Method and device for predicting supply probability and supply price of real estate

Abstract

A method for predicting the supply probability and supply price of real estate according to one aspect comprises: a step of obtaining a first supply probability of the real estate—the supply probability includes a probability of the real estate being supplied as a sale and a probability of the real estate being supplied as a lease—by using housing information, owner information, and a first market information of the real estate as inputs to a first prediction model; and a step of obtaining the supply price of the real estate using the first supply probability.

Description

Technology Field

[0001] The present disclosure relates to a method and apparatus for predicting the supply probability and supply price of real estate. Background Technology

[0002] Housing is a representative durable good; once newly supplied to the market, it takes a long time for it to be demolished, and consequently, the majority of housing traded in the market consists of existing stock. In 2021, out of approximately 1.82 million apartments in Seoul, about 210,000 units (11.5%) were built within the last five years, while approximately 890,000 units (48.8%) were over 20 years old. Therefore, it is crucial to predict not only the supply of new housing but also the patterns of change in existing stock.

[0003] Meanwhile, patterns of housing consumption can be categorized into owner-occupancy and renting based on the type of occupancy. The patterns of supply and demand for each type of occupancy can vary depending on the choices of owners and users, based on market conditions and housing characteristics. Furthermore, changes in housing supply and demand can lead to changes in the prices of relevant housing services in both the sales and rental markets. The smooth functioning of the housing market enables citizens to make rational choices regarding residential mobility and serves as the foundation for the domestic economy. Changes in supply and demand in the existing rental housing market, as well as in the sales market, can cause instability in the housing market and hinder the rational functioning of residential mobility for the public.

[0004] Various methods have been proposed regarding the prediction of real estate sales prices. For example, Korean Patent Publication No. 2017-0143258 discloses a technology for estimating housing prices by synthesizing public real estate data, such as price information from the Korea Appraisal Institute and actual transaction price information from the Ministry of Land, Infrastructure and Transport. However, Korean Patent Publication No. 2017-0143258 did not analyze prices in the rental housing market and did not consider the impact of transitions between owner-occupied and non-owner-occupied housing in the existing housing market. The problem to be solved

[0005] The invention provides a method and apparatus for predicting the supply probability and supply price of real estate. Additionally, the invention provides a computer-readable recording medium storing a program for executing the above method on a computer. The technical problems to be solved are not limited to those described above, and other technical problems may exist. means of solving the problem

[0006] A method for predicting the supply probability and supply price of real estate according to one aspect comprises: a step of obtaining a first supply probability of said real estate—whereby the supply probability includes a probability of said real estate being supplied as a sale and a probability of said real estate being supplied as a lease—by using housing information, owner information, and first market information of said real estate as inputs to a first prediction model; and a step of obtaining the supply price of said real estate using said first supply probability.

[0007] A device for predicting the supply probability and supply price of real estate according to other aspects includes a memory in which a first prediction model and a second prediction model are stored; and at least one processor; wherein the processor takes housing information, owner information, and first market information of the real estate as inputs to the first prediction model to obtain a first supply probability of the real estate—the supply probability includes a probability of the real estate being supplied as a sale and a probability of the real estate being supplied as a lease—and predicts the supply price of the real estate using the first supply probability.

[0008] A computer-readable recording medium according to another aspect includes a recording medium that records a program for executing the above-described method on a computer. Brief explanation of the drawing

[0009] FIG. 1 is a diagram illustrating an example of a system for predicting the supply probability and supply price of real estate according to one embodiment. FIG. 2 is a configuration diagram illustrating an example of a user terminal according to one embodiment. FIG. 3 is a flowchart illustrating an example of a method for predicting the supply probability and supply price of real estate according to one embodiment. FIG. 4 is a diagram illustrating an example of a first prediction model trained to predict the probability of supplying real estate according to one embodiment. FIG. 5 is a diagram illustrating examples of housing information, owner information, and market information according to one embodiment. FIG. 6 is a drawing for explaining an example of address classification according to one embodiment. FIG. 7 is a diagram illustrating an example of a second prediction model trained to predict the price of real estate according to one embodiment. FIG. 8 is a diagram illustrating an example of a method for constructing an integrated prediction model by inputting the supply price of real estate according to one embodiment into a first prediction model. FIGS. 9a to 9c are drawings illustrating an example in which a first prediction model according to one embodiment learns the correlation between independent variables included in actual transaction price information and land register information and the dependent variable, the probability of real estate supply. Specific details for implementing the invention

[0010] The terms used in the embodiments have been selected to be as close as possible to currently widely used general terms; however, these may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been selected at the applicant's discretion, and in such cases, their meanings will be described in detail in the relevant description section. Therefore, terms used in the specification must be defined not merely by their names, but based on their meanings and the content throughout the specification.

[0011] When a part of the specification is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "~ unit" or "~ module" as used in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware or software, or as a combination of hardware and software.

[0012] Additionally, terms including ordinal numbers, such as "first" or "second," used in the specification may be used to describe various components, but said components should not be limited by said terms. Such terms may be used for the purpose of distinguishing one component from another.

[0013] Embodiments are described in detail below with reference to the attached drawings. However, embodiments may be implemented in various different forms and are not limited to the examples described herein.

[0014] FIG. 1 is a diagram illustrating an example of a system for predicting the supply probability and supply price of real estate according to one embodiment.

[0015] Referring to FIG. 1, the system (1) includes a user terminal (10) and a server (20). For example, the user terminal (10) and the server (20) can be connected via wired or wireless communication to transmit and receive data to and from each other.

[0016] For convenience of explanation, FIG. 1 is illustrated as including a user terminal (10) and a server (20) in the system (1), but is not limited thereto. For example, the system (1) may include other external devices (not shown), and the operation of the user terminal (10) and server (20) described below may be implemented by a single device (e.g., user terminal (10) or server (20)) or by more devices.

[0017] The user terminal (10) may be a computing device comprising a display device and a device for receiving user input (e.g., a keyboard, a mouse, etc.), and including memory and a processor. For example, the user terminal (10) may be a notebook PC, a desktop PC, a laptop, a tablet computer, a smartphone, etc., but is not limited thereto.

[0018] The server (20) may be a device that communicates with an external device (not shown) including a user terminal (10). As an example, the server (20) may be a device that stores various data including real estate housing information, owner information, market information, actual transaction price information, and land register information. Alternatively, the server (20) may be a computing device that includes memory and a processor and has its own computational capabilities. If the server (20) is a computing device, the server (20) may perform at least some of the operations of the user terminal (10) described below with reference to FIGS. 1 to 8. For example, the server (20) may be a cloud server, but is not limited thereto.

[0019] The user terminal (10) outputs an image representing information generated through the prediction of the supply probability and supply price of real estate. For example, the image may display the probability that the current owner of the real estate will supply the real estate in the form of a sale, the sale supply price, the probability that the current owner will supply the real estate in the form of a lease, and the lease supply price. Additionally, the image may display information on the past transaction history of the real estate, housing information at the current time of the real estate, owner information, market information, and past transaction history information of real estate similar to the predicted target real estate.

[0020] The real estate subject to prediction can be selected by the user (30) and may be a single house, or may refer to multiple houses included in a specific address or apartment complex. The user (30) can select the real estate subject to prediction by entering the address of the real estate or by selecting a map displayed on the user terminal (10).

[0021] A user terminal (10) according to one embodiment obtains a first supply probability by using real estate housing information, owner information, and first market information as inputs to a first prediction model. Then, it obtains a supply price of real estate by using the first supply probability as inputs to a second prediction model.

[0022] A user terminal (10) according to one embodiment can construct an integrated model of a supply probability prediction model and a price prediction model by obtaining a second supply probability using the obtained supply price as input to the first prediction model.

[0023] Supply and demand in the form of sales and leases influence each other. Meanwhile, there may exist variables (such as owner information or market information) that affect the supply and demand of only one of the two types of supply. Therefore, methods that predict supply probabilities and prices based on only one type of supply, without integrating sales and leases, suffer from reduced accuracy.

[0024] In the specification of the present invention, supply probability includes sales probability and lease probability. And, supply price includes sales supply price and lease supply price. Accordingly, in the embodiment of the present invention, the accuracy of real estate supply probability and price prediction can be improved by integrating predictions for supply in the form of sales and supply in the form of lease.

[0025] Hereinafter, with reference to FIGS. 2 to 8, an example is described in which a user terminal (10) predicts a supply probability using real estate housing information, owner information, and market information, and predicts the price of real estate using the predicted supply probability.

[0026] Meanwhile, for the sake of convenience of explanation, the user terminal (10) has been described throughout the specification as performing operations according to one embodiment, but is not limited thereto. For example, at least some of the operations performed by the user terminal (10) may be performed by the server (20).

[0027] FIG. 2 is a configuration diagram illustrating an example of a user terminal according to one embodiment.

[0028] Referring to FIG. 2, the user terminal (100) includes a processor (110), memory (120), an input / output interface (150), and a communication module (160). For convenience of explanation, FIG. 2 only shows components related to the present invention. Accordingly, other general-purpose components may be included in the user terminal (100) in addition to the components shown in FIG. 2. Furthermore, it is obvious to those skilled in the art that the processor (110), memory (120), input / output interface (150), and communication module (160) shown in FIG. 2 may be implemented as independent devices.

[0029] The processor (110) can process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Here, the instructions may be provided from memory (120) or an external device (e.g., a server). Additionally, the processor (110) can control the overall operation of other components included in the user terminal (100).

[0030] The processor (110) can obtain housing information, owner information, and first market information of the real estate for which it intends to predict the supply probability and supply price. Then, the processor (110) can predict the supply probability of the real estate based on the obtained information. Subsequently, the processor (110) can obtain the supply price of the real estate using the predicted supply probability of the real estate. Here, the supply probability is a value that predicts the probability that the owner of the real estate will supply the real estate in the form of a sale or a lease, respectively.

[0031] Here, the housing information of the real estate may be information entered by a user through an input / output interface (150) or may be stored in memory (110). According to one embodiment, the housing information may include individual information and complex information. Here, the individual information may be information including at least one of a housing address, exclusive area, number of floors, number of rooms, number of bathrooms, and entrance structure. Additionally, the complex information may be information including at least one of a total number of households, elapsed years, number of parking spaces per household, construction company, and distance to a station.

[0032] According to one embodiment, a user terminal (100) obtains address information among real estate housing information from a user, and can collect real estate housing information for which address information has been obtained from a server of a government agency, a media outlet, or an economic reporting agency that provides various information related to real estate.

[0033] According to one embodiment, a user terminal (100) may obtain housing address information of real estate and collect real estate certificate information corresponding to the obtained address information from a server providing real estate certificate information. The user terminal (100) may extract owner information from Section A of the collected real estate certificate information. Here, the owner information may be information including at least one of the period of ownership of real estate, legal personality, number of owners, equity relationship, address classification, age, and maximum amount of debt.

[0034] According to one embodiment, a user terminal (100) may collect first market information at a time when it intends to predict the probability of supply and the supply price of real estate. Here, the first market information may include at least one of a mortgage interest rate, an average transaction price per pyeong, a sales turnover rate, and a lease turnover rate. Alternatively, the first market information may include other macroeconomic indicators that affect the supply and demand of real estate.

[0035] According to one embodiment, the processor (110) can obtain a first supply probability of real estate by using housing information, owner information, and first market information as inputs to a first prediction model (130). The first prediction model (130) may be a model trained to predict the supply probability of real estate based on actual transaction price information and land registry information during a certain period prior to the prediction time.

[0036] The processor (110) can obtain the supply price of the real estate using the first supply probability. Here, the supply price includes the sale supply price when the owner supplies the real estate in the form of a sale and the lease supply price when the owner supplies the real estate in the form of a lease.

[0037] According to one embodiment, the processor (110) can calculate a sales supply price using a sales probability included in the first supply probability, and calculate a lease supply price using a lease probability included in the first supply probability.

[0038] According to another embodiment, the processor (110) can obtain the supply price of real estate by using the first supply probability, demander information, and second market information as inputs to the second prediction model (140). The second prediction model (140) may be a model trained to predict the supply price of real estate based on actual transaction price information and land registry information during a certain period prior to the prediction time. By using the second prediction model (140), the processor (110) can obtain a supply price that takes into account the characteristics of the demander, and the accuracy of the supply price can be improved.

[0039] According to one embodiment, the user information may be information including at least one of the user's age, address classification, legal personality, and number of users. The user information may be input to the user terminal (100) by a user through the input / output interface (150).

[0040] According to one embodiment, the user terminal (100) may collect second market information at a time when it intends to predict the probability of supply and the supply price of real estate. The second market information may be information including at least one of mortgage interest rates and money supply. Alternatively, the second market information may include other macroeconomic indicators that affect the supply price of real estate. According to another embodiment, the user terminal (100) may use the first market information collected to obtain the first supply price as second market information and input it into a second prediction model (140).

[0041] According to one embodiment, the processor (110) can obtain a sales supply price based on a sales probability and a lease supply price based on a lease probability using a second prediction model (140). Then, the processor can calculate the ratio of the obtained sales supply price and the lease supply price, and use the calculated ratio as an input to the first prediction model. In other words, the processor (110) can obtain a second supply probability by inputting the calculated ratio, housing information, and market information into the first prediction model. According to the embodiment, the output value of the first prediction model that predicts the supply probability becomes the input value of the second prediction model that predicts the supply price, and the output value of the second prediction model becomes the input value of the first prediction model, thereby improving the accuracy of the supply probability prediction.

[0042] The processor (110) may be implemented as an array of multiple logic gates, or as a combination of a general-purpose microprocessor and memory storing a program that can be executed on the microprocessor. For example, the processor (110) may include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, etc. In some environments, the processor (110) may include an application-specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), etc. For example, the processor (110) may refer to a combination of processing devices such as a combination of a digital signal processor (DSP) and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors combined with a digital signal processor (DSP) core, or any other combination of such configurations.

[0043] The memory (120) may include any non-transient computer-readable recording medium. As an example, the memory (120) may include a permanent mass storage device such as a random access memory (RAM), read-only memory (ROM), disk drive, solid state drive (SSD), or flash memory. As another example, a permanent mass storage device such as a ROM, SSD, flash memory, or disk drive may be a separate permanent storage device distinct from the memory. Additionally, the memory (120) may store an operating system (OS) and at least one program code (e.g., code for the processor (110) to perform an operation described later with reference to FIGS. 3 through 8).

[0044] These software components may be loaded from a computer-readable recording medium separate from the memory (120). This separate computer-readable recording medium may be a recording medium that can be directly connected to the device (100) and may include, for example, a computer-readable recording medium such as a floppy drive, disk, tape, DVD / CD-ROM drive, memory card.

[0045] Alternatively, software components may be loaded into memory (120) via a communication module rather than a computer-readable recording medium. For example, at least one program may be loaded into memory (120) based on a computer program installed by files provided through a communication module by developers or a file distribution system that distributes installation files for an application (e.g., a computer program for a processor (110) to perform operations described later with reference to FIGS. 3 to 8).

[0046] The input / output interface (150) may be a means for interfacing with a device for input or output (e.g., keyboard, mouse, etc.) that may be connected to or included in the user terminal (100). In FIG. 2, the input / output interface (150) is shown as an element configured separately from the processor (110), but is not limited thereto, and the input / output interface (150) may be configured to be included in the processor (110).

[0047] The communication module (160) may provide a configuration or function for the server (20) and the user terminal (100) to communicate with each other via a network. Additionally, the communication module (160) may provide a configuration or function for the user terminal (100) to communicate with other external devices. For example, control signals, commands, data, etc. provided under the control of the processor (110) may be transmitted to the server (20) and / or external devices via the communication module (160) and the network.

[0048] Meanwhile, although not illustrated in FIG. 2, the user terminal (100) may further include a display device. Alternatively, the user terminal (100) may be connected to an independent display device via wired or wireless communication to transmit and receive data to and from each other. For example, past transaction history, actual transaction price, supply probability, supply price, etc. of real estate may be provided to the user (30) through the display device.

[0049] FIG. 3 is a flowchart illustrating an example of a method for predicting the supply probability and supply price of real estate according to one embodiment.

[0050] Referring to FIG. 3, the method for predicting the supply probability and supply price of real estate consists of steps processed in a time-series manner at the user terminal (10, 100) or processor (110) shown in FIG. 1 and 2. Therefore, even if details are omitted below, the content described above regarding the user terminal (10, 100) or processor (110) shown in FIG. 1 and 2 can also be applied to the method for predicting the supply probability and supply price of real estate in FIG. 3.

[0051] Additionally, as described above with reference to FIG. 1 and FIG. 2, at least one of the steps of the flowchart illustrated in FIG. 3 may be processed in a server (20) or a processor (110).

[0052] In step 310, the processor (110) obtains the first supply probability of the real estate by using the housing information, owner information, and first market information of the real estate as inputs to the first prediction model.

[0053] Here, the first prediction model may be a model trained to predict the probability of supplying real estate based on actual transaction price information and land registry information during a certain period prior to the prediction point. An example of the first prediction model being trained based on actual transaction price information and land registry information is described later in Fig. 4.

[0054] FIG. 4 is a diagram illustrating an example of a first prediction model trained to predict the probability of supplying real estate according to one embodiment.

[0055] Referring to FIG. 4, the first prediction model (400) is trained to predict the probability of supplying real estate (430) based on real estate transaction history (410).

[0056] According to one embodiment, the real estate transaction history (410) may be information that integrates the actual transaction price information (411) and the certified copy of the land register (412) provided to the Ministry of Land, Infrastructure and Transport's actual transaction price disclosure system. The actual transaction price information (411) may include information on sales transaction history and lease transaction history. Additionally, the actual transaction price information (411) may include the address (legal district, lot number, and road name address) of the housing subject to the transaction, the complex name, the year of construction, the floor, the exclusive area, and the time of contract and the contract amount.

[0057] According to one embodiment, the processor (110) acquires real estate public price data and extracts a house in which the building and unit number of the house to be traded can be identified through floor and exclusive area information on the real estate public price data, and can determine the extracted house as the subject of analysis of the first prediction model. According to one embodiment, the processor (110) sets a predetermined period for analyzing real estate transaction history (410), extracts a house that exists at both the start and end times of analysis without being newly built or demolished within the predetermined period, and can determine the extracted house as the subject of analysis of the first prediction model (400).

[0058] For example, the first prediction model (400) may be a regression analysis model that sets the supply type (no transaction, sale, lease) as the dependent variable, sets the housing information, owner information, and market information included in the actual transaction price information (411) and the certified copy of the land register (412) as independent variables, and then performs regression analysis on the dependent variable and the independent variable to analyze the correlation between the independent variable and the dependent variable. The first prediction model (400) may be a multiple logistic regression model that predicts the probability for each of the three classes: no transaction, sale, and lease.

[0059] A processor (110) according to one embodiment may input data preprocessing of housing information, owner information, and market information included in real estate transaction history (410) into a first prediction model (400). For example, the processor (110) may take the natural logarithm of the variables included in the housing information, owner information, and market information, standardize them, or process them as dummy variables.

[0060] The processor (110) can obtain housing information, owner information, and first market information of real estate for which it intends to predict supply probability and supply price. Examples of housing information, owner information, and first market information are described later in FIG. 5.

[0061] FIG. 5 is a diagram illustrating examples of housing information, owner information, and market information according to one embodiment.

[0062] Referring to FIG. 5, housing information (510) may include individual information (511) and complex information (512). Individual information (511) may include the housing address, exclusive area, number of floors, number of rooms, number of bathrooms, and entrance structure. Complex information (512) may include the total number of households, elapsed years, number of parking spaces per household, construction company, and distance to the station.

[0063] The housing address, exclusive area, and number of floors may be extracted from real estate public price data, and the number of rooms, number of bathrooms, entrance structure, total number of households, elapsed years, number of parking spaces per household, and construction company may be extracted from complex information provided by Real Estate 114, but are not limited thereto, and may be stored in the housing information database of memory (120). The distance to the station may be obtained from a map app or a server providing other map information, but is not limited thereto.

[0064] Referring to FIG. 5, owner information (520) may include the period of ownership of the real estate, legal personality, number of owners, address classification, age, and maximum amount of debt.

[0065] The holding period of the real estate, legal personality, number of owners, address classification, and age can be extracted from the information in Section A of the land register. Additionally, the maximum amount of the secured debt can be extracted from the information in Section B of the land register. In this case, legal personality refers to whether the owner is a natural person or a legal entity. Address classification refers to whether the owner's address corresponds to the relevant area, a nearby area, or other areas. Address classification will be described in detail later in Fig. 6.

[0066] FIG. 6 is a drawing for explaining an example of address classification according to one embodiment.

[0067] Referring to FIG. 6, the address classification may be divided into the area where the owner's address is located (610), which is the area where the predicted real estate is located; the neighboring area (620), which is adjacent to the area at the administrative and legal boundary with the area (610); and other areas (630). If the owner is a corporation, the owner's address refers to the location of the corporation's head office.

[0068] Referring again to FIG. 5, the first market information (530) may include mortgage interest rates, monthly rent conversion rates, housing sales price index, housing lease price index, and changes in net population migration apartment inventory.

[0069] According to one embodiment, the processor (110) can determine the average transaction price per pyeong using the Jeonse-monthly rent conversion rate, the housing sales price index, and the housing Jeonse price index. The average transaction price per pyeong includes the average sales price per pyeong and the average rental price per pyeong. For example, in the case of a monthly rent transaction among rental transactions, the processor (110) can determine the average rental price per pyeong by converting the monthly rent into a Jeonse deposit using the Jeonse-monthly rent conversion rate. Additionally, the processor (110) can determine the sales turnover rate and the rental turnover rate from changes in the apartment inventory volume of net population migration.

[0070] Referring again to FIG. 3, in step 320, the processor (110) obtains the supply price of the real estate using the first supply probability.

[0071] According to one embodiment, the processor (110) can obtain the supply price of a real estate property by supply type by using a first supply probability, demander information, and second market information as inputs to a second prediction model. The second prediction model may be a model trained to predict the supply probability of the real estate property based on actual transaction price information and land registry information during a certain period prior to the prediction time. An example of the second prediction model is described later in FIG. 7.

[0072] FIG. 7 is a diagram illustrating an example of a second prediction model trained to predict the price of real estate according to one embodiment.

[0073] Referring to FIG. 7, a processor (110) according to one embodiment inputs the first supply probability (720), demander information (730), and second market information (740) obtained using the first prediction model (710) into the second prediction model (750), and can obtain the supply price (760) of the real estate as the output of the second prediction model (750).

[0074] For example, the second prediction model (750) may be a multiple regression analysis model that sets the supply price of real estate as the dependent variable, sets the first supply probability (720), demander information (730) and market information (740) included in the real estate transaction history as independent variables, and then performs regression analysis on the dependent variable and independent variable to analyze the correlation between the independent variable and the dependent variable.

[0075] Here, the real estate transaction history may be information that integrates actual transaction price information and certified copy of the land register provided to the Ministry of Land, Infrastructure and Transport's real transaction price disclosure system. In the case where the buyer is an individual, the real estate transaction history may include the buyer's date of birth, address at the time of the transaction, and transaction price. The buyer information (730) may be information that includes at least one of the buyer's age, address classification, legal personality, and number of buyers, and the buyer refers to the buyer in a sales transaction and the tenant in a lease transaction. Additionally, the second market information may include the mortgage interest rate or money supply at the time of the transaction.

[0076] The processor (110) can input the first supply probability (720), demander information (730), and market information (740) into the second prediction model (750) after performing data preprocessing on them. For example, the processor (110) can take the natural logarithm of the variables included in the first supply probability (720), demander information (730), and market information (740), standardize them, or treat them as dummy variables.

[0077] According to one embodiment, the processor (110) can obtain a sales supply price based on a sales probability and a lease supply price based on a lease probability. Additionally, the processor (110) can further perform the process of calculating the ratio of the sales supply price and the lease supply price, and obtaining a second supply probability by using the calculated ratio, housing information, owner information, and first market information as inputs to the first model.

[0078] FIG. 8 is a diagram illustrating an example of a method for constructing an integrated prediction model by inputting the supply price of real estate according to one embodiment into a first prediction model.

[0079] Referring to FIG. 8, a processor (110) according to one embodiment can obtain a supply price (840) of real estate by inputting a first supply probability (820) of real estate obtained using a first prediction model into a second prediction model (830), and obtain a second supply probability (820) by inputting the obtained supply price (840) of real estate back into the first prediction model (810).

[0080] FIGS. 9a to 9c are drawings illustrating an example in which a first prediction model according to one embodiment learns the correlation between independent variables included in actual transaction price information and land register information and the dependent variable, the probability of real estate supply.

[0081] Figure 9a is a diagram showing an example of the correlation between the owner's real estate holding period and the probability of real estate supply.

[0082] Referring to Figure 9a, it can be seen that the longer the holding period of real estate, the higher the probability of sale and the lower the probability of lease. Beyond a certain holding period, a locking effect may occur in which the probability of choosing to sell decreases and the probability of a lease transaction increases, but Figure 9a indicates the period before the locking effect occurs.

[0083] Figure 9b is a diagram showing an example of the correlation between owner age and the probability of real estate supply.

[0084] Referring to Figure 9b, it is shown that as the age of the owner increases, the probability of sale decreases significantly, and the probability of lease increases as the age increases.

[0085] Fig. 9c is a diagram illustrating an example of the correlation between the maximum amount of a property owner's claim and the probability of real estate supply.

[0086] Referring to Figure 9c, the probability of sale increased as the owner's maximum debt amount increased but did not show statistical significance, whereas the probability of lease decreased statistically significantly as the maximum debt amount increased.

[0087] Referring to FIGS. 9a through 9c, the supply and demand of sales and leases influence each other, and there may be variables (e.g., maximum loan amount) that affect only one of the supply and demand of either sales or leases. Therefore, a method of predicting the supply probability and price of only one type of supply without integrating sales and leases results in lower accuracy. In an embodiment of the present invention, the accuracy of the prediction of real estate supply probability and price can be improved by integrating the predictions for the supply of sales and the supply of leases.

[0088] Meanwhile, the above-described method can be written as a program executable on a computer and can be implemented on a general-purpose digital computer that operates the program using a computer-readable recording medium. In addition, the structure of the data used in the above-described method can be recorded on a computer-readable recording medium through various means. The computer-readable recording medium includes storage media such as magnetic storage media (e.g., ROM, RAM, USB, floppy disk, hard disk, etc.) and optical reading media (e.g., CD-ROM, DVD, etc.).

[0089] A person skilled in the art related to the present embodiment will understand that it may be implemented in modified forms without departing from the essential characteristics of the description above. Therefore, the disclosed methods should be considered in an illustrative rather than a restrictive sense, and the scope of rights is defined in the claims rather than the description above, and should be interpreted to include all differences within the scope of equivalence.

Claims

Claim 1 A method for predicting supply probabilities and supply prices of real estate, performed by at least one processor, comprising: inputting housing information, owner information, and first market information of the real estate into a first prediction model to obtain a first supply probability including a first sales probability that the real estate will be supplied as a sale and a first lease probability that the real estate will be supplied as a lease; inputting the first supply probability into a second prediction model to obtain a first supply predicted price including a first sales supply price based on the first sales probability and a first lease supply price based on the first lease probability; calculating a ratio of the first sales supply price and the first lease supply price; inputting the ratio into the first prediction model to obtain a second supply probability; and inputting the second supply probability into the second prediction model to obtain a second supply predicted price. Claim 2 In claim 1, the method wherein the first prediction model is a model trained to predict the probability of supply of the real estate based on actual transaction price information and certified copy of the land register information during a certain period prior to the prediction point. Claim 3 A method according to claim 1, wherein the housing information includes individual information and complex information, the individual information includes at least one of a housing address, exclusive area, number of floors, number of rooms, number of bathrooms, and entrance structure, and the complex information includes at least one of a total number of households, elapsed years, number of parking spaces per household, construction company, and distance to a station. Claim 4 In claim 1, the owner information comprises at least one of the holding period of the real estate, legal personality, number of owners, address classification, age, and maximum amount of debt. Claim 5 A method according to claim 1, wherein the first market information comprises at least one of a mortgage interest rate, an average transaction price per pyeong, a sales turnover rate, and a lease turnover rate. Claim 6 In claim 1, the step of obtaining the first supply forecast price comprises the step of inputting the first supply probability, demander information, and second market information into the second forecast model to calculate the first supply forecast price; wherein the demander information includes at least one of demander age, address classification, legal personality, and number of demanders, and the second market information includes at least one of mortgage interest rates and money supply. Claim 7 delete Claim 8 A method according to claim 1, wherein the step of obtaining the second supply probability comprises inputting the ratio, the housing information, the owner information, and the first market information into the first prediction model to obtain the second supply probability. Claim 9 A device for predicting the supply probability and supply price of real estate, comprising: a memory in which a first prediction model and a second prediction model are stored; and at least one processor; wherein the processor inputs housing information, owner information, and a first market information of the real estate into the first prediction model to obtain a first supply probability including a first sales probability that the real estate will be supplied as a sale and a first lease probability that the real estate will be supplied as a lease, inputs the first supply probability into the second prediction model to obtain a first supply prediction price including a first sales supply price based on the first sales probability and a first lease supply price based on the first lease probability, calculates the ratio of the first sales supply price and the first lease supply price, inputs the ratio into the first prediction model to obtain a second supply probability, and inputs the second supply probability into the second prediction model to obtain a second supply prediction price. Claim 10 In claim 9, the device, wherein the first prediction model is a model trained to predict the probability of supply of the said real estate based on actual transaction price information and certified copy of the land register information during a certain period prior to the prediction point. Claim 11 In claim 9, the housing information includes individual information and complex information, the individual information includes at least one of a housing address, exclusive area, number of floors, number of rooms, number of bathrooms, and entrance structure, and the complex information includes at least one of a total number of households, elapsed years, number of parking spaces per household, construction company, and distance to a station. Claim 12 In claim 9, the said owner information comprises at least one of the holding period of said real estate, legal personality, number of owners, address classification, age, and maximum amount of debt. Claim 13 In claim 9, the device wherein the first market information comprises at least one of a mortgage interest rate, an average transaction price per pyeong, a sales turnover rate, and a lease turnover rate. Claim 14 In claim 9, the processor inputs the first supply probability, demander information, and second market information into a second prediction model to obtain the first supply forecast price, wherein the demander information includes at least one of demander age, address classification, legal personality, and number of demanders, and the second market information includes at least one of mortgage interest rates and money supply. Claim 15 delete Claim 16 In claim 9, the processor inputs the ratio, the housing information, the owner information, and the first market information into the first prediction model to perform a prediction of the second supply probability. Claim 17 A computer-readable recording medium storing a program for executing the method according to claim 1 on a computer.

Images