JP2020003869A - Loan examination device - Google Patents

Abstract

To provide a technique for realizing an efficient loan examination.SOLUTION: A loan examination device has: an acceptance unit which accepts inputted examination application information and identity verification material; and an examination processing unit which executes a loan examination to a user on the basis of the examination application information and the identity verification material.SELECTED DRAWING: Figure 5

Description

  The present invention relates generally to financial technology (fintech), and more particularly to a loan review system.

  At present, financial institutions provide various financial services not only through stores but also through networks such as websites. For example, when applying for a personal loan such as a mortgage loan, the customer accesses the website of the financial institution, enters the necessary information in each input field of the application form in the prescribed format, By transmitting the image together with the image information read from the predetermined identity verification material, it is possible to apply for a loan examination.

JP 2017-146844 A

  Pre-screening or provisional screening services are provided for mortgage loan applications from such websites, and based on information such as annual income entered by the customer in the screening application, whether the desired loan amount is within the borrowable amount, Customers can know how much preferential interest rates can be offered. However, the content of the review is based on the information that the customer self-declared, and is correct, whether the customer's personal credit information is correct, whether it is related to anti-social forces ( Checks) cannot be sufficiently confirmed by financial institutions.

  In a typical loan application system, as shown in Fig. 1, there are various channels such as a web application, a tablet application, and a store counter application. In a web application or a tablet application, a customer can easily apply for a preliminary screening. it can. In the examination at the bank after the application for examination, the person in charge checks the input contents based on the submitted identification data, and examines the points based on the age, employer, length of service, annual income, desired loan amount, etc. It checks by hand whether personal credential information such as repayment of borrowings has been delayed, and whether it is related to antisocial forces. The examination result is notified to the customer after receiving confirmation from another approver. For this reason, time is required for the examination, and the response of the examination result is made several days later, and there is a possibility that the customer may leave before the contract. In addition, due to the manual work, the burden of office work for the person in charge is large.

  In view of the above problems, an object of the present invention is to provide a technology for realizing an efficient loan screening system.

In order to solve the above-described problems, one aspect of the present invention performs a loan examination for a user based on the examination application information and the personal identification data, and a receiving unit that receives input examination application information and personal identification data. And a loan examination device having an examination processing unit.
About.

  According to the present invention, an efficient loan examination system can be realized by automating not only the acceptance of a loan examination application but also the loan examination.

It is the schematic which shows the conventional loan examination process. 1 is a schematic diagram showing a loan screening system according to one embodiment of the present invention. It is a schematic diagram showing loan examination processing by one example of the present invention. FIG. 2 is a block diagram showing a hardware configuration of the loan examination device according to one embodiment of the present invention. It is a block diagram showing the functional composition of the loan examination device by one example of the present invention. 6 is a flowchart illustrating a loan examination process according to an embodiment of the present invention.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  In the following embodiment, a loan examination device that examines a loan applied through a network is disclosed. To summarize the embodiment described later, the loan examination apparatus executes a loan examination for a user based on examination application information received from the user via a network and personal identification data. More specifically, the loan examination device determines whether the examination application information is appropriate, that is, whether the input contents of the examination application information and the contents of the identification data match, Using the learned loan screening model, it is determined whether the loan is possible based on the screening application information.

  Although the following embodiments are mainly described with respect to a mortgage loan, the loan according to the present invention is not limited to this, and may be applied to various personal loans such as card loans, education loans, private car loans, and various business loans by corporations. May be applied.

  First, a loan screening system according to an embodiment of the present invention will be described with reference to FIG. FIG. 2 is a schematic diagram showing a loan screening system according to one embodiment of the present invention.

  As shown in FIG. 2, the loan examination system 10 includes a user terminal 50, a loan examination device 100, an in-line database (DB) 150, and an external inquiry device 200.

  The user terminal 50 may be, for example, any information processing device having a communication function such as a personal computer, a smartphone, and a tablet. The user terminal 50 accesses a website of the financial institution and executes a loan application via a network. I do.

  As will be described in detail below, the loan examination device 100 executes a loan examination for the applied loan by communicating with the in-line DB 150 and the external inquiry device 200 when receiving a loan examination application from the user terminal 50. .

  For example, in the specific example shown in FIG. 3, when the loan examination device 100 receives examination application information for preliminary examination and personal identification data from the user terminal 50 via a website operated by the financial institution, the loan examination apparatus 100 The validity of the examination application information is determined by identifying the contents of the description from the image information of the confirmation material and determining whether the input contents of the examination application information match the identified contents. When judging that the examination application information is appropriate, the loan examination apparatus 100 uses an artificial intelligence (AI) model that has been learned based on the examination application information and, if available, the transaction history information of the customer. Perform a preliminary review. When the main screening application is accepted after notifying the pre-screening result to the user terminal 50, the loan screening apparatus 100 transmits the main screening application information (typically, in addition to the information for the preliminary screening, The final examination result is notified to the user terminal 50 based on the external inquiry result from the external inquiry device 200, etc.).

  Although the illustrated specific example describes the loan screening device 100 that follows a two-stage screening process of a pre-screening and a main screening that are often performed on a mortgage loan, the loan screening device 100 according to the present invention is not limited to this. For example, for an unsecured loan such as a card loan, the loan applicability is determined by a one-stage examination in which the applicability judgment in the bank using the examination application information and the bank information and the external inquiry judgment are performed together. You may.

  The in-row DB 150 stores various information held by the financial institution, such as customer information and transaction history information. For example, when the loan examination device 100 requests information on the user who has applied for the loan examination, the in-line DB 150 provides the loan examination device 100 with transaction history information such as deposit / withdrawal information of the user's account and loan information. .

  The external inquiry device 200 is typically an inquiry system of a loan guarantee company, an inquiry system of a deposit insurance organization, or the like. Provide information, reunion check results, etc.

  The loan examination device 100 is typically realized by a server, and may have, for example, a hardware configuration as shown in FIG. That is, the loan examination device 100 includes a drive device 101, an auxiliary storage device 102, a memory device 103, a CPU (Central Processing Unit) 104, an interface device 105, and a communication device 106, which are interconnected via the bus B.

  Various computer programs including programs for realizing various functions and processes described later in the loan examination device 100 may be provided by a recording medium 107 such as a CD-ROM (Compact Disk-Read Only Memory). When the recording medium 107 storing the program is set in the drive device 101, the program is installed from the recording medium 107 to the auxiliary storage device 102 via the drive device 101. However, the installation of the program need not necessarily be performed by the recording medium 107, and may be downloaded from any external device via a network or the like. The auxiliary storage device 102 stores the installed program and also stores necessary files and data. The memory device 103 reads out and stores a program or data from the auxiliary storage device 102 when a program start instruction is issued. The CPU 104, which functions as a processor, executes various functions and processes of the loan examination device 100, which will be described later, according to various data such as programs stored in the memory device 103 and parameters necessary for executing the programs. The interface device 105 is used as a communication interface for connecting to a network or an external device. The communication device 106 performs various communication processes for communicating with an external device. However, the loan examination device 100 is not limited to the hardware configuration described above, and may be realized by any other appropriate hardware configuration.

  Next, a loan screening device 100 according to an embodiment of the present invention will be described with reference to FIG. FIG. 5 is a block diagram showing a functional configuration of the loan examination device according to one embodiment of the present invention.

  As shown in FIG. 5, the loan examination device 100 has a receiving unit 110 and an examination processing unit 110.

  The receiving unit 110 receives the input examination application information and the identification data. More specifically, the reception unit 110 determines whether the examination application information is valid based on the examination application information input by the user and the personal identification data provided by the user. Specifically, the reception unit 110 receives the examination application information received from the user terminal 50 via the network and the image information (for example, PDF data, JPEG data, PNG data, GIF data, etc.) of the personal identification material, and performs the examination. Judge whether the input contents entered in the application information match the contents of the identified personal identification material, and judge the validity of the examination application information.

  For example, the examination application information is provided on a website of the financial institution and has a predetermined format. For example, the customer is required to input information in blanks of the format. On the other hand, the personal identification data is a certificate issued by a predetermined type of public institution such as a driver's license or a my number card, and the layout information of the certificate is registered for each type. Typically, the layout information may indicate which area in the image of each certificate contains information such as name, address, date of birth, and the like.

  The receiving unit 110 analyzes or recognizes the image information of the personal identification material, determines the type of the submitted personal identification material, and describes each of the personal identification materials based on the registered layout information of the certificate of the type. Content can be specified. When a certificate described in an unregistered layout is submitted, the accepting unit 110 determines which part of the contents required to determine the validity of the examination application information is described in the user terminal 50. May be inquired to specify the described location.

  The examination processing unit 120 executes a loan examination for the user based on the examination application information and the identification data. More specifically, when it is determined that the examination application information is appropriate based on the personal identification data, the examination processing unit 120 executes the loan examination for the user based on the examination application information using the learned model. Specifically, when the accepting unit 110 determines that the examination application information provided from the user terminal 50 is appropriate based on the personal identification data, the examination processing unit 120 performs the examination of the loan based on the examination application information. Is executed, and it is determined whether or not the loan for the applied loan can be made, and whether or not a loan can be made for all or a part of the desired loan amount.

  The loan applicability determination can be realized by an artificial intelligence (AI) model such as a neural network or a machine learning model learned in advance based on examination cases held by the financial institution. For example, the model for mortgage loan screening may be learned by any suitable learning algorithm using learning data sampled from past mortgage cases by financial institutions. For example, when the model is configured by a neural network without limitation, information on each case of the past mortgage, for example, attribute information of the borrower (age, residence area, residence period, rent, home, Residential forms such as condominiums and houses, working styles such as self-employed, company employees and contract employees, place of employment, years of service, etc., income and asset information (annual income, existing borrowings, financial assets, real estate, etc.) Purchase price, down payment, desired borrowing amount, repayment period, etc.), collateral information (address, size, etc. of the house to be purchased) are prepared as input data for learning, and repayment results (payment, Is completed as learning output data, and the neural network uses the prepared learning data until the prediction error becomes equal to or less than a predetermined threshold. Or it may be learned by like back propagation. Alternatively, the repayment result is not limited to the two outputs of completed repayment and unpaid repayment. The repayment was completed according to the original repayment plan. The output may be finer, such as not being paid off and being unrecoverable. Alternatively, a rating or the like may be output, and the examination processing unit 120 presents a preferential interest rate corresponding to the rating to a high-rated customer, and disallows a loan or reduces a desired loan amount to a low-rated customer. May be presented. It will be easily understood by those skilled in the art that a machine learning model corresponding to such various output modes can be learned by appropriately adjusting the learning data.

  The examination processing unit 120 notifies the user terminal 50 of the examination result. For example, the examination result may indicate that financing is possible or impossible under all financing conditions such as a user's desired borrowing amount and a repayment period, or by reviewing some financing conditions, It may be that financing is possible based on the determination that financing is possible.

  In one embodiment, the examination processing unit 120 acquires transaction history information and performs a loan examination. More specifically, the examination processing unit 120 may acquire the transaction history information of the user and execute the loan examination for the user based on the examination application information and the transaction history information by using the learned model. For example, when the user has already made a transaction with the financial institution, the loan examination may be executed using the transaction history information of the user in addition to the examination application information. In this case, the trained model includes the borrower's past transaction history information (deposit / withdrawal history, borrowing history, etc.) in the learning input data in addition to the various types of information related to the past mortgage cases described above. May be done. As a result, time-series information such as the borrower's past income and expenditure patterns, trends in income and expenditure balance, and stability of income is included in the learning data, and a more accurate loan screening model can be constructed.

  In one embodiment, the examination processing unit 120 may further refer to the external inquiry apparatus 200 for a user and determine whether to execute a loan examination for the user based on the inquiry result. That is, the examination processing unit 120 can perform the loan examination in consideration of not only the determination of the lending availability in the bank, but also the personal credit information by the loan guarantee company, the rejection check result by the deposit insurance organization, and the like. This makes it possible to execute a more appropriate loan examination based on not only self-reported information from the user but also various information from an external inquiry agency.

  Next, a loan examination process according to an embodiment of the present invention will be described with reference to FIG. FIG. 6 is a flowchart showing a loan examination process according to one embodiment of the present invention. The loan examination process may be started, for example, in response to acceptance of examination application information from the user terminal 50.

  As shown in FIG. 6, in step S101, the loan examination device 100 receives examination application information from the user terminal 50 via a network.

  In step S <b> 102, the loan examination device 100 accepts personal identification data from the user terminal 50 via the network. Note that steps S101 and S102 may be performed in a different order or may be performed together.

  In step S103, the loan examination device 100 determines the validity of the examination application information based on the personal identification data. If the input contents of the examination application information match the contents of the identification data, the loan examination apparatus 100 determines that the examination application information is appropriate, and proceeds to step S104. On the other hand, if the input contents of the examination application information and the contents of the identification data do not match, the loan examination device 100 notifies the user terminal 50 of the mismatched portion and urges the user to confirm whether there is an error in the input contents. You may.

  In step S104, the loan examination device 100 executes a loan examination for the user based on the examination application information using the learned model. After the loan examination, the loan examination apparatus 100 notifies the user terminal 50 of the examination result. For example, the examination result may indicate that financing is possible or impossible under all financing conditions such as the user's desired borrowing amount and repayment period, or financing is possible or impossible by reviewing some financing conditions. It may be that.

  As described above, the embodiments of the present invention have been described in detail. However, the present invention is not limited to the specific embodiments described above, and various modifications may be made within the scope of the present invention described in the appended claims.・ Change is possible.

10 Loan Examination System 50 User Terminal 100 Loan Examination Device 200 External Inquiry Device

Claims (4)

A receiving unit for receiving the input examination application information and identification data,
An examination processing unit that executes a loan examination for a user based on the examination application information and the identification data;
Loan screening device with a.   2. The loan examination device according to claim 1, wherein the receiving unit specifies the description content of the provided identity verification material based on layout information of the identity verification material. 3.   The loan examination device according to claim 1, wherein the examination processing unit acquires transaction history information and executes a loan examination.   The loan examination device according to any one of claims 1 to 3, wherein the examination processing unit further refers to an external inquiry system for the user, and determines whether to execute a loan examination for the user based on an inquiry result.

Images