value corresponding to a first date and a second value corresponding to a second date, each first date preceding a corresponding second date;

determining, by the processor, a time interval between each first date and each corresponding second date;

determining, by the processor, a second level measurement of housing volatility corresponding to a second time period by deriving a measure of deviation based on each time interval and a plurality of ratios of each first value and corresponding second value, wherein the plurality of ratios correspond to a log ratio of value changes between the first value and the second value for each of the plurality of real estate properties, and wherein the measure of deviation is based on a difference between the log ratio of value changes and an annualized variance for the plurality of real estate properties;

adjusting, by the processor, the target performance level based on a relationship between the first level measurement of housing volatility and the second level measurement of housing volatility, wherein the adjustment accounts for a relationship between housing volatility and relative predictability of actual sales prices of real estate properties;

accessing over the first and second network connections, in the at least one database, and by the processor, stored data representing performance of the automated valuation model during a time period corresponding to the second level measurement of housing volatility, the stored data including a percentage of property values estimated by the automated valuation model for a set of properties that are within the pre-determined range of actual sales prices for the set of properties;

comparing, by the processor, the performance of the automated valuation model to the adjusted target performance level;

generating, by the processor, an indication of accuracy of the automated valuation model based on the comparing;

generating instructions that modify operation of at least one web page displaying the indication of accuracy of the automated valuation model based on the indication of accuracy of the automated valuation model;

transmitting, by the processor over the network over the first and third network connections, the created web page for display on the client terminal in response to the user request; and

transmitting, by the processor over the network to an automated valuation model evaluation engine, the indication of accuracy of the automated valuation model, wherein the indication of accuracy includes a “pass” or “fail” result, wherein the received transmission of the indication of accuracy causes the automated valuation model evaluation engine to further evaluate the automated valuation model based on an expected level of performance, and wherein the expected level of performance is adjusted based on either the first or second level measurement of housing volatility.

2. The computer-implemented method according to claim 1 , wherein the target performance level is a base target coverage for the automated valuation model.

3. The computer-implemented method according to claim 2 , wherein the base target coverage corresponds to a percentage of estimates by the automated valuation model that are expected to fall within a target confidence of actual property values, during the time period corresponding to the first level measurement of volatility.

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

selecting real estate properties having characteristics in common with real estate properties used to determine the performance of the automated valuation model; and

determining the second level measurement of housing volatility based on the selected real estate properties.

5. The computer-implemented method according to claim 4 , wherein the common characteristics correspond to one of a group comprising a property type, a loan type, and a location.

6. The computer-implemented method according to claim 1 , wherein the first level measurement of housing volatility and the second level measurement of housing volatility are determined based on real estate data regarding the same geographic region.

7. The computer-implemented method according to claim 1 , wherein adjusting the target performance level is based on a relationship between the standard deviation of the first level measurement of housing volatility and the standard deviation of the second level measurement of housing volatility.

8. The computer-implemented method according to claim 1 , wherein the target performance level is derived using stochastic techniques.

9. The computer-implemented method according to claim 1 , further comprising storing the adjusted target performance level after adjusting the target performance level.

10. The computer-implemented method according to claim 1 , wherein displaying an indication of accuracy further comprises:

outputting pass data to a web page sent to a client terminal; and

outputting fail data to the web page sent to the client terminal.

11. A system comprising:

a computer processor connected to a communication network, at least one database, and a client terminal; and

a memory device in communication with the processor and configured to store instructions, wherein, when the processor executes the instructions, the processor:

receives, from the client terminal connected to the processor over the communication network, a user request to evaluate the performance of an automated valuation model;

identifies, in the at least one database through the communication network, a target performance level for evaluating an automated valuation model, the target performance level representing a target performance of the automated valuation model at estimating values of real estate properties, wherein the target performance of the automated valuation model is based on stored data including a percentage of property values estimated by the automated valuation model for a plurality of real estate properties that are within a pre-determined range of actual sales prices for the set of properties during a time period corresponding to a first level measurement of housing volatility, and wherein the first level measurement of housing volatility is derived from historical data of value changes of the plurality of real estate properties;

accesses, in the at least one database through the communication network, stored property values of the plurality of real estate properties;

identifies, for each of the plurality of real estate properties, a first value corresponding to a first date and a second value corresponding to a second date, each first date preceding a corresponding second date;

determines a time interval between each first date and each corresponding second date;

determines a second level measurement of housing volatility corresponding to a second time period by deriving a measure of deviation based on each time interval and a plurality of ratios of each first value and corresponding second value, wherein the plurality of ratios correspond to a log ratio of value changes between the first value and the second value for each of the plurality of real estate properties, and wherein the measure of deviation is based on a difference between the log ratio of value changes and an annualized variance for the plurality of real estate properties;

adjusts the target performance level based on a relationship between the first level measurement of housing volatility and the second level measurement of housing volatility, wherein the adjustment accounts for a relationship between housing volatility and relative predictability of actual sales prices of real estate properties;

accesses, in the at least one database through the communication network, stored data representing performance of the automated valuation model during a time period corresponding to the second level measurement of housing volatility, the stored data including a percentage of property values estimated by the automated valuation model for a set of properties that are within the pre-determined range of actual sales prices for the set of properties;

compares the performance of the automated valuation model to the adjusted target performance level;

generates through the communication network, an indication of accuracy of the automated valuation model based on the comparing;

creates a web page displaying the indication of accuracy of the automated valuation model;

transmits, over the network, the created web page for display on the client terminal in response to the user request; and

transmits, over the network to an automated valuation model evaluation engine, the indication of accuracy of the automated valuation model, wherein the indication of accuracy includes a “pass” or “fail” result, wherein the received transmission of the indication of accuracy causes the automated valuation model evaluation engine to further evaluate the automated valuation model based on an expected level of performance, and wherein the expected level of performance is adjusted based on either the first or second level measurement of housing volatility.

12. The system of claim 11 , wherein the target performance level is a base target coverage for the automated valuation model.

13. The system of claim 12 , wherein the base target coverage corresponds to a percentage of estimates by the automated valuation model that are expected to fall within a target confidence of actual property values, during the time period corresponding to the first level measurement of volatility.

14. The system of claim 11 , wherein the memory further comprises instructions that, when executed by the processor, cause the processor to perform operations including:

selecting real estate properties having characteristics in common with real estate properties used to determine the performance of the automated valuation model; and

determining the second level measurement of housing volatility based on the selected real estate properties.

15. The system of claim 14 , wherein the common characteristics correspond to one of a group comprising a property type, a loan type, and a location.

16. The system of claim 11 , wherein the first level measurement of housing volatility and the second level measurement of housing volatility are determined based on real estate data regarding the same geographic region.

17. The system of claim 11 , wherein adjusting the target performance level is based on a relationship between the standard deviation of the first level measurement of housing volatility and the standard deviation of the second level measurement of housing volatility.

18. The system of claim 11 , wherein the target performance level is derived using stochastic techniques.

19. The system of claim 11 , wherein the memory further comprises instructions that, when executed by the processor, cause the processor to store the adjusted target performance level after adjusting the target performance level.

20. The system of claim 11 , wherein the memory further comprises instructions that, when executed by the processor, cause the processor to perform operations including:

outputting pass data to a web page sent to a client terminal; and

outputting fail data to the web page sent to the client terminal.

Assignments (3)
CORRECTION BY DECLARATION ERRONEOUSLY RECORDED ON REEL NO. 054298 AND FRAME NO. 0539. Recorded Aug 27, 2021
From: FEDERAL HOME LOAN MORTGAGE CORPORATION (FREDDIE MAC)
To: FEDERAL HOME LOAN MORTGAGE CORPORATION (FREDDIE MAC)
Reel/Frame 057671/0039 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 3, 2020
From: HEUER, JOAN D.; OCWEN FINANCIAL CORPORATION; ALTISOURCE HOLDINGS S.A.R.L.; ALTISOURCE S.AR.L.; FEDERAL HOME LOAN MORTGAGE CORPORATION
To: HEUER, JOAN D.; STEVEN MNUCHIN, UNITED STATES SECRETARY OF THE TREASURY AND SUCCESSORS THERETO.; ANDREI IANCU, UNDER SECRETARY OF COMMERCE FOR INTELLECTUAL PROPERTY, AND DIRECTOR OF THE UNITED STATES PATENT AND TRADEMARK OFFICE AND SUCCESSORS THERETO; LAUREL M. LEE, FLORIDA SECRETARY OF STATE AND SUCCESSORS THERETO; JEANETTE NÚÑEZ, LIEUTENANT GOVERNOR OF FLORIDA AND SUCCESSORS THERETO.; : ASHLEY MOODY, FLORIDA OFFICE OF THE ATTORNEY GENERAL AND SUCCESSORS THERETO.; TIMOTHY E. GRIBBEN, COMMISSIONER FOR BUREAU OF THE FISCAL SERVICE, AGENCY OF THE UNITED STATES DEPARTMENT OF THE TREASURY AND SUCCESSORS AND ASSIGNS THERETO.
Reel/Frame 054298/0539 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 13, 2018
From: TATANG, MENNER; GORDON, J. DOUGLAS; XIONG, MING; CHEN, SHAOJIE
To: FEDERAL HOME LOAN MORTGAGE CORPORATION (FREDDIE MAC)
Reel/Frame 046347/0241 →