KR102004751B1 - System and method for granting confidence score for extimated property price - Google Patents

Abstract

A system and method for providing a reliability rating for a property estimate price is disclosed. A real estate price estimation module for estimating real estate prices by a predetermined automated valuation model (AVM); A reliability evaluation module for evaluating reliability of the real estate price estimated by the real estate price estimation module and assigning the rating to the rating; And a reliability evaluation verification module for verifying the rating given by the reliability evaluation module. According to the system and method for assigning the reliability rating to the estimated value of the real estate described above, the reliability of the official land price, which is the standard of the taxation standard of the government, is configured to evaluate the accuracy and reliability of the real estate price estimation, This can be used to estimate new real estate prices with high reliability.

Description

TECHNICAL FIELD [0001] The present invention relates to a system and a method for assigning a reliability rating to an estimated value of a real estate,

The present invention relates to a system and method for estimating and assigning a reliability rating, and more particularly, to a reliability rating system and method for estimating a real estate price.

The government estimates real estate prices by applying an automated valuation model (AVM) on land and buildings across the country to levy property taxes on real estate. As an automatic evaluation model, mathematical models such as regression analysis model and artificial intelligence can be used.

Estimated real estate prices are used as official land prices, and financial institutions such as banks also use automatic valuation models to estimate the value of collateral.

However, the estimated prices calculated by various automatic evaluation models are also inevitably variable, and there is no index to judge how accurate these estimated prices are.

Because there are various types of automatic evaluation models, if the accuracy and reliability can be verified, real estate prices can be easily and accurately estimated.

10-2007-0034337

It is an object of the present invention to provide a reliability rating system for a real estate estimated price.

Another object of the present invention is to provide a method for assigning a reliability rating to an estimated real estate price.

According to another aspect of the present invention, there is provided a system for assigning a reliability rating to a real estate estimation price, comprising: a real estate price estimation module for estimating real estate prices using an automated valuation model (AVM); And a reliability evaluation module that evaluates reliability of the real estate price estimated by the real estate price estimation module and assigns the rating to the reliability evaluation module.

Here, the reliability evaluation module can be configured such that the reliability is evaluated to be higher as the number of cases of transactions in a predetermined peripheral region of the real estate is large and the characteristics of real estate in the peripheral region are similar.

At this time, the property of the real estate may be configured to include the area and the elapsed years of the real estate.

And the reliability evaluation module may be configured to assign the rating using the values obtained by standardizing and summing the price gap rate of the automatic evaluation model, the transaction price volatility, the neighboring region transaction frequency, the elapsed year specificity, and the dedicated area specificity have.

And the reliability evaluation module is classified into A grade, 0.0 or more and less than 1.0 when the standardized value of the automatic valuation model, the price fluctuation rate of the automatic valuation model, the transaction price price variability, the surrounding area transaction frequency, , A rating of B may be made to give a rating of C from -1.0 to less than 0.0, and a rating of D to less than 1.0.

On the other hand, it may be configured to further include a reliability evaluation verification module that verifies the rating given by the reliability evaluation module.

여기서, 상기 비율은 추정가격/실제거래가격이고, 상기 비율이 1.0 초과이면 상기 자동 평가 모델이 과대 추정한 것으로 판단하고, 상기 비율이 1.0 미만이면 상기 자동 평가 모델이 과소 추정한 것으로 판단하고, 상기 비율이 1.0에 가까울수록 정확하게 가격을 추정한 것으로 판단하도록 구성될 수 있다.Here, the reliability evaluation and verification module may be configured to calculate COD (Coefficient Of Dispersion) according to the following equation to verify the rating,

If the ratio is less than 1.0, it is determined that the automatic evaluation model is underestimated. If the ratio is less than 1.0, the automatic evaluation model is estimated to be underestimated, The closer the ratio is to 1.0, the more accurately the price is estimated.

According to another aspect of the present invention, there is provided a method for providing a reliability rating of a real estate estimation price, the real estate price estimation module estimating a real estate price using an automated valuation model (AVM); Evaluating reliability of the real estate price estimated by the real estate price estimation module and assigning the rating to the reliability evaluation module; And the reliability evaluation verification module verifying the rating assigned by the reliability evaluation module.

Here, the step of evaluating the reliability of the real estate price estimated by the reliability evaluation module by the real estate price estimation module and assigning the rating to the real estate price estimation module may include: Can be configured to highly evaluate the reliability.

At this time, the property of the real estate may be configured to include the area and the elapsed years of the real estate.

And the reliability evaluation module evaluating the reliability of the real estate price estimated by the real estate price estimation module and assigning the rating to the reliability evaluation module may further include a step of calculating a price gap rate, a transaction price variability, And can be configured to give the above-mentioned grade using a value obtained by standardizing and summing the specificity and dedicated area specificity, respectively.

And the reliability evaluation module evaluating the reliability of the real estate price estimated by the real estate price estimation module and assigning the rating to the reliability evaluation module may further include a step of calculating a price gap rate, a transaction price variability, If the standardized value of the specificity and dedicated area specificity is 1.0 or more, the grade A is assigned. If the value is 0.0 or more and 1.0 or less, the grade B is assigned.

여기서, 상기 비율은 추정가격/실제거래가격이고, 상기 비율이 1.0 초과이면 상기 자동 평가 모델이 과대 추정한 것으로 판단하고, 상기 비율이 1.0 미만이면 상기 자동 평가 모델이 과소 추정한 것으로 판단하고, 상기 비율이 1.0에 가까울수록 정확하게 가격을 추정한 것으로 판단하도록 구성될 수 있다.And the step of verifying the rating given by the reliability evaluation module by the reliability evaluation module is configured to calculate the COD (Coefficient Of Dispersion) according to the following equation to verify the rating,

If the ratio is less than 1.0, it is determined that the automatic evaluation model is underestimated. If the ratio is less than 1.0, the automatic evaluation model is estimated to be underestimated, The closer the ratio is to 1.0, the more accurately the price is estimated.

According to the system and method for assigning the reliability rating to the estimated value of the real estate described above, the reliability of the official land price, which is the standard of the taxation standard of the government, is configured to evaluate the accuracy and reliability of the real estate price estimation, This can be used to estimate new real estate prices with high reliability.

1 is a block diagram of a reliability rating system for a real estate estimation price according to an embodiment of the present invention.
FIGS. 2A to 2C are diagrams illustrating rating calculation for estimated real estate prices according to an embodiment of the present invention.
3 is a flowchart of a method for assigning a reliability rating to a real estate estimate price according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail to the concrete inventive concept. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals are used for like elements in describing each drawing.

The terms first, second, A, B, etc. may be used to describe various elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Do not.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram of a reliability rating system for a real estate estimation price according to an embodiment of the present invention.

Referring to FIG. 1, a reliability rating system 100 for a real estate estimation price according to an embodiment of the present invention includes a real estate price estimation module 110, a reliability evaluation module 120, and a reliability evaluation and verification module 130 . ≪ / RTI >

The reliability rating system 100 for the real estate estimated price evaluates the reliability of the real estate price estimated based on a predetermined automated valuation model (AVM), and the real estate price with low reliability is estimated by another automatic evaluation model And newly calculated to calculate a correct estimated price.

Hereinafter, the detailed configuration will be described.

The real estate price estimation module 110 may be configured to estimate the real estate price by a predetermined automatic evaluation model.

Here, the automatic evaluation model may include all the mathematical models such as the regression analysis model and the artificial intelligence. And the real estate price may be an official gazette that becomes a tax base, or it may be the price independently estimated by the financial institution for the value of the collateral.

The reliability evaluation module 120 may be configured to evaluate the reliability of the real estate price estimated by the real estate price estimation module 110 to give a rating. Here, the grade can be divided into four grades of A grade, B grade, C grade and D grade. Class A has the highest reliability for the estimated price, and Class D has the lowest reliability for the estimated price.

The reliability evaluation module 120 can be configured to evaluate the reliability as the number of cases of transactions in a predetermined peripheral region of the real estate and the similarity of the properties of real estate in the peripheral region are high. Here, the property of the real estate can be configured to include the area and the elapsed years of the real estate. In other words, the reliability of the estimated price can be increased if the sample size is large and the area or age of the sample is similar.

Specifically, the reliability evaluation module 120 is configured to assign a rating using a value obtained by standardizing and summing the price gap rate of the automatic evaluation model, the transaction price volatility, the neighboring region transaction frequency, the elapsed year specificity, and the exclusive area specificity, respectively .

Here, the price gap rate of the automatic evaluation model means the ratio of the maximum price calculation value to the minimum price calculation value among the automatic evaluation models. And the transaction price volatility means the value of the regression model R ² based on the 30 transaction cases in the neighborhood. And the frequency of transactions in the neighboring region means the number of transaction prices that are concluded in a nearby area within a radius of 200 m. And the specificity of the elapsed years means the gap between the average number of years elapsed and the number of elapsed years for the 30 cases in the neighboring area. The specific area specificity means the gap between the average area of 30 cases of nearby regional transactions and the area dedicated to this area.

More specifically, the reliability evaluation module 120 determines whether the standard deviation of the automatic valuation model, the price volatility of the transaction model, the transaction price variability, the adjacent region transaction frequency, the year-to-year specificity, A class B rating of 0.0 or more and less than 1.0, a class C rating of 1.0 or more and less than 0.0, and a class D rating of less than 1.0.

The reliability evaluation verification module 130 may be configured to verify the rating assigned by the reliability evaluation module 120. [

The reliability evaluation and verification module 130 may be configured to calculate COD (Coefficient Of Dispersion) according to the following equation (1) to verify the rating.

Here, the ratio is the estimated price / actual transaction price. If the ratio is over 1.0, it is determined that the automatic evaluation model is overestimated. If the ratio is less than 1.0, it is determined that the automatic evaluation model is underestimated. It can be configured to judge that the price is accurately estimated.

FIGS. 2A to 2C are diagrams illustrating rating calculation for estimated real estate prices according to an embodiment of the present invention.

FIG. 2A shows an example in which an automatic evaluation model is constructed for seven multi-family houses in Yongsan-gu area to estimate the real estate price, and then the reliability of the estimated price of the real estate is evaluated and given a rating.

FIG. 2B shows ratios for each of the A to D grades. Here, it is preferable to re-estimate the real estate price using at least another automatic evaluation model for the case of the D-grade.

In FIG. 2 (d), the results of the reliability evaluation and rating are shown in a graph. The COD of the A grade is 8.42, the COD of the B grade is 9.99, the COD of the C grade is 15.96, the COD of the D grade is 16.04, and the granting of the price grade is interpreted as relatively reasonable.

3 is a flowchart of a method for assigning a reliability rating to a real estate estimate price according to an embodiment of the present invention.

Referring to FIG. 3, the real estate price estimation module 110 estimates the real estate price by a predetermined automated valuation model (S101).

Next, the reliability evaluation module 120 evaluates the reliability of the real estate price estimated by the real estate price estimation module 110, and assigns the rating to the reliability (S102).

Here, the reliability evaluation module 120 can be configured such that the reliability is evaluated to be higher as the number of cases of transactions in a predetermined peripheral region of the real estate is large and the characteristics of the real estate in the peripheral region are similar. At this time, the characteristics of the real estate can be configured to include the area and the elapsed years of the real estate.

The reliability evaluation module 120 may be configured to assign a rating using a value obtained by standardizing and summing the price gap rate of the automatic evaluation model, the transaction price volatility, the adjacent region transaction frequency, the elapsed year specificity, and the dedicated area specificity .

In this case, if the standardized value of the price variance rate, the transaction price price variability, the area transaction frequency, the elapsed year specificity, and the specific area specificity of the corresponding automatic evaluation model is 1.0 or more, If it is 1.0 or more, it may be configured to give grade C if less than 0.0 and to grade D if it is less than 1.0.

Next, the reliability evaluation and verification module 130 verifies the rating assigned by the reliability evaluation module 120 (S103).

Here, the reliability evaluation and verification module 130 may be configured to calculate COD (Coefficient Of Dispersion) according to the following equation (2) to verify the rating.

Here, the ratio is the estimated price / actual transaction price. If the ratio is over 1.0, it is determined that the automatic evaluation model is overestimated. If the ratio is less than 1.0, it is determined that the automatic evaluation model is underestimated. It can be configured to judge that the price is accurately estimated.

It will be understood by those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit and scope of the invention as defined in the following claims will be.

110: Real estate price estimation module
120: Reliability evaluation module
130: Reliability Evaluation Verification Module

Claims (13)

A real estate price estimation module for estimating a real estate price of a predetermined real estate by a plurality of automated valuation models (AVM);
Wherein the real estate price estimation module calculates a real estate price by using the ratio of the actual price transaction price of the predetermined real estate to the maximum price calculation value of the ratio of the prices calculated by the plurality of automatic evaluation models to the lowest price calculation value A reliability evaluation module that evaluates reliability and assigns a rating;
And a reliability evaluation verifying module for verifying a rating assigned by the reliability evaluation module using a ratio of a real estate price estimated by the plurality of automatic evaluation models to an actual transaction price of the real estate,
The real estate price estimation module includes:
And an automatic evaluation model different from the corresponding automatic evaluation model is applied to a real estate price of a grade lower than a predetermined standard among the classes verified by the reliability evaluation and verification module,
The reliability evaluation module includes:
Evaluating the reliability of the real estate price again estimated by the real estate price estimation module, and re-rating the real estate price,
Wherein the reliability evaluation verification module comprises:
And to re-verify the rating re-granted by the reliability evaluation module. The system of claim 1, wherein the reliability evaluation module comprises:
Wherein the reliability evaluation unit evaluates the reliability of the estimated real estate price when the number of transactions in a predetermined peripheral area of the real estate is large and the characteristics of the real estate in the peripheral area are similar. 3. The method according to claim 2,
The real estate area and the elapsed years of the real estate. The system of claim 1, wherein the reliability evaluation module comprises:
Wherein the system is configured to assign the grade using a value obtained by standardizing and summing the price gap rate of the automatic evaluation model, the transaction price volatility, the neighboring region transaction frequency, the elapsed year specificity, and the exclusive area specificity, Reliability rating system for. 5. The apparatus of claim 4, wherein the reliability evaluation module comprises:
If the standardized and summed values of the price variance rate, the transaction price variability, the surrounding region transaction frequency, the elapsed year specificity, and the specific area specificity of the automatic evaluation model are 1.0 or more, 0.0 > C < / RTI > rating if the value is less than 0.0 and D if the value is less than 1.0. delete 6. The system according to claim 5,
And calculating the COD (Coefficient Of Dispersion) according to the following equation to verify the rating,
[Mathematical Expression]

If the ratio is less than 1.0, it is determined that the automatic evaluation model is underestimated. If the ratio is less than 1.0, the automatic evaluation model is estimated to be underestimated, The estimated price is estimated to be an accurate price as the ratio is closer to 1.0. Estimating a real estate price of a predetermined real estate by a plurality of automatic valuation models (AVM);
The reliability evaluation module calculates the estimated value of the real estate price estimated by the real estate price estimation module using the ratio of the actual price transaction price of the predetermined real estate to the maximum price calculation value of the ratio of the prices calculated by the plurality of automatic evaluation models Evaluating the reliability of the real estate price and assigning the rating;
And verifying a rating assigned by the reliability evaluation module using a ratio of a real estate price estimated by the plurality of automatic evaluation models to an actual transaction price of the real estate,
Wherein the real estate price estimation module estimates the real estate price by a predetermined automatic evaluation model,
And an automatic evaluation model different from the corresponding automatic evaluation model is applied to a real estate price of a grade lower than a predetermined standard among the classes verified by the reliability evaluation and verification module,
Wherein the reliability evaluation module evaluates the reliability of the real estate price estimated by the real estate price estimation module,
Evaluating the reliability of the real estate price again estimated by the real estate price estimation module, and re-rating the real estate price,
Wherein the step of verifying the rating provided by the reliability assessment module,
And to re-verify the rating again given by the reliability evaluation module. 9. The method according to claim 8, wherein the reliability evaluation module evaluates reliability of the real estate price estimated by the real estate price estimation module,
And the reliability is evaluated to be higher as the number of transactions in a predetermined peripheral region of the real estate is large and the characteristics of the real estate in the peripheral region are similar to each other. 10. The method according to claim 9,
Wherein the estimated real estate price includes an area of the real estate and the number of years elapsed. 9. The method according to claim 8, wherein the reliability evaluation module evaluates reliability of the real estate price estimated by the real estate price estimation module,
Wherein the system is configured to assign the grade using a value obtained by standardizing and summing the price gap rate of the automatic evaluation model, the transaction price volatility, the neighboring region transaction frequency, the elapsed year specificity, and the exclusive area specificity, How to give a reliability rating for. 12. The method according to claim 11, wherein the reliability evaluation module evaluates reliability of the real estate price estimated by the real estate price estimation module and assigns a rating,
If the standardized and summed values of the price variance rate, the transaction price variability, the surrounding region transaction frequency, the elapsed year specificity, and the specific area specificity of the automatic evaluation model are 1.0 or more, 0.0 > class < / RTI > rating if the value is less than 0.0, and class D if the value is less than 1.0. 13. The method of claim 12, wherein the step of verifying the rating assigned by the reliability assessment module,
And calculating the COD (Coefficient Of Dispersion) according to the following equation to verify the rating,
[Mathematical Expression]

If the ratio is less than 1.0, it is determined that the automatic evaluation model is underestimated. If the ratio is less than 1.0, the automatic evaluation model is estimated to be underestimated, Wherein the estimated price is estimated to be an accurate price as the ratio approaches 1.0.

Images