JP2020067682A - Device, method, and program for determining loan condition - Google Patents

Abstract

To increase financing opportunities by presenting a loan condition of available loan to an enterprise which desires the loan without requiring the enterprise for troublesome procedure.SOLUTION: A device 100 can communicate with a user terminal 110 of a user enterprise via a computer network, and provides an accounting service to the user terminal 110. The device 100 stores transaction data indicating one or more transactions performed by enterprises, and stores journalization data formed by journalizing one or more transactions indicated by the transaction data. First, the device 100 acquires one or more financial indexes by using financial data stored in the device 100 (S201). Then, the device 100 evaluates one or more reliability indexes on the financial data of the enterprise (S202). Accuracy of the loan condition determined on the basis of the financial indexes is significantly affected by the reliability of the financial data. Finally, the loan condition is determined on the basis of one or more financial indexes and one or more reliability indexes (S203).SELECTED DRAWING: Figure 2

Description

  The present invention relates to an apparatus, a method and a program therefor for determining a loan condition, and more specifically, an apparatus, a method and a method for determining a loan condition of a loan available to a company that wants to receive a loan. Regarding the program.

  Usually, for business loans, companies that want to receive loans apply, and financial institutions receive credit applications and perform credit screening to find out the available loan amount.

  However, psychological thresholds such as resistance and anxiety about borrowing are generally high, and the burden of explicitly applying to financial institutions is large. In addition, complicated procedures such as preparation of documents to be submitted make the burden of application large.

  For this reason, small companies often apply only when they are in a situation where they are under pressure, and they have not been able to consider the option of financing by financing until the time when they are really in trouble.

  If a company of a certain size or larger has dedicated financial personnel, it is always necessary to keep track of the funds that can be raised by the company, but for many small and medium-sized enterprises, it is possible to raise the funds. It is not easy to grasp such a large amount of money as a management option.

  The present invention has been made in view of such problems, and an object thereof is to enable a company that wants to receive a loan to present the loan conditions of a possible loan to the company without performing complicated procedures. , To increase financing opportunities.

  In order to achieve such an object, the first aspect of the present invention is a method for determining a loan condition of a loan available to a company, which comprises using one or more of the financial data of the company. A financial index of the company, a step of evaluating one or more reliability of the financial data of the company, and a loan to the company based on the one or more financial indexes and the one or more reliability. Determining a condition, wherein the financial data is associated with the company in an accounting service provided on a server for cloud computing.

  Further, a second aspect of the present invention is characterized in that, in the first aspect, the acquisition, the evaluation, and the determination are performed on the server.

  Moreover, the 3rd aspect of this invention is a 1st or 2nd aspect WHEREIN: At least any one of the said 1 or several reliability is a part or all of the transaction data contained in the said financial data. The reliability is calculated based on the number of inputs for each input path to the accounting service.

  In a fourth aspect of the present invention, in the third aspect, the input path is manually input to a web page of the accounting service, image analysis of an image uploaded to a server providing the accounting service, and At least one of receiving from a server that provides an accounting service and a server of a cooperation destination capable of communicating on a computer network, and creating a bill for the accounting service on the server that provides the accounting service. To do.

  Further, a fifth aspect of the present invention is characterized in that, in the fourth aspect, the cooperation destination includes a financial institution.

  A sixth aspect of the present invention is the method according to any one of the first to fifth aspects, wherein at least one of the one or a plurality of reliability levels is manually input of financial data in the accounting service. It is characterized in that it is a reliability calculated based on the number of all or a part of approvals made by an account different from the account, or the number corresponding thereto.

  Further, a seventh aspect of the present invention is the method according to any one of the first to sixth aspects, wherein at least one of the one or a plurality of reliabilities is a transaction input with a voucher in the accounting service. The reliability is calculated based on a part or all of the numbers or a number corresponding thereto.

  An eighth aspect of the present invention is characterized in that, in the seventh aspect, the voucher is a bill.

  Further, a ninth aspect of the present invention is the method according to any one of the first to eighth aspects, wherein at least one of the one or more reliability levels is added to the financial data in the accounting service. The reliability is calculated based on the number of some or all of the corrections or the number corresponding thereto.

  Further, a tenth aspect of the present invention is the method according to any one of the first to ninth aspects, wherein the determination is based on the one or more financial indicators and the one or more reliability, and a default of the company. It is characterized by including a step of calculating a rate and a step of determining a financing condition according to the default rate.

  An eleventh aspect of the present invention is characterized in that, in the tenth aspect, the default rate is calculated using a prediction model by regression analysis or machine learning.

  Further, a twelfth aspect of the present invention is the method according to any one of the first to ninth aspects, wherein the determination is a step of calculating a default rate of the company based on the one or more financial indicators, It is characterized by including a step of calculating a prediction error of the default rate of the company based on one or a plurality of reliability, and a step of determining a financing condition according to the default rate and the prediction error.

  Further, a thirteenth aspect of the present invention is characterized in that, in the twelfth aspect, the determination determines a borrowable amount according to the default rate and an interest rate according to the prediction error.

  A fourteenth aspect of the present invention is a program for causing a computer to execute a method for determining a loan condition of a loan available to a company, wherein the method stores financial data of the company. Based on the one or more financial indicators and the one or more credibility, the step of obtaining one or more financial indicators using, the step of evaluating one or more credibility with respect to the financial data of the company, Determining the loan conditions for the company, wherein the financial data is linked to the company in an accounting service provided on a server for cloud computing.

  A fifteenth aspect of the present invention is, in the first aspect, an apparatus for determining a loan condition of a loan available to a company, wherein one or a plurality of financial conditions are calculated by using the financial data of the company. Obtaining an index, evaluating one or more reliability of the financial data of the company, determining a loan condition for the company based on the one or more financial indexes and the one or more reliability, and The financial data is linked to the company in an accounting service provided on a server for cloud computing.

  According to one aspect of the present invention, by using one or more financial indicators based on the financial data of the target company together with one or more reliability of the financial data, the relevant company can be operated without complicated procedures. It is possible to determine the loan terms of possible loans to companies.

It is a figure which shows the apparatus for determining the loan conditions concerning the 1st Embodiment of this invention. It is a figure which shows the flow of the determination method of the loan conditions concerning the 1st Embodiment of this invention.

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

(First embodiment)
FIG. 1 shows an apparatus for determining a loan condition according to the first embodiment of the present invention. The device 100 can communicate with a user terminal 110 of a user company via a computer network such as the Internet, and provides an accounting service to the user terminal 110. The device 100 stores transaction data representing one or a plurality of transactions conducted by a company, and also stores journal data that journals one or a plurality of transactions represented by the transaction data.

  In the present specification, “financial data” is used as a concept including transaction data and journal data, and further includes trial balance data and financial statement data that can be created by aggregating the journal data. Here, the financial statement data includes at least one of balance sheet data and income statement data.

  The device 100 includes a communication unit 101 such as a communication interface, a processing unit 102 such as a processor and a CPU, and a storage unit 103 including a storage device such as a memory and a hard disk or a storage medium, and stores programs for performing each process. It can be configured by executing and may include one or more devices or servers. The server can be a server for cloud computing, and can be one or more instances on a public or private cloud. The program may include one or a plurality of programs, and may be recorded in a computer-readable storage medium to be a non-transitory program product. The storage of data in the device 100 may be a storage medium or a storage device such as a database 104 accessible from the device 100, in addition to the storage in the storage unit 103.

  In order to enable a company that wants to receive a loan to present the loan conditions of a possible loan to the company without performing complicated procedures, in the present embodiment, an accounting service is provided in the device 100 itself that determines the loan condition. Financial data that is provided and thereby stored in the device 100 in association with the company is used. As a result, the loan conditions can be presented without requiring the user company to perform any special procedure. Since financial data can be analyzed in real time as needed, loan conditions can also be presented in real time.

  The device 100 first acquires one or a plurality of financial indicators using the financial data (S201). Examples of financial indicators include equity ratio, current ratio, sales growth rate, and receivable turnover period. The financial indicator can be calculated using one or more components of the financial data of the target company (hereinafter also referred to as “financial data component”), or the component of the financial data of the target company itself can be calculated. Can be Examples of the latter include cash balance, loan balance, accounts receivable, sales amount, capital, and the like.

  Next, the apparatus 100 evaluates one or a plurality of reliability levels regarding the financial data of the company (S202). Since the financial index is based on the financial data, the accuracy of the loan condition determined based on the financial index is greatly affected by the reliability of the financial data. The reliability can be used as an index showing the reliability of a part or all of the financial data of the company. It can be the confidence of some or all of the financial data component or components underlying the indicator.

  For example, when cash or cash is used as a financial index, the reliability of transaction data representing a transaction of depositing or withdrawing from a bank account becomes a problem. Therefore, as will be described later, it is possible to evaluate the reliability based on the input path of the transaction data. Further, when sales, sales, sales growth rate or sales receivable turnover period are used as financial indicators, reliability is low unless the bill for each sales is sent to the other party. As a premise, reliability is low unless an invoice is prepared. Therefore, for each sales, it is conceivable to evaluate the reliability based on whether or not it is stored in the device 100 that the bill corresponding to the sales has been created and / or sent.

Then, the loan condition is determined based on the one or more financial indicators and the one or more reliability (S203). For example, as an example, the default rate is p _d , the logit of the default rate p _d is logit (p _d ), the financial index is x _i (i is an integer from 1 to m), and the reliability is x ′ _j (j is 1 to 1). n is an integer), one or more financial indicators x _i , one or more reliability x ′ _j are explanatory variables, and the default rate p _d is an objective variable to construct a prediction model represented by the following equation.

Here, α, β _i , and β ′ _j are parameters determined by the model construction and are stored in the device 100. Then, the loan condition including the borrowable amount according to the predicted default rate p _d is determined. As a specific example, the borrowable amount can be associated with each other according to the value of the default rate p _d or the value range, and the association can be stored in the device 100. In this specification, the term "default rate" is defined as "default" when a company that receives a loan falls into a financial condition of a certain standard or when the company is overdue to repay its debt. Probability is calculated. For example, defaults include deposit balances, equity ratios, etc. falling below a certain level, and repayment being overdue by one month or more or three months or more.

As another example, the predicted default rate is p _pred , the actual default rate is p _act , the difference between the predicted default rate p _pred and the actual default rate p _act is Δp, the logit of the difference Δp is logit (Δp), and the reliability is x. _{'j (j} is an integer from 1 to n) and one or more reliability x' _j the explanatory variables, to build a prediction model represented by the following formula difference Δp as objective variables.

Here, α and β ′ _j are parameters determined by the model construction and are stored in the apparatus 100. Prediction is performed by making it possible to predict the difference between the prediction default rate p _pred predicted by the above-described prediction model, the model in which the reliability is excluded from the explanatory variables from the above prediction model, or another prediction model, and the actual default rate p _act. A loan condition can be determined according to the default rate p _pred and the prediction error Δp. More specifically, as an example, the _borrowable amount can be determined according to the predicted default rate p _pred , and the interest rate can be determined according to the prediction error Δp.

  Here, a prediction model is constructed by regression analysis, the prediction model is stored in the storage unit 103 of the device 100 or a storage medium or a storage device accessible from the device 100, and the prediction model is used at the time of prediction. The model is not limited to the one based on the regression analysis, and as an example, a learned model generated by machine learning is used as a prediction model to make a loan condition determination based on one or more financial indicators and one or more reliability. It is possible to do.

  In this way, by using one or more financial indicators based on the financial data of the target company together with one or more reliability regarding the financial data, it is possible for the company without causing the company to perform complicated procedures. Loan conditions for various loans can be determined. If necessary, loan condition display data for displaying the determined loan condition may be transmitted to the user terminal 110 and displayed on the display screen of the user terminal 110.

  In the above description, it is assumed that each of the above processes is performed by a server for cloud computing that provides an accounting service. It is conceivable that financial data may be sent to a server other than the server managed by the company that manages the accounting service to determine the loan conditions at the destination. It is preferable to close the server managed by the company that manages the service and perform each process without increasing the risk that the financial data of the target company that wants to receive the loan is exposed to the outside.

  In addition, it may be considered that the loan approval / disapproval condition is that the reliability value used in the prediction model is equal to or larger than a predetermined threshold value. A company that does not have a certain level of trustworthiness does not judge the loan conditions because it cannot perform credit screening, and determines that the loan cannot be loaned as a loan condition, so that the reliability can be determined quantitatively in the screening related to the credit policy. It can be used as an index.

  If there is no description of “only” such as “based only on XX”, “according to only XX”, and “only in case of XX”, additional information in this specification Note that it is envisaged that also can be considered. Also, as an example, it should be noted that the description “b in case of a” does not necessarily mean “always b in case of a”, unless explicitly stated.

  In addition, as a precaution, even if some method, program, terminal, device, server, or system (hereinafter, “method etc.”) has an aspect that performs an operation different from the operation described in this specification, each of the present invention The aspect is intended for the same operation as any one of the operations described in the present specification, and the existence of an operation different from the operation described in the present specification means that the method etc. It is added that it does not fall outside the scope of the embodiment.

(Second embodiment)
In the second embodiment, details of one or more degrees of reliability regarding financial data will be described.

One of the grounds for the input path reliability, and the input path of financial data to accounting services device 100 is provided. The data received by the device 100 from the server of the accounting service that can communicate on the computer network is more objectively reliable than the data manually input by the user company on the web page of the accounting service. The data obtained from the cooperation destination includes detailed data from a financial institution, purchase data from an EC operating company, sales data from a POS cash register service providing company, and the like.

  As a specific example of the reliability, the number of transactions of a part or all of the transactions input to the accounting service in a predetermined period with respect to the transaction data received from the server of the cooperation destination. Or a value corresponding to the ratio. Alternatively, the ratio of the number of some or all of the journals input to the transaction data received from the linked server to the number of all or some of the journals input to the accounting service in a predetermined period, or The value corresponding to the ratio can be the reliability. Further, it is possible to calculate reliability in accordance with the cooperation destination, weight each reliability, and consider it in prediction of default rate and determination of loan conditions. For example, it is conceivable that the transaction data input by the reception from the server of the financial institution is given the highest weight and is evaluated the highest. More generally, the reliability is the number of transactions of some or all of the transactions entered by using the transaction data received from the collaborating server, or some or all of the journals entered for the transaction data. It can be calculated based on the numbers or their corresponding numbers. The number corresponding to the number of journals includes the journal amount, and so on. More generally, the reliability can be calculated based on the number of inputs of some or all of the transaction data to the accounting service for each input path or the number corresponding thereto.

  Further, as an input path, image analysis of an image uploaded to the device 100 that provides an accounting service can be mentioned. When the transaction data is generated from the analysis of the voucher image, the reliability can be highly evaluated as compared to the case where the transaction data is manually input.

  In addition, as an input path, there can be mentioned creation of a bill in the accounting service on the device 100 that provides the accounting service. The bill data of the bill is stored in the device 100 as transaction data.

One of the reasons for approval / correction reliability is the number of approvals for financial data. When transaction data is manually input, it is more reliable when it is approved by an account different from the account that manually input the transaction data, as compared to when it is not approved. Therefore, the ratio of the number of transactions of some or all of the approved transactions to the number of transactions of some or all of the transactions input or manually input to the accounting service in the predetermined period or the value corresponding to the ratio may be set. it can. Or, the ratio of the number of journals entered to some or all of the approved transaction data to some or all of the journals entered or manually entered into the accounting service in a predetermined period, or the corresponding ratio The value to be set can be the reliability. Alternatively, the ratio of some or all of the approved journals to some or all of the journals entered or manually entered into the accounting service in a predetermined period, or the value corresponding to the ratio is defined as the reliability. can do. More generally, the number of transactions of some or all of the transactions for which the reliability is approved, the number of journals entered for some or all of the approved transactions, or the number of all or some of the approved journals. Alternatively, it can be calculated based on the numbers corresponding to these.

  The manually entered transaction data may be approved according to a predetermined automatic approval rule. Unless the automatic approval rule is tampered with, it is conceivable that the transaction data that has been automatically approved will be highly evaluated in reliability as compared with the unapproved transaction data.

  Alternatively, if the transaction or journal data is modified, it is less reliable than if it were not. Therefore, the ratio of the number of transactions of some or all of the transactions that have been corrected to the number of transactions of some or all of the transactions that were input or manually input to the accounting service in the prescribed period, or the value corresponding to this, is used as the Can be Or, the ratio of the number of journals entered to some or all of the transaction data, which has been corrected, to the number of some or all of the journals entered or manually entered in the accounting service in a predetermined period, or The value corresponding to the ratio can be the reliability. In addition, the reliability shall be the ratio of the number of some or all of the journals that have been corrected to the number of all or some of the journals input to the accounting service in the prescribed period, or the value corresponding to this. You can More generally, the confidence level is defined as the number of transactions for some or all of the transactions that have been modified, the number of journals entered for some or all of the transactions that have been modified, or the number of journals that have been modified. It can be calculated based on the number of some or all of the journals or the number corresponding to these. In this example, the larger the number, the lower the reliability.

One of the grounds for the voucher reliability is the presence or absence of voucher for financial data. If transaction data is manually input, or if vouchers such as receipts, receipts, and invoices are also attached or input, it is more reliable than without vouchers. For example, considering the case where the invoice is a voucher, it can be said that the reliability is higher when the invoice is sent to the billing party as described above. Therefore, it corresponds to the ratio of the number of transactions of some or all manually entered or manually entered with the voucher for the number of transactions of some or all manually entered or manually entered into the accounting service in the prescribed period, or the relevant ratio. The value to be set can be the reliability. Or, it corresponds to the ratio of the number of journals entered for some or all of the transactions with voucher for some or all of the journals entered or manually entered in the accounting service in a predetermined period, or the corresponding ratio. The value can be the reliability. More generally, the reliability is the number of transactions of part or all of the transactions manually or manually input with a voucher, or the number of journals input to some or all of the transactions of voucher or a number corresponding to these. Can be calculated based on

  In an example in which the reliability of sales financial data is evaluated based on the fact that the invoice accompanies the voucher, if both of the transactions are users of the accounting service provided by the device 100, the billing is performed at the billing destination. It is possible to reliably confirm that the invoice has been sent because the transaction represented by the invoice is registered, and that the invoice is opened or viewed. It is also possible to send the bill data of the bill via the apparatus 100. Further, the bill can be created in the accounting service provided by the device 100, and the bill data of the bill can be downloaded from the device 100 and can be received. By storing in the apparatus 100 that the other party has downloaded, even if the other party of the invoice is a non-user of the accounting service, the invoice is sent to the other party and is opened or browsed. You can check that. It may be possible to evaluate the invoice as having been sent based on the fact that the invoice was created within the accounting service and a link for download was generated. In particular, when an invoice to a counterparty with a record of past deposits is opened or viewed, or when the transaction represented by the invoice is registered, compared to a counterparty without a past deposit record. The reliability of sales based on the invoice or financial data including the sales can be highly evaluated.

Transaction detail data If the entered journal data is accompanied by transaction detail data related to transaction details such as business partner, expected settlement date, department, sub-subject, etc., it can be evaluated as highly accurate input and is highly reliable. Is high. Therefore, trust the ratio of the number of some or all of the journals with transaction detail data or the value corresponding to the ratio to the number of all or some of the journals entered or manually entered into the accounting service in a predetermined period. It can be degree. More generally, the degree of reliability can be calculated based on the number of some or all of the journals input or manually input with transaction detail data, or the number corresponding to these.

(Third Embodiment)
In the first and second embodiments, description has been made assuming that the loan condition is determined using one or more financial indicators and one or more reliability, but in the third embodiment, other than financial indicators. Incorporate the index of into the prediction model.

  For example, companies with the same industry type and the same sales scale, or companies with the same industry type and the same sales scale are defined as similar companies, and a model for determining loan conditions is defined for each category of similar companies to which the target company belongs. You can choose. Further, it is possible to define a model of loan condition determination for each category of similar companies to which the target company belongs, by defining companies with similar years of business history, that is, within the same business history, as similar companies.

  Alternatively, it is conceivable that the business history or a value corresponding thereto is used as an explanatory variable. Furthermore, attribute data representing the attributes of the target company such as the age of the founder and the location of the head office may be used as an explanatory variable.

100 device 101 communication unit 102 processing unit 103 storage unit 104 database 110 user terminal

Claims (15)

A method for determining the loan terms of a possible loan to a company,
Acquiring one or more financial indicators using the financial data of the company;
Evaluating one or more degrees of confidence in the financial data of the company;
Determining loan conditions for the company based on the one or more financial indicators and the one or more reliability levels,
The method of claim 1, wherein the financial data is associated with the company in an accounting service provided on a server for cloud computing.   The method of claim 1, wherein the obtaining, the evaluating, and the determining are performed on the server.   At least one of the one or a plurality of reliability levels includes a reliability level calculated based on the number of inputs to each of the accounting services for a part or all of the transaction data included in the financial data. The method according to claim 1 or 2, characterized in that:   The input path is a manual input to the accounting service web page, image analysis of an image uploaded to a server providing the accounting service, and a cooperation destination capable of communicating with the server providing the accounting service on a computer network. The method of claim 3, comprising receiving from a server and / or billing the accounting service on a server that provides the accounting service.   The method according to claim 4, wherein the partner includes a financial institution.   At least one of the one or more reliability levels is based on a part or all of the approvals by an account different from the account that manually inputs the financial data in the accounting service, or a corresponding number. Method according to any of claims 1 to 5, characterized in that it comprises a calculated reliability.   At least one of the one or a plurality of credibility levels includes a credibility level calculated based on a part or all of the transactions input with voucher in the accounting service or a number corresponding thereto. The method according to any one of claims 1 to 6, characterized in that:   8. The method of claim 7, wherein the voucher is a bill.   At least one of the one or more reliability is a reliability calculated based on the number of some or all of the corrections made to the financial data in the accounting service or the number corresponding thereto. 9. A method according to any of claims 1 to 8, characterized in that it comprises: The determination is
Calculating a default rate of the company based on the one or more financial indicators and the one or more reliability levels;
10. The method according to claim 1, further comprising: determining a loan condition according to the default rate.   The method according to claim 10, wherein the calculation of the default rate is performed using a prediction model by regression analysis or machine learning. The determination is
Calculating a default rate of the company based on the one or more financial indicators;
Calculating a prediction error of the default rate of the company based on the one or more reliability levels;
The method according to any one of claims 1 to 9, further comprising a step of determining a loan condition according to the default rate and the prediction error.   13. The method according to claim 12, wherein the determination determines a borrowable amount according to the default rate, and determines an interest rate according to the prediction error. A program for causing a computer to execute a method for determining a loan condition of a loan available to a company, the method comprising:
Acquiring one or more financial indicators using the financial data of the company;
Evaluating one or more degrees of confidence in the financial data of the company;
Determining loan conditions for the company based on the one or more financial indicators and the one or more reliability levels,
The program wherein the financial data is linked to the company in an accounting service provided on a server for cloud computing. A device for determining loan conditions for loans available to companies,
Obtain one or more financial indicators using the financial data of the company,
Assessing one or more degrees of confidence in the financial data of the company,
Determining loan conditions for the company based on the one or more financial indicators and the one or more reliability levels,
The apparatus wherein the financial data is linked to the company in an accounting service provided on a server for cloud computing.

Images