Method and system for providing a home data index model

• US 10,380,652 B1
• Filed: 10/16/2009
• Issued: 08/13/2019
• Est. Priority Date: 10/18/2008
• Status: Active Grant

• Current Assignee: ClearCapital.com, Inc.
• Original Assignee: ClearCapital.com, Inc.
• Inventors: Marshall, Kevin Leon, McSweeny, Sean M., Villacorta, Alexander
• Primary Examiner(s): Whitaker, Andrew B
• Application Number:
  US12/581,060
• Time in Patent Office: 3,588 Days
• Field of Search: 705313
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration
• CPC Class Codes: G06Q 30/0206 Price or cost determination based on market factors
• CPC Class Codes: G06Q 30/0278 Product appraisal
• CPC Class Codes: G06Q 50/16 Real estate

Abstract

The present invention builds Home Data Index (HDI) models. One driving force behind this HDI initiative is that no one model or measure can truly capture the widely dynamic movement of home prices. Even within a small geographical area, such as a ZIP code, there is significant variation in property sale types, sale frequencies and sale values. To better describe these variations, the present invention presents a suite of paired sales and price per square foot index models built around an array of property transaction characteristics. These HDI models expand on the usage and understanding of traditional home price indices (HPIs) by implementing a multidimensional index comprised of four main dimensions: geography; time frames; value range; and property sales type. Several layers exist within each dimension, allowing for more than 300 different index model perspectives for a given property address. For each permutation among the layers of the four main dimensions, a model is constructed with an associated confidence score that reflects the statistical relevance of each estimate.

Claims

1. A method of providing a home data index model in real-time, the method comprising:

selecting a model from a plurality of possible models stored in a memory, the selected model having the smallest relevant geographic resolution with the most specific cost constraints specific to a particular user, wherein the most specific cost constraints are stored in memory and include spatial resolution, data time lag resolution, sale value stratification organized across a plurality of different tiers and property sale type separated across a plurality of different sale transactions each having a set of characteristics;

performing a first accuracy test for the selected model to determine accuracy of the selected model against an accuracy threshold criteria;

performing a second accuracy test, the second accuracy test determining the accuracy of generalized characteristics of the selected model;

verifying that all values have been processed through the first accuracy test and second accuracy test; and

providing the home data index model in real time based on the processed values stored in memory, wherein the method is processed as a result of a processor executing instructions stored in the memory.

2. The method in claim 1, further comprising, after performing the second accuracy test but before the verification step, a step of repeating the first accuracy test and the second accuracy test with a new selected model having a higher relevant geographic resolution, the repeating being performed based on a result from the first accuracy test and the second accuracy test.

3. The method in claim 2, further comprising, after the first accuracy test but before the second accuracy test, a step of generalizing cost constraints for the selected model before performing the second accuracy test.

4. The method in claim 2, wherein the new selected model has a more specific cost constraints.

5. The method in claim 1, further comprising, after the first accuracy test but before the second accuracy test, a step of selecting an alternative model as the selected model with a higher relevant geographic resolution before generalizing cost constraints.

6. A system for providing a home data index model in real-time, the system comprising:

a processor; and

memory storing instructions executable by the processor to;

select a model, from a plurality of possible models stored in a memory, the selected model having a smallest relevant geographic resolution with a most specific cost constraints specific to a particular user, wherein the most specific cost constraints are stored in memory and include spatial resolution, data time lag resolution, sale value stratification organized across a plurality of different tiers and property sale type separated across a plurality of different sale transactions each having a set of characteristics;

perform a first accuracy test for the selected model to determine accuracy of the selected model against an accuracy threshold criteria;

perform a second accuracy test for the selected model to determine accuracy of generalized characteristics of the selected model;

verifying that all values have been processed through the first accuracy test and the second accuracy test; and

providing the home data index model in real-time based on the processed values stored in memory, wherein the model is selected, the first and second accuracy test is performed and the verification that all values have been processed are performed as a result of a processor executing instructions stored in the memory.

7. The system in claim 6, wherein the instructions stored in memory and executed by the processor further include after performance of the second accuracy test but before the verification step, a step for repeating the first accuracy test and the second accuracy test with a new selected model having a higher relevant geographic resolution, the repeating being performed based on the result from the first accuracy test and the second accuracy test.

8. The system in claim 7, wherein the instructions stored in memory and executed by the processor further include after performance of the first accuracy test but before the second accuracy test, a step of generalizing cost constraints for the selected model before performing the second accuracy test.

9. The system in claim 7, wherein the new selected model has a more specific cost constraints.

10. The system in claim 6, wherein the instructions stored in memory and executed by the processor further include after performance of the first accuracy step but before the second accuracy step, a step for selecting an alternative model as the selected model having a higher relevant geographic resolution before generalizing cost constraints.

11. A computer readable medium containing a set of instructions executable by a processor for providing a home data index model in real-time, said set of instructions comprising:

selecting a model, from a plurality of possible models stored in a memory, the selected model having a smallest relevant geographic resolution with a most specific cost constraints specific to a particular user, wherein the most specific cost constraints are stored in memory and include spatial resolution, data time lag resolution, sale value stratification organized across a plurality of different tiers and property sale type separated across a plurality of different sale transactions each having a set of characteristics;

performing a first accuracy test for the selected model to determine accuracy of the selected model against an accuracy threshold criteria;

performing a second accuracy test, for the selected model to determine accuracy of generalized characteristics of the selected model;

verifying that all values have been processed through the first accuracy test and the second accuracy test; and

providing the home data index model in real-time based on the processed values stored in memory, wherein the model is selected, the first and second accuracy test is performed and the check for additional values is processed as a result of a processor executing instructions stored in the memory.