KR102628559B1 - Method and device for providing real estate mortgage loan automatic screening platform - Google Patents

Abstract

According to an embodiment of the present invention, a method of providing an automatic real estate mortgage loan screening platform performed by a server includes the steps of (a) collecting and processing real estate-related information into preset categories; (b) receiving an input for designating an examination item from a user terminal, analyzing prices related to the examination item, and providing price analysis information to the user terminal; (c) analyzing risks for collateral loans related to the reviewed items and providing risk analysis information to the user terminal; and (d) calculating the appropriate market price and loanable amount of the item to be reviewed based on the market price analysis information and risk analysis information and providing it to the user terminal, wherein the market price analysis information and risk analysis information are included in the review. It includes visualized graphs and comprehensive analysis reports based on at least one of the following: region, area, or time series related to the product.

Description

Method and device for providing automatic screening platform for real estate mortgage loans {METHOD AND DEVICE FOR PROVIDING REAL ESTATE MORTGAGE LOAN AUTOMATIC SCREENING PLATFORM}

The present invention relates to a method and device for providing an automatic real estate mortgage loan screening platform performed by a server.

From the past, real estate has accounted for most of the household economy. Accordingly, the demand for capital loans using real estate as collateral has increased day by day, and the home mortgage loan market has also reached an enormous size.

Even though most of the loan amount at financial institutions consists of collateral loans, the real estate collateral loan process is carried out manually, step by step, and usually takes more than four times more time than general financial loans.

In addition, according to these offline systems, there is a high possibility that people's subjective judgments will be involved, and problems of financial information asymmetry between loan applicants and financial institutions often arise. In addition, it is inconvenient for loan applicants to visit branches multiple times, and it also requires a large investment of money and time from the financial institution's perspective.

Meanwhile, as the economic downturn continues, loan demand increases and real estate market prices show a downward trend, making mortgage loan risk management by financial institutions more important.

In response to these issues, along with the expansion of online banking, financial institutions have recently been increasing their investments in automated systems to universalize digital finance and are expanding non-face-to-face loan services. However, the enormous amount of data on real estate is difficult to control because it is not uniform and has different standards, and because it is accompanied by systematic management and analysis, advanced technology related to this is required.

The present invention systematically collects and processes real estate-related information, and based on this, analyzes the market price and mortgage loan risk of the items under review in various ways and provides them to the user terminal, thereby providing accuracy and convenience in understanding the review information of the items under review. The purpose is to In addition, the purpose is to provide an automated mortgage loan screening system by extracting the appropriate market price and mortgage loan amount of the items to be reviewed, presenting them to the user, and recommending screening and evaluation based on previously collected data.

According to an embodiment of the present invention, a method of providing an automatic real estate mortgage loan screening platform performed by a server includes the steps of: (a) collecting and processing real estate-related information into preset categories; (b) receiving an input for designating an examination item from a user terminal, analyzing prices related to the examination item, and providing price analysis information to the user terminal; (c) analyzing risks for collateral loans related to the reviewed items and providing risk analysis information to the user terminal; and (d) calculating the appropriate market price and loanable amount of the reviewed item based on the market price analysis information and risk analysis information and providing the results to the user terminal.

According to an embodiment of the present invention, the market analysis information and risk analysis information include a visualized graph and a comprehensive analysis report based on at least one of region, area, and time series related to the examination item.

According to an embodiment of the present invention, the graph of the market analysis information and risk analysis information is composed of a set of a plurality of points with unique effective values, and when an input for the point is received from the user terminal, The effective value corresponding to the point is expressed as numerical information and provided to the user terminal.

In the method of providing an automatic real estate mortgage loan screening platform according to an embodiment of the present invention, step (a) uses machine learning to extract the appropriate market price and appropriate collateral loan amount for each real estate based on the collected real estate-related information. It includes the step of performing (machine learning), wherein the machine learning applies preset learning modeling according to the region and size of the real estate, and the real estate-related information includes real estate transaction information, and the real estate transaction information is predetermined. The preprocessing process is performed through a resampling technique.

According to an embodiment of the present invention, in the method of providing an automatic real estate mortgage loan screening platform, step (b) includes selling price information and prices between the screening item and real estate within a predetermined range in the area to which the screening item belongs. Comprising a step of comparatively analyzing change trends and providing sales price comparison information and price change rate information of the reviewed product according to the price change trend to the user terminal, wherein a predetermined range within the area to which the reviewed product belongs is an administrative district. This is set in detail or is set based on the preset radius of the screening object.

According to an embodiment of the present invention, the method of providing an automatic review platform for real estate mortgage loans includes, in step (b), analyzing the market trend and actual transaction price trend of the reviewed product during a preset period, and analyzing the market trend and actual transaction price. A step of providing trend comparison information comparing the estimated trends to the user terminal, wherein the trend comparison information includes information on the difference between the market price and the actual transaction price of the reviewed product for each transaction completed for the reviewed product and the reviewed product. Transaction statistics information on the items reviewed above is included to determine whether the current market price is appropriate.

According to an embodiment of the present invention, the method of providing an automatic real estate mortgage loan screening platform includes step (b), complex information of the complex to which the screening item belongs, and an area adjacent to the real estate within a predetermined administrative district where the screening item is located. It includes the step of providing the sales price increase rate compared to the jeonse price and the sale supply and demand ratio of the reviewed property to the user terminal, wherein the complex information includes the distribution of actual transaction prices of real estate in the complex for a preset period, composition ratio by pyeong, and pyeong. It includes at least one of market price comparison information and comparison information with nearby complexes.

According to an embodiment of the present invention, the risk analysis information includes real estate supply information, number of items for sale, number of actual transactions, market price, successful bid rate, population information, transaction turnover rate, and real estate supply information within a predetermined administrative district where the review item is located. Information on changes in the jeonse rate and transaction volume of the complex, and comparative information on the real estate balance composition and real estate price composition for each predetermined range within the area to which the above-mentioned review item belongs are included, but the predetermined range within the area to which the above-mentioned item belongs is subdivided into administrative districts. It is set or set based on the preset radius of the screening object.

In the method of providing an automatic real estate mortgage loan screening platform according to an embodiment of the present invention, in step (c), the lower limit price and average price of real estate transaction prices in a predetermined range within the area to which the screening item belongs are obtained from a preset financial institution server. and receiving upper limit price information; And based on the lower limit, average price, and upper limit price information of the actual real estate transaction price, a predetermined actual transaction price range is set, and market price forecast information showing the distribution of actual transaction prices that occurred during a preset period through the actual transaction price range is sent to the user terminal. It includes steps to provide.

According to an embodiment of the present invention, the method of providing an automatic review platform for real estate mortgage loans includes step (c) of analyzing evaluation indicators for the review items based on the risk analysis information and providing them to the user terminal. Including, the evaluation index consists of liquidity, volatility, and stability items, and the evaluation index score calculated according to a preset operation corresponding to each of the above items and the evaluation index score are visualized in a predetermined shape and displayed on the user terminal. Provided, the liquidity is applied to the auction information, listing information, transaction turnover rate, and real demand index of the reviewed product, the volatility is applied to the real estate price change rate of the reviewed product and location, and the stability is the current market price of the reviewed product. The loan amount, senior receivable amount, and desired loan amount are calculated according to the applied calculation.

According to an embodiment of the present invention, the method of providing an automatic review platform for real estate mortgage loans includes the step (d) of providing a predetermined loan information input interface and a review result input interface to the user terminal, The screening result input interface includes a score input menu corresponding to preset collateral evaluation items, and the loanable amount is automatically changed according to input from the user terminal in the loan information input interface.

According to an embodiment of the present invention, the method of providing an automatic review platform for real estate mortgage loans includes the step (d) of accumulating collateral evaluation items for the review item or real estate similar to the review item previously entered from other user terminals. Analyzing data, configuring the score based on the cumulative data analysis in the score input menu and recommending it to the user terminal, wherein real estate similar to the item to be reviewed is the area, size, and amount of the item to be reviewed. At least one of the criteria falls within a preset similarity range.

According to an embodiment of the present invention, the process of analyzing the accumulated data uses a preset machine learning model, and the machine learning model includes the accumulated data, the examination item, or market price analysis information of real estate similar to the examination item, and At least one of the risk analysis information is used as an input value, and the collateral evaluation score for the screening item is used as an output value, and the collateral evaluation score corresponding to the output value is the evaluation score entered by the user terminal through the score input menu and If it is within a preset error range, it is provided to the user terminal.

According to an embodiment of the present invention, the method of providing an automatic real estate mortgage loan review platform calculates the difference between the score calculated based on the cumulative data analysis and the evaluation score entered by the user terminal through the score input menu, , including configuring and providing the calculated difference value in the score input menu.

According to an embodiment of the present invention, a method of providing an automatic review platform for real estate mortgage loans is performed by performing a predetermined simulation to relatively evaluate the possibility of passing the review for each collateral evaluation item of the review item compared to all real estate included in the database. It includes the step of configuring and providing the relative evaluation score calculated according to the results in the score input menu.

According to an embodiment of the present invention, the method of providing an automatic review platform for real estate mortgage loans includes the step (d) of providing register information of the reviewed item to the user terminal; and restricted real rights in the register information. It includes the step of providing a restricted real rights input interface to the user terminal through which information can be selectively entered, wherein the restricted real rights information includes information on senior claims registered in the register, and is divided into valid rights and deleted rights. is provided to the user terminal, and the loanable amount is automatically changed by additionally applying the total senior bond amount calculated according to the selection input of the user terminal in the restricted real rights input interface.

According to an embodiment of the present invention, an apparatus for providing an automatic review platform for real estate mortgage loans includes a memory storing a program for performing a method for providing an automatic review platform for real estate mortgage loans and a processor for executing the program, the processor By executing the program, real estate-related information is collected and processed into preset categories, input of designation of examination items is received from the user terminal, market prices related to the examination items are analyzed, and market analysis information is sent to the user terminal. provide, analyze risks for collateral loans related to the reviewed product, provide risk analysis information to the user terminal, calculate the appropriate market price and loanable amount of the reviewed product based on the market price analysis information and risk analysis information, and Provided to the user terminal, the market analysis information and risk analysis information include a visualized graph and a comprehensive analysis report based on at least one of region, area, and time series related to the review item.

According to an embodiment of the present invention, the real estate mortgage loan automatic review platform builds a database by categorizing real estate information, and performs data processing and analysis by linking data by category, systematizing a large amount of data. It can be provided to the user.

In addition, by providing visual statistical data that analyzes market information and risk information related to real estate collateral from various aspects, it is possible to induce rational decision-making regarding collateral screening. This allows financial institutions to manage mortgage loan risks more accurately, and thus enables a departure from the existing method of calculating high interest rates for insurance purposes to avoid risk, allowing an appropriate interest rate to be calculated.

Therefore, an appropriate collateral loan amount can be provided to loan customers, asymmetry in financial information between institutions and individuals can be resolved, and the soundness of collateral loans can be expanded.

Meanwhile, the real estate mortgage loan automatic screening platform according to an embodiment of the present invention complements the inconsistent standards of the real estate market through a predetermined learning system and provides updated real estate rights information, etc., which changes in real time. It can enable accurate and flexible response to the market.

In this way, by providing an automated screening system for real estate mortgage loans, we can break away from the existing offline, manual process, dramatically reducing time and cost for financial institutions and providing convenience and transparency of loans to customers. You can.

Figure 1 is a structural diagram of a system for providing an automatic real estate mortgage loan screening platform according to an embodiment of the present invention.
Figure 2 is a flowchart of a method for providing an automatic real estate mortgage loan screening platform according to an embodiment of the present invention.
3 to 6 are diagrams illustrating an example in which price analysis information according to an embodiment of the present invention is provided to a user terminal.
Figures 7 to 10 are exemplary diagrams showing an example in which risk analysis information according to an embodiment of the present invention is provided to a user terminal.
Figure 11 is an example diagram showing the appropriate market price and loanable amount of an item to be reviewed according to an embodiment of the present invention and a user interface related thereto.
Figure 12 is an example diagram in which the register copy information and restricted real rights input interface of the examined object are provided according to an embodiment of the present invention.
Figure 13 is a flow chart of a process in which automatic real estate mortgage loan screening is performed according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . Additionally, when a part "includes" a certain component, this means that it may further include other components rather than excluding other components, unless specifically stated to the contrary.

In this specification, some of the operations or functions described as being performed by a terminal or device may instead be performed on a server connected to the terminal or device. Likewise, some of the operations or functions described as being performed by the server may also be performed on a terminal or device connected to the server.

The “terminal” mentioned below may be implemented as a computer or portable terminal that can connect to a server or other terminal through a network. Here, the computer is, for example, a laptop equipped with a web browser, a desktop, a laptop, a VR HMD (e.g., HTC VIVE, Oculus Rift, GearVR, DayDream, PSVR, etc.), etc. may include. Here, VR HMD is for PC (e.g. HTC VIVE, Oculus Rift, FOVE, Deepon, etc.), mobile (e.g. GearVR, DayDream, Storm Magic, Google Cardboard, etc.), and console (PSVR). Includes independently implemented Stand Alone models (e.g. Deepon, PICO, etc.). Portable terminals are, for example, wireless communication devices that ensure portability and mobility, including smart phones, tablet PCs, and wearable devices, as well as Bluetooth (BLE, Bluetooth Low Energy), NFC, RFID, and ultrasonic devices. , may include various devices equipped with communication modules such as infrared, WiFi, and LiFi. In addition, “network” refers to a connection structure that allows information exchange between nodes such as terminals and servers, including a local area network (LAN), a wide area network (WAN), and the Internet. (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth communication, infrared communication, and ultrasound. This includes, but is not limited to, communication, Visible Light Communication (VLC), LiFi, etc.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the attached drawings.

Figure 1 is a structural diagram of a system for providing an automatic review platform for real estate mortgage loans according to an embodiment of the present invention.

Referring to Figure 1, the real estate mortgage loan automatic screening platform providing system according to an embodiment of the present invention includes a server 100 that performs the overall process, a user terminal 200, and a network communication network 300 connecting them. . For example, the user terminal 200 may be a terminal of a reviewer who is the subject of loan review, or a terminal of a financial institution to which the reviewer belongs, but the scope of the user is not limited.

Figure 2 is a flowchart of a method for providing an automatic real estate mortgage loan screening platform according to an embodiment of the present invention.

Referring to FIG. 2, first, in step S210, the server 100 may collect and process real estate-related information into preset categories. Here, real estate-related information can be collected through Internet crawling, data purchase, and downloading of files containing information, and the collection method does not limit the present invention. For example, through linking with the servers of certain financial institutions and government agencies, a vast amount of real estate-related information can be collected, and an individual DB can be built for each real estate in granular units such as block number and street number. In addition, individual DBs can be classified by region, size, amount, etc. and processed into data of a preset range, configuring market price, auction, registration, actual transaction, and other items, and information in the individual DB corresponding to each item. can be extracted and saved. In other words, the server 100 can perform the task of preprocessing real estate-related information so that it can be used as appropriate data in each process, such as market price analysis, risk analysis, and loan review, which will be described later.

Looking at the process of pre-processing real estate transaction information, which is representative of real estate-related information, for example, a certain resampling technique can be used. Specifically, real estate transaction information has aperiodic characteristics due to the nature of data being generated only when an actual transaction occurs, so it is difficult to process the data by forming an ordinary periodic algorithm. Accordingly, the server 100 groups individual real estate into predetermined regional units and categorizes them by preset real estate area. Specific real estate samples that do not correspond to each unit region or area are supplemented by applying certain statistical analysis techniques to form a distribution model that can uniquely identify actual transaction information. Afterwards, through repeated cross validation, the validity and representativeness of the distribution model is secured so that it can be accurately applied to actual transactions. Additionally, the overfitting problem of the real transaction distribution model can be solved by performing a certain regression analysis process.

Meanwhile, the server 100 can perform a certain amount of machine learning to extract the appropriate market price and appropriate collateral loan amount for each real estate based on the collected real estate-related information. Generally, the appropriate real estate market price provided by financial institutions or other institutions is provided according to the size of the real estate. However, since market prices vary widely by region and property type, there is a problem that the maximum price is usually different despite the same square footage. According to one embodiment of the present invention, in order to solve this problem, the appropriate market price of individual real estate can be corrected by applying preset learning modeling according to the area and size of the real estate. For example, the actual transaction distribution model described above can be used. In addition, a learning method that makes predictions by consisting of multiple decision tree nodes, a learning method that increases predictive power by configuring multiple input variables into multidimensional vectors, a learning method that classifies input data in time series and consists of multiple transfer functions, and regression learning. Using this combined artificial neural network learning method, multiple modeling can be constructed and the most appropriate model for each individual property can be applied to extract an accurate appropriate market price. For example, if the price fluctuation market in the area where the relevant examination item is located is greatly influenced by the appropriate price set every quarter, the output value (= appropriate price) is fed back as a component of the input value and re-learned, an artificial neural network model. This can be applied.

In an additional embodiment, as real estate is managed in detailed individual databases such as units, lakes, and lot numbers, in order to effectively link register copies and ledger information of individual real estate, the server 100 is distributed across servers of various other organizations. A type of scraping can be performed that allows real estate-related information to be individually collected and managed.

In step S220, the server 100 receives an input for designating an examination item from the user terminal 200, analyzes the market price related to the examination item in various ways, and provides price analysis information to the user terminal 200. . Through the user terminal 200, the user can input bibliographic information of an examination item that is subject to examination or for which information is desired to be searched into the platform according to an embodiment of the present invention. Bibliographic information may include, for example, subdivided administrative districts at the city/city/city/county/district/eup/myeon/dong level to which the real estate belongs, number of districts, lot number, floor plan, etc., and an optional input field for viewing a copy of the register of the subject being examined is additionally provided. It can be. In addition, the server 100 can receive input from the user terminal 200, such as the personal information of the loan applicant, that is, the borrower, and the loan application product, and can additionally request the borrower's current loan status and desired loan amount in the mortgage loan review. You can receive basic information without restrictions.

Hereinafter, with reference to Figures 3 to 6, the provision of market analysis information will be described in detail.

3 to 6 are diagrams illustrating an example in which price analysis information according to an embodiment of the present invention is provided to a user terminal.

First, referring to FIG. 3, the server 100 is based on a market analysis report 31 containing a comprehensive price analysis comment of the examination item and at least one of region, area (= square footage), and time series related to the examination item. A visualized graph can be provided to the user terminal 200.

Here, the analysis report 31 may be composed by selecting analysis items that can play the most essential role in the loan review of the relevant review item among the market analysis information. Referring to Figure 3, for example, the average sales price, sales price increase rate, and jeonse price increase rate of the reviewed product and comparison information with the preset range in the area to which the reviewed product belongs, actual transaction price distribution information, average by unit and price within the complex You can see that the price information is displayed differently. That is, according to one embodiment of the present invention, the server 100 extracts key analysis items while analyzing the market price of the examination item, and automatically applies the price information corresponding to the analysis item to the preset basic phrase to provide an analysis report. (31) can be generated and provided to the user terminal 200.

As described above, market analysis information may be provided as visualized data analyzed in various ways, and the server 100 may additionally provide explanatory text 32 regarding the interpretation method or contents of such data. For example, referring to FIG. 3, when the server 100 receives a predetermined input from the user terminal 200 for a preset area in the visualized graph or determines the location of the cursor, the interpretation method and contents of the corresponding graph (32) can be provided. Therefore, even if you are a reviewer who still lacks expertise or a general user who wants to check price information, you can easily understand the significance of the price analysis information.

Additionally, the visualized graph may be composed of a set of multiple points with unique effective values (33). For example, referring to the left graph of FIG. 3, you can see that the linear graph is composed of a set of preset point units. When the server 100 receives a predetermined input from the user terminal 200 about a specific point (=point) or determines the location of the cursor, it displays in a predetermined way that the point is selected, and sends a message corresponding to the point. A valid value (33) can be provided. Here, the effective value 33 may include basic information and numerical information contained in the corresponding point in the graph. Meanwhile, in the case of a linear graph, point units are shown as examples, but depending on the type of graph, such as circular, bar, area, scatter, stock, surface, radial, or combination, unique information is contained within the graph. If it is a work area, it can be composed of points without limitation. In this way, users can understand market analysis information at a glance through visualized data and at the same time receive specific effective values (33), which in some cases can help them make more sophisticated and rational decisions. there is.

Hereinafter, an embodiment of providing price analysis information will be described with reference to FIGS. 3 to 6.

Referring to FIG. 3, the server 100 can compare and analyze sale price information between the examination item and real estate within a predetermined range within the area to which the examination item belongs and provide the sale price comparison information to the user terminal 200. . Here, the predetermined range within the area to which the examination object belongs may be set by subdividing administrative districts or may be set based on a preset radius of the examination object. In other words, the sales price information of all real estate included in each range of city/city/county/gu/village/village/dong/complex units can be compared and analyzed with the sales price information of the relevant reviewed property. In addition, the sale price information of real estate located within a predetermined range, such as 1km or 500m radius around the subject, can be compared and analyzed. For example, even if the real estate belongs to the same complex, the location may be set in a different administrative district depending on the area in which it is located, and as a result, the difference in market price may be significant, so comparative analysis based on the radius of the subject being reviewed is meaningful. You can have The above-mentioned criteria for comparison are not limited to sales price information, and can also be applied to other market analysis information and risk analysis information, which will be described later, depending on their characteristics.

Meanwhile, sales price information can be comparatively analyzed based on a preset period, and may include sales price per unit area, average price, and lease price information.

For example, comparative analysis information on sales price and sales price per area can be used as data to determine the superiority of the reviewed product in the local real estate market. In other words, it can be judged that the higher the price level in the lower regional unit compared to the upper regional unit, the superiority in market prices in the regional market is shown in relation to the items being reviewed.

In addition, the comparative analysis information of the average market price by region compares the price level of the reviewed product, the relevant complex, and the lower regional unit with the price level of the upper regional unit, thereby identifying the individuality of the reviewed product and the relevant complex and the characteristics of the real estate market at the lower regional unit. It can be used as data for

The server 100 can compare and analyze price fluctuation trends between the reviewed items and real estate in each region and provide price change ratio information of the reviewed items according to the trend to the user terminal 200. Referring to the graph on the left of Figure 4, a quadrant-shaped graph is formed based on the average price increase rate in the rising phase and the average price increasing rate in the falling phase of the upper regional market, and each corresponding to the rising rate of the lower regional market. You can see the points being organized in the graph. Among these, the points 41 corresponding to the sub-regional market to which the examination item belongs can be displayed separately. Here, the closer to the 1st quadrant, the region maintains a high price increase rate regardless of the trend, and if it is located in the 4th quadrant, it can be judged to have a high rate of increase in a strong market but weak price support in a bear market.

The server 100 may analyze the market price trend and actual transaction price trend of the reviewed product over a preset period and provide trend comparison information comparing each trend to the user terminal 200. Here, the trend comparison information may include information on the difference between the market price of the reviewed item and the actual transaction price for each transaction concluded in advance, and transaction statistics information to determine whether the current market price of the reviewed item is appropriate. For example, referring to the graph on the right side of Figure 4, the difference between the monthly actual transaction price and the market price is composed of points for a preset period and appears on the graph, and the more points corresponding to positive values, the more undervalued the current market price can be understood to be.

In addition, the analyzed market trend can provide information on the market trend of the reviewed item, and the actual transaction trend can provide reliable information on the price in that it is the actual traded amount. In addition, the trend comparison information between market price and actual transaction price can be used as data to understand the possibility of price change and price stability of the reviewed product.

The server 100 may provide the user terminal 200 with the sales price increase rate of the real estate in a predetermined administrative district where the reviewed product is located compared to the surrounding area and the sale supply/demand ratio of the reviewed product to the rental price. Referring to the graph on the left of Figure 5, it can be seen that comparative information on the market price increase rates of submarkets by town, township, dong, and area over a predetermined period is provided. For example, rising and falling periods for each submarket can be displayed in different colors, and the contrast can be changed depending on the growth rate. Here, if the growth rate of the submarket to which the product under review belongs is higher than the growth rate of other submarkets, it can be judged that the upward power is high during a price rise and low during a decline.

Referring to the graph on the right side of Figure 5, you can see an example in which the jeonse and sales supply and demand ratios are provided. When the jeonse supply and demand index on the vertical axis is greater than 100, it means that there is a lot of jeonse demand, and when the buyer advantage index on the horizontal axis is greater than 100, it means that it is a seller-dominant market. Points containing the supply and demand index information of the reviewed items by month can be configured in the graph, and the graph can be configured to become darker as time goes by, allowing users to easily understand the time series changes in the supply and demand ratio.

The server 100 can provide complex information of the complex to which the examination item belongs to the user terminal 200, and the complex information includes the actual transaction price distribution of real estate in the complex for a preset period, composition ratio by pyeong, and market price comparison by pyeong. It may include at least one of information and comparative information with nearby complexes.

Referring to FIG. 6, an example of providing comparative information with nearby complexes will be described. First, a map consisting of a predetermined range including the location of the inspected object may be provided. When receiving an input for the search radius and equilibrium range from the user terminal 200, the radius corresponding to the input is displayed on the map, and complexes included within the radius are automatically selected to provide an interface to select the complex to be compared. It may be provided to the user terminal 200. According to the input of the complex to be compared in the interface from the user terminal 200, a comparative graph of the market price and price per unit area of the complex of the examination object and the complex to be compared may be generated and provided to the user terminal 200.

An example of market price analysis information was introduced with reference to each drawing, but it is not limited to this, and is not limited to the annual increase rate of real estate prices by regional unit, average pre-sale price information by regional unit, price distribution by real estate age, local news of the location of the subject being reviewed, etc. Any analysis information that can be effective data for understanding market prices and making decisions can be included as market analysis information.

Referring again to FIG. 2 , in step S230, the server 100 may analyze risks for collateral loans related to items under review and provide risk analysis information to the user terminal 200.

Hereinafter, with reference to FIGS. 7 to 10, the provision of risk analysis information will be described in detail.

Figures 7 to 10 are exemplary diagrams showing an example in which risk analysis information according to an embodiment of the present invention is provided to a user terminal.

First, referring to FIG. 7, the server 100 is based on a risk analysis report 71 containing a comprehensive risk analysis comment of the examination object and at least one of region, area (= square footage), and time series related to the examination object. A visualized graph can be provided to the user terminal 200. Explanations related to this shall replace the content described above in the market analysis information.

According to one embodiment of the present invention, risk analysis information includes real estate supply information, number of items for sale, number of actual transactions, market price, successful bid rate, population information, transaction turnover rate, and information on the supply of real estate in a predetermined administrative district where the item for review is located. Information on changes in lease rates, transaction volumes, and comparative information on real estate area composition and real estate price composition by predetermined range within the area to which the subject to be reviewed may be included.

In relation to this, an embodiment in which risk analysis information is provided will be described with reference to the drawings. First, on the left side of FIG. 7, a graph is shown analyzing the monthly number of items for sale, number of actual transactions, and market price in equilibrium corresponding to the review items for one year. For example, if the graph shows a trend in which the sale price increases and the number of items for sale decreases, the user may determine that the item being reviewed shows a phenomenon of being locked for sale. Conversely, if the number of sales increases and maintains while the number of sales decreases, the user may determine that there is a possibility of downward adjustment of the market price.

On the right side of Figure 7, there is a graph showing changes in the lease rate and transaction volume of the complex to which the review item belongs over the past three years. Points can be configured for each quarter in the graph, and based on a predetermined input from the user terminal 200, valid values of the lease rate, sale transaction volume, lease transaction volume, and sale price for the quarter corresponding to the point may be additionally provided. there is. For example, if the graph shows a trend of increasing transaction volume, the user can predict a rise in market prices, but if the real estate market is in a boom period, the effect of freezing transaction volume due to certain regulations must be considered.

Referring to Figure 8, on the left side of Figure 8, there is a graph in which the winning bid rate of the sub-regional unit to which the item under review belongs is analyzed in time series. For example, if the graph shows a generally upward trend regarding the winning bid rate, the user can interpret that market participants are optimistic about the value of the region.

On the right side of Figure 8, there is a graph analyzing the population distribution by age group over 5 years in the area to which the examination item belongs. Through this, users can infer the characteristics of real estate demand in the region. For example, if there is a large population in their teens or 40s, it can be judged as a place with a high demand for educational facilities and medium-sized or larger flat housing. If there is a large population in their 20s or 30s, there is a preference for convenience facilities and cultural facilities. It can be judged that there is a high demand for large, small and medium-sized houses.

Referring to FIG. 9, on the left side of FIG. 9, there is a graph showing the distribution by area of real estate in the complex, nearby area, and upper area where the subject to be reviewed is included. Through this, the user can understand the degree of scarcity of the balance of the reviewed items compared to the nearby region and the upper region.

In addition, the server 100 receives the lower limit, average price, and upper limit price information of the real estate transaction price for each region to which the examination item belongs from a preset financial institution server, and based on this, sets a predetermined actual transaction price range and continues for a preset period. Market price prediction information 91 showing the distribution of the actual transaction price generated through the actual transaction price section can be provided to the user terminal 200. On the right side of Figure 9, a graph 91 related to this is shown. Through this price prediction information 91, the user can determine the direction and intensity of change in the actual transaction price related to the reviewed item. For example, if there are many transactions in the range above the average price, it can be determined that the price upward trend was dominant, and if there are many transactions in the range below the lower limit or above the upper limit, it can be determined that the real estate market is highly volatile.

Meanwhile, the server 100 may analyze a predetermined evaluation index 101 for the examination item based on the risk analysis information and provide it to the user terminal 200. Additionally, the server 100 may calculate an evaluation index score by analyzing the evaluation index 101, visualize the calculated evaluation index score in a predetermined shape, and provide it to the user terminal 200. In other words, the server 100 converts the risk analysis information into a predetermined evaluation index 101 that can be a component of the screening criteria and provides it, thereby providing a direction that allows the user to manage loan risks more objectively and quickly. can be presented.

Referring to FIG. 10, the evaluation index 101 based on risk analysis information may be composed of liquidity, volatility, and stability items. The server 100 may calculate and provide an evaluation index score according to a preset calculation corresponding to each item. For example, for liquidity, auction information such as the successful bid rate of the reviewed item, listing information, transaction turnover rate, and actual demand index are applied, volatility is applied to the reviewed item and the rate of change in real estate prices in the location of the reviewed item, and stability is applied to the current status of the reviewed item. The market price, senior bond amount, borrower's loan amount, and desired loan amount can be calculated according to the applied calculation. This evaluation index 101 may be included and provided in the overview menu within the platform according to an embodiment of the present invention, and as the evaluation index score is composed of a predetermined visual shape, the user determines the risk of loaning the reviewed item. You can understand it with your eyes.

Meanwhile, if you briefly introduce the overview menu, the most important information may be included in the review of the real estate mortgage loan. For example, since the loan amount is the most realistic factor from the perspective of an institution or individual, information related to the market price of the examined item directly related to it can be included in the overview menu. In addition, since loan-related risk management is very important, auction information including the above-mentioned evaluation index and expected winning bid price of collateral can be configured.

Next, referring to FIG. 2, in step S240, the server 100 may calculate the appropriate market price and loanable amount of the item to be reviewed based on the market analysis information and risk analysis information and provide the results to the user terminal 200. In this regard, the content to which certain machine learning is applied shall be replaced with the above-described description.

Figure 11 is an example diagram showing the appropriate market price and loanable amount of an item to be reviewed and a predetermined user interface related thereto according to an embodiment of the present invention.

Referring to FIG. 11, first, the server 100 provides the self-calculated appropriate market price 111 and the loanable amount 112 of the item to be reviewed to the user terminal 200. Additionally, a predetermined loan information input interface may be provided, and the loanable amount may be automatically changed according to the corresponding input from the user terminal 200.

The loan information input interface may include an interface regarding collateral, an interface regarding an examination agency, and an interface regarding the borrower. First, the appropriate value of the collateral may be determined according to the input of the user terminal 200 in the interface regarding the collateral. Specifically, when a collateral item is successful at an auction, the amount is repaid according to a preset ranking, so it is necessary to deduct this from the appropriate market price of the item being reviewed. For example, if the subject matter is rented, the rental deposit and the small deposit depending on the area, amount, and air defense system are recognized as the priority for repayment, so the corresponding amount should be excluded from the value as collateral. In addition, prior to entering into a security contract with the review agency, there are senior claims based on a contract concluded in advance, and based on this, there are restricted real rights or registered claims in the review item, so when the collateral is auctioned, repayment is given priority over the review agency. If there is a right to receive, the highest bond amount corresponding to the senior bond shall be excluded from the value of the collateral. In this way, the server 100 provides a deposit input interface and a senior bond amount input interface 114, etc. to the user terminal 200, receives the input, and deducts the amount corresponding to the input from the existing calculated loanable amount. The task can be performed, and the loanable amount can be automatically changed and provided to the user terminal 200 accordingly.

Meanwhile, previously, the user performing the review had to collect information on senior claims or restricted real rights through separate tasks, such as requesting a copy of the register from the borrower or accessing a separate real estate-related agency server. In this case, a considerable amount of time and effort is consumed, and depending on the type of senior claim, there are cases where it is not related to the auction of the subject being reviewed, so the fair value of the collateral may be set lower, creating a disadvantageous situation for the borrower. According to one embodiment of the present invention, in order to solve this problem, the server 100 collects the register copy information of the examined object, provides it to the user terminal 200, and uses a predetermined restricted real rights input interface 121. can be provided additionally.

Figure 12 is an example diagram in which the register copy information and restricted real rights input interface of the examined object are provided according to an embodiment of the present invention.

Referring to Figure 12, an embodiment of providing a copy of the register is shown. Users can view claims such as restricted real rights and lease rights registered for the items under review in the order set. Additionally, rights that have been expunged, i.e. deleted, may be expressed differently and provided separately from valid rights.

Separately from this, since there may be a number of restricted real rights and senior claims in some cases, the server 100 provides a summary of information on restricted real rights and senior claims and at the same time provides a restricted real rights input interface 121 that allows selection and input. can be provided. This restricted real rights input interface 121 may be configured in an area close to the register copy information, may be included in the senior claim amount input interface 114, and may be provided in the form of a pop-up window. The user can view the rights information configured in the restricted real rights input interface 121 and the maximum bond amount corresponding thereto, and select the senior claim or restricted real right to be applied to the value of the collateral. For example, by excluding deleted rights as well as rights that do not affect the auction of the reviewed item depending on their nature, such as exclusive rights or rights with limited dividend demands, it is possible to prevent them from being applied unfavorably to the borrower. there is. The server 100 may receive such user input and calculate the total senior bond amount by adding up the maximum bond amount corresponding to the selected right. The previously provided loanable amount may be automatically changed by applying the calculated total amount of senior receivables.

In other words, users can conveniently view bonds such as restricted real rights or lease rights registered in the examination items using the platform of the present invention without investing additional time and effort, and quickly adjust the loanable amount. It can be done.

According to an embodiment of the present invention, a representative example of the input interface for the examination agency is one for loan to value (LTV) compared to market price. The server 100 can basically set and provide LTV through existing senior loans and new loans, but the figures may vary depending on the nature of the financial institution. Accordingly, when the user inputs the LTV, the server 100 can receive it and automatically change the loanable amount based on the input LTV. Of course, LTV is an example of the standard applied to the loan amount, but depending on the situation, other standards such as DTI and DSR may be established and applied.

According to one embodiment of the present invention, the input interface for the borrower may include an input interface for the borrower's mortgage loan application product information, desired loan amount, real estate mortgage loan information other than this mortgage loan, and other credit loan information. In addition, the user terminal 200 can receive the borrower's credit rating, financial information, assets held, income information, capital stability, etc. from the credit-related agency server and input them into the platform. This borrower-related information can be entered directly by the user using an input interface for the borrower, or the loan application information entered by the borrower online can be received and linked and inputted on the platform.

That is, according to one embodiment of the present invention, the final loanable amount can be derived according to the input of the user terminal 200 in the loan information input interface described above. For example, the server 100 provides in advance the loanable amount based on market analysis information and risk analysis information. Afterwards, when the server 100 receives inputs regarding the LTV, total senior bond amount, and deposit from the user terminal 200, the server 100 may perform calculations corresponding thereto to calculate the final loanable amount 112. Here, the calculation may be to subtract the total amount of senior bonds and deposit from the extracted appropriate market price multiplied by LTV. The server 100 can automatically change the calculated final loanable amount and provide it to the user terminal 200.

Meanwhile, in step S240, the server 100 may provide the user terminal 200 with a screening result input interface 113 that includes a score input menu corresponding to preset collateral evaluation items. Referring to FIG. 11, for example, collateral evaluation items may be composed of stability, exchangeability, and marketability items, and a score input menu corresponding to each item may be displayed and provided in a predetermined shape. Users can view market analysis information and risk analysis information and set scores for each item based on this. In addition, the maximum bond amount, balance, repayment method, repayment period, interest rate, number of delinquencies, etc. for senior bonds accompanying the review items can be considered, or information related to the borrower, such as the borrower's credit rating, can be considered and reflected in the score.

However, by being based on data analyzed in various ways, the score can be set more transparently and clearly compared to the conventional collateral evaluation, but difficulties in subjective judgment may still exist. In this regard, according to one embodiment of the present invention, when the server 100 retains a certain level of accumulated data on the collateral evaluation items of real estate similar to the relevant examination item or the examination object previously input from other user terminals, this accumulated data is stored at a certain level. By analyzing the data and recommending the calculated score to the user terminal 200, it is possible to provide assistance in the user's reasonable evaluation of collateral. For example, as described above, the server 100 can classify individual DBs by region, size, amount, etc., and the server 100 determines the scope to which the examination item belongs and real estate within the scope. You can perform primary filtering on individual DBs. Next, secondary filtering can be performed to remove real estate without data on collateral evaluation items in the individual DB of the extracted real estate. Afterwards, the secondary filtered real estate properties are limited to a preset range by considering the area, size, amount, etc., and then similar real estate properties can be finally selected. The server 100 may derive an average value of the scores for the previously entered collateral evaluation items of the reviewed items and the selected similar real estate through a predetermined operation, and recommend this to the user terminal 100. Additionally, according to one embodiment, the server 100 may calculate the difference between the derived average value for each item and the evaluation score for each item previously entered by the user terminal 100, and provide this additionally or separately.

In a further embodiment, the server 100 may perform some machine learning to build a learning model for collateral evaluation in order to provide more sophisticated recommendations. For example, the learning model searches the DB of the examination item and real estate similar to the examination item, extracts each information used in market price analysis and risk analysis, and deductible amounts such as the total amount of senior bonds, etc. and sets them as input values. And, it may be in the form of deriving scores for collateral evaluation items as output values through a predetermined artificial neural network. In addition, existing collateral evaluation item scores that have already been entered can also be set as input values, and regression analysis can be applied in which the derived output values are again used as input values. The server 100 may provide the user terminal 200 with collateral evaluation results derived by applying input values for the examination items to the learning model constructed in this way. According to one embodiment of the present invention, the collateral evaluation score derived through machine learning can be provided only when it is within a preset error range compared to the score entered by the user in the score input menu. Therefore, it is possible to solve the overfitting problem of machine learning and prevent user confusion. Additionally, according to one embodiment, the difference between the collateral evaluation score derived through machine learning and the evaluation score entered by the user can be provided for each item to help the user make a reasonable decision.

In an additional embodiment, the server 100 compares the possibility of passing the screening for each item of the corresponding screening item based on at least one of the entire real estate in the DB, the primary filtered real estate, and the similar real estate extracted through the secondary filtering. A simulation can be performed to evaluate. The relative evaluation score calculated according to the results of this simulation may be provided to the user terminal 200 together with the recommendation score for each item or separately. Additionally, if the relative evaluation score for each item does not reach the preset minimum value, certain visual information indicating 'failure' may be additionally provided to the item. Through this, users can check the relative recommendation score as well as the absolute recommendation score calculated by analyzing the accumulated data, allowing them to make sophisticated decisions. Meanwhile, according to one embodiment, if the average value for each item of the relative evaluation score derived based on similar real estate does not reach the preset minimum value or exceeds the preset maximum value, the server 100 automatically screens the items to be reviewed. Accordingly, result information on whether the examination has passed or not can be additionally provided in one area of the examination result input interface 113.

Hereinafter, with reference to FIG. 13, automatic review of a real estate mortgage loan according to an embodiment of the present invention will be described.

Figure 13 is a flow chart of a process in which automatic real estate mortgage loan screening is performed according to an embodiment of the present invention.

First, in step S310, the user terminal 200 can select and input predetermined screening criteria. The review criteria may mean a review index consisting of an evaluation index based on the above-mentioned risk analysis information, a pre-set individual index, and a predetermined external index. Here, individual indicators may include the location, area, sales price, sales price per unit area, market price increase rate, actual transaction price increase rate, lease rate, successful bid price rate, transaction volume, supply quantity, population information, etc. Each of these individual indicators is given a default setting value corresponding to the screening item, and a process of comparison with the average value for each complex and regional unit can be performed, thereby creating a relative screening indicator that calculates statistical influence that can be used as a screening standard. It can mean. Therefore, the user can decide whether to select each individual indicator as a screening standard by considering the calculated statistical influence.

Additionally, external indicators may refer to absolute screening indicators for screening items. For example, rights relationships such as provisional seizure, restricted property rights, joint ownership, etc., individual restrictions on the subject to be reviewed, including the presence or absence of illegal buildings, etc., and legal requirements including selection of overheated speculation zones, air defenses, LTV, etc. there is. In addition, certain analysis indicators that are automatically calculated or manually input through pre-performed simulations of various scenarios related to bond collection, such as auctions and winning bids, may be included.

In step S310, the server 100 may set the final screening logic based on the screening criteria selected and input from the user terminal 200. For example, by configuring a predetermined and function or or function depending on the region, area, and amount of the examination object, screening logic can be set to determine whether the selected screening index satisfies the preset criteria simultaneously or selectively. Through this screening logic, the server 100 can derive whether or not the loan is approved for the reviewed item. In addition, the server 100 performs the task of deriving a predetermined weight applied to the loanable amount and loan interest rate by including a process in which special conditions such as provisional seizure registration are excluded depending on the stage in the examination logic for the examination item. You can. This final screening logic may be applied simultaneously to the borrower screening and collateral screening, which will be described later, or may be set and applied separately.

In step S320, the server 100 may receive input of the borrower's application product and personal information from the user terminal 200 and perform a borrower screening by querying and analyzing predetermined borrower-related information. For example, the borrower screening may be performed based on the input of the user terminal 200 in the interface for the borrower described above. In addition, as described above, the borrower-related information may include the current status of the borrower's credit rating, financial information, assets held, income information, and capital stability, and the server 100 can directly receive this from the credit-related server and query it. . The server 100 can derive loan approval and interest rate conditions based on borrower screening.

In step S330, the server 100 may receive an input for an item to be reviewed from the user terminal 200 and perform a collateral review to derive the appropriate market price and loanable amount of the item to be reviewed. The detailed description related to this will replace the content described above through steps S210 to S240. However, a weight according to the final screening logic may be applied to the collateral amount derived in S240 and finally confirmed.

In step S340, the server 100 may query the base interest rate for the borrower's application product and derive the final loan interest rate by applying the weight calculated according to the final screening logic within the borrower screening and collateral screening.

In step S350, the server 100 may provide the user terminal 200 with the loan approval status derived from the borrower screening, the available collateral amount derived from the collateral screening, and the final loan interest rate derived from the collateral screening.

In this way, as the loan screening results are automatically provided by the server 100, the inefficiencies and inconveniences of the existing manual real estate mortgage loan are resolved, and cost and time savings and efficient risk management are provided to the screening agency. , borrowers can be provided with transparency and accuracy in the loan review process.

In an additional embodiment, the server 100 identifies a product optimized for the borrower among the loan products within the relevant screening institution (=financial institution) based on the results of the automatic screening, automatically configures the product, and provides it to the user terminal 200. can do. In this case, the products comprised are not limited to real estate mortgage loan products and may also include other financial products. In addition, in an additional embodiment, after a collateral loan for the relevant screening item has been made, if the loan has been repaid to some extent, the server 100 may set a lower interest rate, but satisfy the remaining repayment amount of the loan for the screening item. New loan products available can be guided to the user terminal 200. Additionally, if the server 100 determines that the loan repayment for the subject being reviewed is being performed normally, it may recommend to the user terminal 200 another financial product with a higher limit suitable for the borrower. Through this, users can provide borrowers with information about loan products suitable for their circumstances, thereby increasing the credit rating of financial institutions, generating additional profits, and providing borrowers with safer repayments and opportunities for additional loans. You can.

The apparatus for providing an automatic review platform for real estate mortgage loans according to an embodiment of the present invention may be configured to include a memory storing a program (or application) for performing a method for providing an automatic review platform for real estate mortgage loans and a processor for executing the above program. there is.

One embodiment of the present invention may also be implemented in the form of a recording medium containing instructions executable by a computer, such as program modules executed by a computer. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include all computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

Although the methods and systems of the present invention have been described with respect to specific embodiments, some or all of their components or operations may be implemented using a computer system having a general-purpose hardware architecture.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

100: server 200: user terminal

Claims (16)

In a method of providing an automatic real estate mortgage loan screening platform performed by a server,
(a) collecting and processing real estate-related information into preset categories;
(b) receiving an input for designating an examination item from a user terminal, analyzing prices related to the examination item, and providing price analysis information to the user terminal;
(c) analyzing risks for collateral loans related to the reviewed items and providing risk analysis information to the user terminal; and
(d) calculating the appropriate market price and loanable amount of the reviewed item based on the market analysis information and risk analysis information and providing the appropriate market price and loanable amount to the user terminal;
Including,
The market analysis information and risk analysis information include visualized graphs and comprehensive analysis reports based on at least one of region, area, and time series related to the review item,
In step (a),
Performing machine learning to extract appropriate market prices and appropriate collateral loan amounts for each real estate based on the collected real estate-related information; Including,
The machine learning applies preset learning modeling depending on the area and size of the real estate,
The real estate-related information includes real estate transaction information, and the real estate transaction information is preprocessed through a predetermined resampling technique,
In the pre-processing process, each real estate is grouped into categories according to preset regions and areas, and real estate not included in the category is supplemented into each category through preset statistical analysis techniques, so that the actual transaction distribution shows the characteristics of actual transaction information according to each category. forming a model,
How to provide an automatic review platform for real estate mortgage loans. According to clause 1,
The graph of the market analysis information and risk analysis information is composed of a set of multiple points with unique effective values,
When receiving an input for the point from the user terminal, the effective value corresponding to the point is expressed as numerical information and provided to the user terminal,
How to provide an automatic review platform for real estate mortgage loans. delete According to clause 1,
In step (b),
Compare and analyze sales price information and price fluctuation trends between the above-mentioned examination items and real estate within a predetermined range within the area to which the above-mentioned examination items belong, and obtain sales price comparison information and price change ratio information of the above-mentioned examination items according to the price fluctuation trends. Including providing to the user terminal,
The predetermined range within the area to which the examination object belongs is set by subdividing administrative districts or is set based on the preset radius of the examination object,
How to provide an automatic review platform for real estate mortgage loans. According to clause 1,
In step (b),
Analyzing the market trend and actual transaction price trend of the reviewed item during a preset period, and providing trend comparison information comparing the market price trend and the actual transaction price trend to the user terminal;
The trend comparison information includes information on the difference between the market price and the actual transaction price of the reviewed product for each transaction completed for the reviewed product, and transaction statistics information for the reviewed product to determine whether the current market price of the reviewed product is appropriate. person,
How to provide an automatic review platform for real estate mortgage loans. According to clause 1,
In step (b),
Providing complex information of the complex to which the examination object belongs, the sales price increase rate compared to the surrounding area of real estate in a predetermined administrative district where the examination object is located, and the sales supply and demand ratio of the examination object to lease to the user terminal; Including; ,
The complex information includes at least one of the actual transaction price distribution of real estate in the complex during a preset period, composition ratio by pyeong, market price comparison information by pyeong, and comparative information with nearby complexes,
How to provide an automatic review platform for real estate mortgage loans. According to clause 1,
The risk analysis information includes real estate supply information, number of properties for sale, number of actual transactions, market price, successful bid rate, population information, transaction turnover rate, lease rate of the complex to which the review item belongs, transaction volume change information, and Comparative information on the real estate equilibrium composition and real estate price composition by predetermined range within the area to which the above-mentioned examination item belongs is included,
The predetermined range within the area to which the examination object belongs is set by subdividing administrative districts or is set based on the preset radius of the examination object,
How to provide an automatic review platform for real estate mortgage loans. According to clause 1,
In step (c),
Receiving, from a preset financial institution server, information on the lowest price, average price, and highest price of actual real estate transaction prices within a predetermined range within the area to which the reviewed item belongs; and
Based on the lower limit, average price, and upper limit price information of the actual real estate transaction price, a predetermined actual transaction price range is set, and market price forecast information showing the distribution of actual transaction prices that occurred during a preset period through the actual transaction price range is provided to the user terminal. steps;
Including,
How to provide an automatic review platform for real estate mortgage loans. According to clause 1,
In step (c),
Analyzing evaluation indicators for the screening item based on the risk analysis information and providing the evaluation index to the user terminal;
The evaluation index consists of liquidity, volatility, and stability items, and the evaluation index score calculated according to a preset operation corresponding to each of the above items and the evaluation index score are visualized in a predetermined shape and provided to the user terminal,
The liquidity is applied to the auction information, listing information, transaction turnover rate, and actual demand index of the reviewed product, the volatility is applied to the rate of change in real estate prices of the reviewed product and its location, and the stability is applied to the current market price and loan amount of the reviewed product. , the senior receivable amount and the desired loan amount are calculated according to the applied calculation,
How to provide an automatic review platform for real estate mortgage loans. According to clause 1,
In step (d),
Including providing a predetermined loan information input interface and a screening result input interface to the user terminal,
The screening result input interface includes a score input menu corresponding to preset collateral evaluation items,
The loanable amount is automatically changed according to the input of the user terminal in the loan information input interface,
How to provide an automatic review platform for real estate mortgage loans. According to clause 10,
In step (d),
Analyze cumulative data on the collateral evaluation items of the reviewed item or real estate similar to the reviewed item previously entered from other user terminals, and configure the score calculated based on the cumulative data analysis in the score input menu to the user terminal. Recommended steps to include;
Real estate similar to the above-mentioned examination item is one in which at least one of the criteria of area, size, and amount of the above-mentioned examination object falls within a preset similar range,
How to provide an automatic review platform for real estate mortgage loans. According to clause 11,
The process of analyzing the accumulated data uses a preset machine learning model,
The machine learning model uses at least one of the cumulative data, market price analysis information and risk analysis information of the examination object or real estate similar to the examination object as an input value, and uses the collateral evaluation score for the examination object as an output value,
The collateral evaluation score corresponding to the output value is provided to the user terminal when the evaluation score entered by the user terminal through the score input menu is within a preset error range,
How to provide an automatic review platform for real estate mortgage loans. According to clause 11,
Calculating a difference value between a score calculated based on the analysis of the accumulated data and an evaluation score entered by the user terminal through the score input menu, and configuring and providing the calculated difference value in the score input menu; Including,
How to provide an automatic review platform for real estate mortgage loans. According to clause 11,
A step of performing a predetermined simulation to relatively evaluate the possibility of passing the screening for each collateral evaluation item of the screening object compared to all real estate included in the database, and configuring and providing the relative evaluation score calculated according to the performance results in the score input menu. ; Including,
How to provide an automatic review platform for real estate mortgage loans. According to clause 10,
In step (d),
Providing register copy information of the examination item to the user terminal; And
Providing a restricted real rights input interface to the user terminal through which restricted real rights information in the register copy information can be selected and inputted; including,
The restricted real rights information includes information on senior claims registered in the register, and is divided into valid rights and deleted rights and provided to the user terminal,
The loanable amount is automatically changed by additionally applying the total senior bond amount calculated according to the selection input of the user terminal in the restricted real rights input interface,
How to provide an automatic review platform for real estate mortgage loans. The device that provides the automatic review platform for real estate mortgage loans is,
A memory storing a program for performing a method of providing an automatic real estate mortgage loan screening platform; and
It includes a processor for executing the program,
The processor collects and processes real estate-related information into preset categories by executing the program,
Receiving an input of designation of an examination item from a user terminal, analyzing the market price related to the examination item, and providing price analysis information to the user terminal,
Analyzing risks for collateral loans related to the reviewed items and providing risk analysis information to the user terminal,
Based on the market analysis information and risk analysis information, the appropriate market price and loanable amount of the reviewed item are calculated and provided to the user terminal,
The market analysis information and risk analysis information include visualized graphs and comprehensive analysis reports based on at least one of region, area, and time series related to the review item,
The process of collecting and processing the above real estate-related information into preset categories is,
Based on the real estate-related information collected above, machine learning is performed to extract the appropriate market price and appropriate collateral loan amount for each property,
The machine learning applies preset learning modeling depending on the area and size of the real estate,
The real estate-related information includes real estate transaction information, and the real estate transaction information is preprocessed through a predetermined resampling technique,
In the pre-processing process, each real estate is grouped into categories according to preset regions and areas, and real estate not included in the category is supplemented into each category through preset statistical analysis techniques, so that the actual transaction distribution shows the characteristics of actual transaction information according to each category. forming a model,
A device that provides an automatic review platform for real estate mortgage loans.

Images