Device, system and method for diagnosing real estate purchase, and program

Abstract

To evaluate whether a user can purchase a piece of real estate which is under consideration for purchase, in a long-term field of view, from various conditions of the user, by using a learning model generated according to mechanical learning.SOLUTION: A real estate purchase diagnosis device 1 capable of freely communicating with a user's terminal device comprises: a reception part for receiving user information from the terminal device; a mechanical learning part 11e for generating a purchase difficulty evaluation model according to mechanical learning, based on learning data containing user information and purchase track records of the past; a purchase difficulty evaluation part 11c for evaluating whether a user being an evaluation object can purchase a selected piece of real estate, according to the purchase difficulty evaluation model; a generation part 11f for generating display data based on an evaluation result; and a transmission part for transmitting the display data to the terminal device.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a technique for evaluating the difficulty of purchasing real estate. [Background technology]

[0002] Traditionally, when purchasing real estate, it is common to apply for a mortgage, etc., but in addition to approving the mortgage, it is desirable to have a long-term evaluation of whether the user can purchase the property in question based on various conditions of the user.

[0003] Here, Patent Document 1 proposes a technology in which the system has at least real estate property information, valuation calculation information, and loan conditions stored in a database, and the real estate property transaction processing server includes a real estate property information search means for searching for information on real estate properties that meet the conditions, a valuation calculation means for calculating the valuation of the real estate property, a loan condition determination means for determining whether the loan conditions desired by the loan applicant satisfy the loan conditions, and a loan screening certification information issuance means for issuing loan screening certification information if the loan conditions desired satisfy any of the loan conditions. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2009-151579 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, Patent Document 1 merely determines whether the desired loan conditions satisfy the loan conditions, and does not disclose any long-term evaluation of whether the user can purchase real estate in the first place based on their various conditions.

[0006] The present invention has been made in consideration of such problems, and its purpose is to use a learning model generated by machine learning based on various conditions of the user to evaluate, from a long-term perspective, whether the user can purchase a property that the user is considering purchasing. [Means for solving the problem]

[0007] In order to solve the above problems, a real estate purchase diagnosis device according to one embodiment of the present invention is a real estate purchase diagnosis device capable of communicating with a user's terminal device, and includes a receiving unit that receives user information from the terminal device, a machine learning unit that generates a purchase difficulty assessment model through machine learning based on learning data including the user information and past purchase history, a purchase difficulty assessment unit that evaluates whether a real estate property selected by the user to be evaluated is purchaseable using the purchase difficulty assessment model, a generation unit that generates display data based on the evaluation results, and a transmission unit that transmits the display data to the terminal device.

[0008] A real estate purchase diagnosis system according to another aspect of the present invention is a real estate purchase diagnosis system comprising a user's terminal device and a real estate purchase diagnosis device, wherein the terminal device comprises a first transmission unit that transmits user information to the real estate purchase diagnosis device, a first receiving unit that receives display data from the real estate purchase diagnosis device, and a display unit that performs display based on the display data, and the real estate purchase diagnosis device comprises a second receiving unit that receives the user information from the terminal device, a machine learning unit that generates a purchase difficulty assessment model by machine learning based on learning data including the user information and past purchase history, a purchase difficulty assessment unit that evaluates whether a real estate property selected by the user to be evaluated is purchaseable using the purchase difficulty assessment model, a generation unit that generates display data based on the evaluation result, and a first transmission unit that transmits the display data to the terminal device.

[0009] A real estate purchase diagnosis method according to another aspect of the present invention is a method using a real estate purchase diagnosis device that is capable of communicating with a user's terminal device, in which a receiving unit receives user information from the terminal device, a machine learning unit generates a purchase difficulty assessment model through machine learning based on learning data including the user information and past purchase history, a purchase difficulty assessment unit evaluates whether a real estate property selected by the user to be evaluated is purchaseable using the purchase difficulty assessment model, a generation unit generates display data based on the evaluation results, and a transmission unit transmits the display data to the terminal device.

[0010] A program relating to another aspect of the present invention causes a real estate purchase diagnosis device, capable of communicating with a user's terminal device, to function as a receiving unit that receives user information from the terminal device, a machine learning unit that generates a purchase difficulty assessment model through machine learning based on learning data including the user information and past purchase history, a purchase difficulty assessment unit that uses the purchase difficulty assessment model to evaluate whether a real estate property selected by the user to be evaluated is purchaseable, a generation unit that generates display data based on the evaluation results, and a transmission unit that transmits the display data to the terminal device. Effect of the Invention

[0011] According to the present invention, there is provided a technology that uses a learning model generated by machine learning based on various conditions of a user to evaluate, from a long-term perspective, whether the user can purchase a property that the user is considering purchasing. It is possible. [Brief description of the drawings]

[0012] [Figure 1] 1 is a configuration diagram of a real estate purchase diagnosis system according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a configuration diagram of a real estate purchase diagnosis device in the system. [Diagram 3] FIG. 2 is a configuration diagram of a terminal device in the system. [Figure 4] 13 is a flowchart showing the processing steps of a real estate purchase diagnosis by the system. [Diagram 5] 13 is an example of a display screen on the terminal device side of the system. [Figure 6] 13 is an example of a display screen on the terminal device side of the system. [Figure 7] 13 is an example of a display screen on the terminal device side of the system. [Figure 8] 13 is an example of a display screen on the terminal device side of the system. [Figure 9] 13 is an example of a display screen on the terminal device side of the system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0014] FIG. 1 shows the configuration of a real estate purchase diagnosis system according to an embodiment of the present invention, and will be described.

[0015] As shown in the figure, the real estate purchase diagnosis system is configured by connecting a real estate purchase diagnosis device 1, which is made up of a server device or the like, and a user's terminal device 2 wirelessly or wired via a communication network 3 such as the Internet. As the user's terminal device 2, various devices such as a smartphone, a tablet terminal, a notebook personal computer, a desktop personal computer, etc. can be used.

[0016] In such a configuration, the user accesses a website provided by the real estate purchase diagnosis device 1 through the terminal device 2 and narrows down the real estate to be considered for purchase. Then, a request for a real estate purchase diagnosis is sent to the real estate purchase diagnosis device 1. When the real estate purchase diagnosis device 1 receives this diagnosis request, it evaluates whether the selected real estate can be purchased in the first place based on user information including the user's attribute information, etc., using an evaluation model obtained by machine learning. If it is evaluated that the purchase possibility is high, it refers to loan product information related to each company's loan product, and calculates the probability of loan approval, loan amount, etc. of the loan product based on the user information using the evaluation model obtained by machine learning.

[0017] These evaluation results are transmitted from the real estate purchase diagnosis device 1 to the user's terminal device 2 and displayed on the terminal device 2. Therefore, the user can know through the terminal device 2 whether it is reasonable to purchase the real estate selected by the user in the first place (purchase feasibility), what is the probability of obtaining a loan product, etc. during the purchase consideration process.

[0018] 2(a) to 2(d) show the configuration of a real estate purchase diagnosis device in a real estate purchase diagnosis system according to an embodiment of the present invention, and will be described.

[0019] 2(a), the real estate purchase diagnosis device 1 has a control unit 11, a communication unit I / F 12, and a storage unit 13. The control unit 11, the communication I / F 12, and the storage unit 13 are communicatively connected via a system bus. In addition to these components, the device may have an input unit such as a keyboard or a mouse, and a display unit such as a liquid crystal display for displaying various information.

[0020] The communication I / F 12 is realized by, for example, a network interface card (NIC) or the like, and is a communication interface that is connected to a communication network 3 such as the Internet by wired or wireless means and communicates with the terminal device 2 or the like. The storage unit 13 is realized by a semiconductor memory element such as a random access memory (RAM) or a flash memory, a hard disk drive (HDD), an optical disk device, or the like, and stores in advance the programs to be executed by the control unit 11. The storage unit 13 has a user information storage unit 14, a loan product information storage unit 15, a purchase difficulty evaluation storage unit 16, a loan approval evaluation storage unit 17, and a learning storage unit 18.

[0021] The user information storage unit 14 stores user information including user attribute information in association with a user ID. Here, the "user information" refers to various information inputted into the terminal device 2 when requesting a diagnosis, and more specifically, includes the following information: User's basic information (name, gender, date of birth, phone number, address, family composition, intended resident) - Information about the intended purchase (current status, property type, expected delivery date of the building, the intended owner of the property, the person taking out the mortgage, and the intended residence of the owner, etc.) Property details (property address, room number, property information web page URL, etc.) Purchase financing information (property price, renovation / remodeling costs, miscellaneous expenses, personal funds, etc.) Work information (industry, employment type, job type, number of employees, date of joining the company, previous year's salary, etc.) -Deposit information (deposit amount, etc.) Current loan information (if any, repayment status, etc.)

[0022] The loan product information storage unit 15 stores information on loan products of each company in association with a loan product ID. Specifically, it stores attribute information of loan product providing companies and detailed information on loan products (interest rates, loan conditions, etc.).

[0023] The purchase difficulty evaluation memory unit 16 stores the ID of the user to be evaluated, the evaluation result (probability), etc., linked to the purchase difficulty evaluation ID. It also stores comment information to be presented by the user corresponding to the probability. The loan approval evaluation memory unit 17 stores the ID of the user to be evaluated, the loan product ID, and the evaluation result (loan approval probability, loan amount, etc.), linked to the loan approval evaluation ID. It also stores comment information to be presented to the user corresponding to the probability. The learning memory unit 18 stores learning data used for machine learning of the evaluation model, and also stores the purchase difficulty evaluation model, loan approval evaluation model, etc. obtained by machine learning.

[0024] The control unit 11 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), etc. The control unit 11 is composed of an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Array), etc. The control unit 11 reads out and executes programs stored in the storage unit 13, thereby functioning as a transmission / reception control unit 11a, a personal credit information determination unit 11b, a purchase difficulty evaluation unit 11c, a loan approval evaluation unit 11d, a machine learning unit 11e, a generation unit 11f, and a main control unit 11g.

[0025] The transmission / reception control unit 11a functions as a receiving unit that receives user information transmitted from the terminal device 2, and as a transmitting unit that transmits evaluation results and the like to the terminal device 2. The personal credit information judgment unit 11b judges whether the user's personal credit information acquired via the transmission / reception control unit 11a satisfies a predetermined personal credit information condition. Here, the personal credit information condition is a condition for eliminating abnormal values ​​(e.g., negative information, etc.), and performs a process of filtering the user's loan application according to the condition and excluding loan applications that do not satisfy the condition. Here, the "personal credit information" includes the unsecured repayment amount, the number of consumer loans, the number of overdue payments less than 30 days, the number of overdue payments 30 days or more, the number of gray claims, the number of negative claims, the remaining unsecured repayment amount, the remaining secured repayment amount, etc.

[0026] The purchase difficulty evaluation unit 11c evaluates whether or not the user to be evaluated can purchase the selected real estate in the first place (how difficult it is). More specifically, as shown in Fig. 2(b), the purchase difficulty evaluation unit 11c is composed of a probability calculation unit 11c-1 and a comment generation unit 11c-2. The probability calculation unit 11c-1 calculates the purchase difficulty (probability of being able to purchase) based on the user information using a purchase difficulty evaluation model stored in the learning storage unit 19, and the comment generation unit 11c-2 extracts comment information corresponding to the probability from the purchase difficulty evaluation storage unit 17 and generates a comment.

[0027] The loan approval evaluation unit 11d evaluates whether or not the user to be evaluated can receive approval for a loan product when applying for a loan product to purchase real estate. More specifically, the loan approval evaluation unit 11d includes a loan approval probability calculation unit 11d-1, a loan amount calculation unit 11d-2, and a comment generation unit 11d-3, as shown in FIG. 2(c). The loan approval probability calculation unit 11d-1 calculates the loan approval probability based on user information using the loan approval evaluation model generation unit 11e-2 stored in the learning memory unit 19, the loan amount calculation unit 11d-2 calculates the loan amount based on the user information, and the comment generation unit 11d-3 extracts comment information corresponding to the loan probability from the loan approval evaluation memory unit 18 to generate a comment.

[0028] As shown in FIG. 2(d), the machine learning unit 11e includes a purchase difficulty evaluation model generation unit 11e-1 and a loan approval evaluation model generation unit 11e-2. The purchase difficulty evaluation model generation unit 11e-1 generates a purchase difficulty evaluation model by machine learning based on learning data such as user information and past purchase records for the user information. The loan approval evaluation model generation unit 11e-2 generates a loan approval evaluation model by machine learning based on learning data such as user information, personal credit information, screening financial institution, desired loan amount, and screening result. This model generation uses about 10,000 past performance data held by the company, so it is possible to generate an optimal evaluation model. Since performance data is accumulated every time a user uses the system, the machine learning unit 11e may periodically regenerate the evaluation model and update the evaluation model stored in the learning storage unit 19.

[0029] The generating unit 11f generates display data related to the evaluation result by the purchase difficulty evaluating unit 11c, the evaluation result by the loan approval evaluating unit 11d, etc. In addition, the main control unit 11g is in charge of overall control of the real estate purchase diagnosis device 1, for example, authentication of users, etc.

[0030] FIG. 3 shows the configuration of a terminal device in the real estate purchase diagnosis system according to the embodiment of the present invention, and will be described.

[0031] As shown in the figure, the terminal device 2 has a control unit 21, a communication unit 22, an operation unit 23, a display unit 24, and a storage unit 25. The units 21 to 25 are connected to each other via a bus line so as to be able to communicate with each other. The communication unit 22 is realized by, for example, a NIC or the like, and is connected to a communication network 4 such as the Internet by wire or wirelessly, and is a communication interface for communicating with the real estate purchase diagnosis device 1 and the like. The operation unit 23 is realized by a mouse, a keyboard, or the like, and accepts various operation inputs by a user. The display unit 24 is realized by a liquid crystal display or the like, and performs various displays. The operation unit 23 and the display unit 24 may be integrated into a touch panel. The storage unit 25 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, a HDD, or an optical disk device, and stores a program executed by the control unit 21. The control unit 21 is realized by a CPU, an MPU, or the like, and functions as a main control unit 21a, a display control unit 21b, and a transmission / reception control unit 21c by executing a program stored in the storage unit 25.

[0032] In this configuration, the main control unit 21a controls the entire terminal device. The display control unit 21b controls the display on the display unit 24 based on the display data related to the evaluation result etc. received by the transmission / reception control unit 21c. The transmission / reception control unit 21c functions as a transmission unit that transmits user information to the real estate purchase diagnosis device 1 and a reception unit that receives the display data etc. from the real estate purchase diagnosis device 1.

[0033] Hereinafter, with reference to the flowchart of FIG. 4, a detailed description will be given of the processing procedure of diagnosis by the real estate purchase diagnosis device according to the embodiment of the present invention.

[0034] Before entering this process, as a premise, in the machine learning unit 11e, the purchase difficulty evaluation model generation unit 11e-1 generates a purchase difficulty evaluation model by machine learning based on learning data such as user information and past purchasing history for the user information, and stores it in the purchase difficulty evaluation memory unit 16, and the loan approval evaluation model generation unit 11e-2 generates a loan approval evaluation model by machine learning based on learning data such as user information, personal credit information, screening financial institution, desired loan amount, screening results, etc., and stores it in the loan approval evaluation memory unit 17.

[0035] When this process starts, the transmission / reception control unit 11a acquires user information transmitted from the terminal device 2 (S1) and acquires personal credit information (S2). Then, the personal credit information judgment unit 11b judges whether the user's personal credit information acquired via the transmission / reception control unit 11a satisfies a predetermined personal credit information condition (S3). Here, the "personal credit information condition" is a condition for eliminating abnormal values ​​(e.g., negative information, etc.), and the user's loan application is filtered by the condition, and a process is performed to exclude loan applications that do not satisfy the condition. Here, the "personal credit information" includes the unsecured repayment amount, the number of consumer loans, the number of overdue payments of less than 30 days, the number of overdue payments of 30 days or more, the number of gray claims, the number of negative claims, the remaining unsecured repayment amount, the remaining secured repayment amount, etc.

[0036] Next, the purchase difficulty evaluation unit 11c evaluates whether the user to be evaluated can purchase the selected real estate in the first place (how difficult it is) (S4). More specifically, in the purchase difficulty evaluation unit 11c, the probability calculation unit 11c-1 calculates the purchase difficulty (probability of being able to purchase) based on the user information using the purchase difficulty evaluation model stored in the learning storage unit 19, and the comment generation unit 11c-2 extracts comment information corresponding to the probability from the purchase difficulty evaluation storage unit 17 and generates a comment.

[0037] Next, the loan approval evaluation unit 11d evaluates whether or not the user to be evaluated can receive approval for a loan product when applying for a loan product to purchase real estate (S5). More specifically, in the loan approval evaluation unit 11d, the loan approval probability calculation unit 11d-1 calculates a loan approval probability based on user information using the loan approval evaluation model generation unit 11e-2 stored in the learning memory unit 19, the loan amount calculation unit 11d-2 calculates a loan amount based on the user information, and the comment generation unit 11d-3 extracts comment information corresponding to the loan probability from the loan approval evaluation memory unit 18 to generate a comment.

[0038] In this manner, the generation unit 11f generates display data relating to the evaluation results by the purchase difficulty evaluation unit 11c and the evaluation results by the loan approval evaluation unit 11d (S6), and the transmission / reception control unit 11a functions as a transmission unit and transmits the display data to the terminal device 2 (S7). In this manner, a series of processes relating to the diagnosis is completed.

[0039] Here, the screen transition on the user's terminal device 2 side will be described in detail with reference to FIG. 5 to FIG.

[0040] In the user's terminal device 2, a screen as shown in FIG. 5 is displayed on the display unit 24. In this screen, a property can be searched for by accessing a real estate site. When the desired real estate site is selected, the screen switches to a screen as shown in FIG. 6, and a property can be searched for. When the button "Simulate payment amount" at the bottom of this search result screen is selected, a diagnosis request is made to the real estate purchase diagnosis device 1. At this stage, part of the user information is input on the terminal device 2 side, and is transmitted to the real estate purchase diagnosis device 1 side at the time of the request. The real estate purchase diagnosis device 1 calculates the estimated payment amount, the total payment amount, etc. for the selected property, and transmits it to the terminal device 2. In the terminal device 2, the estimated payment amount, the total payment amount, etc. are displayed on the screen of FIG. 7.

[0041] When the "More Details" button is selected on the screen of Fig. 7, a request is made for this service related to purchase difficulty evaluation and loan approval evaluation. At this time, an input screen is presented, prompting the user to input more detailed user information. The user information is sent from the terminal device 2 to the real estate purchase diagnosis device 1.

[0042] In the real estate purchase diagnosis device 1, a purchase difficulty evaluation, a loan approval evaluation, etc. are performed by the above-mentioned processing, and display data related to the results are transmitted to the terminal device 2. In the terminal device 2, based on this display data, a screen as shown in Fig. 8 and Fig. 9 is displayed. That is, as shown in Fig. 8, the probability related to purchase difficulty (purchase possibility) (70% in this example) is displayed at the top together with a comment for the user, and below that, an introduction of various loan products (interest rate, monthly repayment amount, total repayment amount, etc.), a loan approval probability (40% in this example), and a comment for the user are presented.

[0043] As described above, according to an embodiment of the present invention, a purchase difficulty assessment model is generated by machine learning based on user information, which is quantitative and qualitative information about the user, and past purchase history data.Based on the purchase difficulty assessment model, it is possible to calculate whether the user can purchase the real estate property selected by the user in the first place, i.e., the probability related to purchase difficulty, and present this to the user.This enables the user to explore their own ability to pay, financial burden, etc. before conducting detailed consideration.

[0044] Although the embodiment of the present invention has been described above, it goes without saying that the present invention is not limited to this embodiment and various improvements and modifications can be made without departing from the spirit and scope of the present invention.

[0045] For example, the user information is not limited to the above-mentioned information, and it is of course possible to employ various quantitative and qualitative information. [Explanation of symbols]

[0046] 1... real estate purchase diagnosis device, 2... terminal device, 3... network, 11... control unit, 11a... transmission / reception control unit, 11b... personal credit information judgment unit, 11c... purchase difficulty evaluation unit, 11c-1... probability calculation unit, 11c-2... comment generation unit, 11d... loan approval evaluation unit, 11d-1... loan approval probability calculation unit, 11d-2... loan amount calculation unit, 11d-3... comment generation unit, 11e... machine learning unit, 11e-1... purchase difficulty evaluation model generation unit, 11e-2...loan approval evaluation model generation unit, 11f...generation unit, 11g...main control unit, 12...communication I / F, 13...memory unit, 14...user information memory unit, 15...loan product information memory unit, 16...memory unit for purchase difficulty evaluation, 17...memory unit for loan approval evaluation, 18...learning memory unit, 21...control unit, 21a...main control unit, 21b...display control unit, 21c...transmission / reception control unit, 22...communication I / F, 23...operation unit, 24...display unit, 25...memory unit.

Claims

1. A real estate purchase diagnosis device that can communicate with a user's terminal device, A receiving unit that receives user information from the terminal device; A machine learning unit that generates a purchase difficulty evaluation model by machine learning based on learning data including the user information and past purchase records; a purchase difficulty evaluation unit that evaluates whether a real estate property selected by a user to be evaluated is purchaseable by using the purchase difficulty evaluation model; a generation unit that generates display data based on the evaluation result; A transmission unit that transmits the display data to the terminal device. Real estate purchase diagnostic device.

2. The machine learning unit further generates a loan approval evaluation model by machine learning based on learning data such as personal credit information, screening financial institutions, desired loan amount, and screening results, The system further includes a loan approval evaluation unit that uses the loan approval evaluation model to evaluate whether or not the user to be evaluated can be approved for a loan product when applying for a loan product to purchase real estate. The real estate purchase diagnosis device according to claim 1.

3. A real estate purchase diagnosis system comprising a user terminal device and a real estate purchase diagnosis device, The terminal device A first transmission unit that transmits user information to the real estate purchase diagnosis device; A first receiving unit that receives display data from the real estate purchase diagnosis device; A display unit that performs display based on the display data; Equipped with The real estate purchase diagnosis device includes: A second receiving unit that receives user information from the terminal device; A machine learning unit that generates a purchase difficulty evaluation model by machine learning based on learning data including the user information and past purchase records; a purchase difficulty evaluation unit that evaluates whether a real estate property selected by a user to be evaluated is purchaseable by using the purchase difficulty evaluation model; a generation unit that generates display data based on the evaluation result; A first transmission unit that transmits the display data to the terminal device. Real estate purchase diagnosis system.

4. The machine learning unit further generates a loan approval evaluation model by machine learning based on learning data such as personal credit information, screening financial institutions, desired loan amount, and screening results, The real estate purchase diagnosis device further includes a loan approval evaluation unit that uses the loan approval evaluation model to evaluate whether or not the user to be evaluated can be approved for a loan related to a loan product when applying for a loan product to purchase real estate. The real estate purchase diagnosis system according to claim 3.

5. A method for a real estate purchase diagnosis device that can communicate with a user's terminal device, comprising: A receiving unit receives user information from the terminal device, A machine learning unit generates a purchase difficulty assessment model by machine learning based on learning data including the user information and past purchase records, a purchase difficulty evaluation unit evaluates whether or not the real estate property selected by the user to be evaluated is purchaseable using the purchase difficulty evaluation model; A generation unit generates display data based on the evaluation result, A transmission unit transmits the display data to the terminal device. How to diagnose real estate purchase.

6. The machine learning unit further generates a loan approval evaluation model by machine learning based on learning data such as personal credit information, screening financial institutions, desired loan amount, and screening results, A loan approval evaluation unit evaluates, by the loan approval evaluation model, whether or not the user to be evaluated can be approved for a loan product when applying for a loan product to purchase real estate. The method for diagnosing a real estate purchase according to claim 5.

7. A real estate purchase diagnostic device that can communicate freely with the user's terminal device, a receiving unit for receiving user information from the terminal device; A machine learning unit that generates a purchase difficulty evaluation model by machine learning based on learning data including the user information and past purchase records; a purchase difficulty evaluation unit that evaluates whether or not a real estate property selected by a user to be evaluated is purchaseable using the purchase difficulty evaluation model; A generation unit that generates display data based on the evaluation result; and a transmitting unit that transmits the display data to the terminal device; program.

8. The machine learning unit further generates a loan approval evaluation model by machine learning based on learning data such as personal credit information, screening financial institutions, desired loan amount, and screening results, The loan approval evaluation model also functions as a loan approval evaluation unit that evaluates whether or not the user to be evaluated can be approved for a loan product when applying for a loan product to purchase real estate. The program according to claim 7.

Images