JP2017126351A - Information processing apparatus and information processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To output need information relating to possibility for a client to utilize a predetermined financial product or risk information relating to a bad debt risk or an arrear risk in the case where money is lent to a client, on the basis of objective data.SOLUTION: An information processing apparatus comprises a generation part 11 including an artificial intelligence function, and an output part 30 for outputting information generated by the generation part 11. By using an adoption variable generated from any one or more of attribute information of a client who utilizes a financial institute, examination information relating to the client, and transaction information of the client in the financial institute and a coefficient with respect to the adoption variable, the generation part 11 generates need information relating to possibility for a certain client to utilize a predetermined financial product or risk information relating to a bad debt risk or an arrear risk in the case where money is lent to a certain client. The adoption variable and the coefficient are determined based on result data in the past.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information processing apparatus and an information processing method having a generation unit having an artificial intelligence function.

Conventionally, the utilization of artificial intelligence functions has been attempted, and the research field has also been diversified (see Patent Document 1). On the other hand, various financial products have been provided to customers from financial institutions, and their contents are also diverse. When a financial institution provides a financial product, it is very likely that the customer may use the financial product and how much risk there is when the customer lends money. However, these decisions were made by financial institution staff themselves based on certain information.

JP-A-10-207504

The above judgment requires considerable experience, and depending on the judgment method, it may not always be based on objective data.

The present invention relates to an information processing apparatus capable of outputting needs information regarding the possibility of a customer using a predetermined financial product or risk information regarding a credit loss risk or arrears risk when money is lent to a customer based on objective data And an information processing method.

An information processing apparatus according to the present invention includes:
A generation unit having an artificial intelligence function, the adoption variable generated from any one or more of attribute information of a customer who uses a financial institution, examination information about the customer, and transaction information of the customer at the financial institution, and A generation unit that generates a need information on a possibility that a certain customer uses a predetermined financial product or a risk information on a credit loss risk or arrears risk when lending money to the certain customer by using a coefficient for the employment variable;
An output unit for outputting information generated by the generation unit;
With
The adoption variable and the coefficient are determined based on past performance data.

An information processing apparatus according to the present invention includes:
A verification unit that verifies whether or not the predetermined financial product was actually used by the customer, or whether or not the loan was actually delinquent or arrears occurred when lending money to the customer; ,
The verification result by the verification unit may be used as the past performance data regarding the need information or the risk information generated after the verification result is output.

In the information processing apparatus according to the present invention,
The generation unit may generate the needs information and the risk information.

In the information processing apparatus according to the present invention,
The generation unit may generate the adopted variable and the coefficient using the attribute information, the examination information, and the transaction information.

In the information processing apparatus according to the present invention,
The artificial intelligence function of the generation unit may generate the needs information or the risk information using different adoption variables and different coefficients for different financial products.

An information processing apparatus according to the present invention includes:
You may further provide the calculation part which calculates a profit using the borrowing amount of the said certain customer, the interest rate at the time of the said borrowing, and expense information.

In the information processing apparatus according to the present invention,
The borrowing amount and the interest rate may be determined based on the risk information.

An information processing apparatus according to the present invention includes:
You may further provide the calculation part which calculates the creditable amount with respect to the said certain customer, or the applicable interest rate with respect to the said certain customer from the said risk information produced | generated by the said production | generation part.

In the information processing apparatus according to the present invention,
The attribute information may include name identification information for collectively managing the same customer.

In the information processing apparatus according to the present invention,
The attribute information may include information about the customer's family.

In the information processing apparatus according to the present invention,
The transaction information may include deposit transaction information, loan transaction information, contract information with the financial institution, service usage information provided by the financial institution, or settlement information.

In the information processing apparatus according to the present invention,
The examination information may include information on the customer's borrowing application to the financial institution or the credit information of the customer.

In the information processing apparatus according to the present invention,
For each of a plurality of financial products provided by the financial institution, the generation unit generates the needs information or the risk information,
The output unit may output the needs information or the risk information related to each of a plurality of financial products.

In the information processing apparatus according to the present invention,
The generation unit generates the adopted variable and a coefficient for the adopted variable from any one or more of the attribute information, the examination information, and the transaction information in a plurality of financial institutions, and uses the adopted variable and the coefficient The needs information or the risk information may be generated.

In the information processing apparatus according to the present invention,
The output unit has a needs value included in the needs information equal to or greater than a needs threshold.
Or it is good also considering only the customer whose risk value contained in the said risk information is below a risk threshold as an object of output.

An information processing method according to the present invention includes:
A hiring variable generated from any one or more of attribute information of a customer who uses a financial institution, examination information about the customer, and transaction information of the customer in the financial institution by the generating unit having an artificial intelligence function, and the hiring Using a coefficient for a variable, generation information is generated by the generation unit regarding the need information regarding the possibility that the certain customer uses the predetermined financial product or the risk of credit loss or the delinquency risk when lending money to the certain customer. And
Outputting the information generated by the generator by an output unit;
With
The adoption variable and the coefficient are determined based on past performance data.

According to the present invention, the generation unit having an artificial intelligence function includes an employment variable generated from any one or more of attribute information of a customer who uses a financial institution, examination information about the customer, and transaction information in the customer's financial institution, and Using the coefficient for the recruitment variable, generates information on the needs of a certain customer's possibility of using a given financial product or risk information on the risk of credit loss or delinquency when lending money to a customer. Output by the part. Employment variables and coefficients to be used are determined based on past performance data. For this reason, needs information or risk information can be output based on objective data.

FIG. 1 is a schematic block diagram for explaining an outline of a system including an information processing apparatus according to an embodiment of the present invention. FIG. 2 is a schematic block diagram for explaining an outline of a system including the information processing apparatus according to the embodiment of the present invention from a viewpoint different from FIG. FIG. 3 is a diagram for explaining an aspect of information processing in the information processing apparatus according to the embodiment of the present invention. FIG. 4 is a diagram showing an aspect of information output from the information processing apparatus according to the embodiment of the present invention. FIG. 5A is a diagram showing, as an example, recruitment variables, coefficients, and the like in a card loan, and FIG. 5B is a diagram showing recruitment variables, coefficients, etc. in an automobile loan as an example.

Embodiment << Configuration >>
Embodiments of an information processing apparatus according to the present invention will be described below with reference to the drawings. Here, FIG. 1 to FIG. 5 are diagrams for explaining an embodiment of the present invention.

As shown in FIG. 2, in this embodiment, the information processing apparatus is described as being installed in an external organization of the financial institution. However, the present invention is not limited to this, and the information processing apparatus is installed in the financial institution. In this case, the financial institution may own and / or manage the information processing apparatus. The information processing apparatus according to the present embodiment may be composed of a single device or a plurality of devices. Further, when an information processing apparatus is configured from a plurality of devices, each device does not need to be provided in the same space such as the same room, and may be provided in different rooms, different buildings, different areas, and the like. In addition, when an information processing device is composed of a plurality of devices,
A part thereof may be owned and / or managed by a financial institution and the rest may be owned and / or managed by an external institution.

As illustrated in FIG. 1, the information processing apparatus according to the present embodiment has an artificial intelligence function, a generation unit 11 that generates predetermined information, and an output unit 30 that outputs information generated by the generation unit 11. ,have. The generation unit 11 employs an employment variable generated from one or more of attribute information of a customer who uses a financial institution such as a bank or a post office, examination information about the customer, and transaction information of the customer's financial institution, and the employment variable. The coefficient is used to generate information on needs related to the possibility of a certain customer using a predetermined financial product and / or risk information on the risk of credit loss or delinquency when lending money to a certain customer. Employment variables and coefficients are
It is determined by the generation unit 11 based on past performance data. This past result data includes past result data input in advance and a verification result by the verification unit 16 described later (more precisely, needs information and risk information are generated for the certain customer. Includes previously verified results.)

In the following description, the generation unit 11 will be described mainly using an aspect in which both the need information and the risk information are generated. However, the present invention is not limited to this, and the generation unit 11 can generate only the need information or the risk information. You may come to create.

As illustrated in FIG. 1, the information processing apparatus includes a device storage unit 20 that stores various information and a device control unit 10 that performs various controls. The generation unit 11, the calculation unit 15, and the verification unit 16 described later are all included in the device control unit 10. The device storage unit 20 may store a verification result by the verification unit 16 to be described later, in addition to data input in advance for automatically generating needs information and risk information. In addition, when a certain amount of data is accumulated, the data input in advance for generating the needs information and the risk information may be deleted. In addition, data including verification results older than a certain period (for example, two years) may be deleted. In this way, when generating needs information and risk information based only on data within a certain period (for example, within 2 years), highly accurate needs information and risk information are generated and output in line with the times. can do.

As an example of the artificial intelligence function, a classifier using a machine learning technique can be used. According to this classifier, for each customer, the probability that a target event such as the probability of a credit loss (in the case of a risk model), product application (in the case of a needs model) or the like occurs from customer information in a certain past period (for example, two years) Can be output. In this classifier, employed variables (elements) to be used and their coefficients (weights) are determined by machine learning technology so that the probability that a target event will occur is most likely from past performance data. Then, by applying the defined recruitment variables (elements) and their coefficients (weights) to data related to the target customer (= “a certain customer”), the customer needs rate for each product and the absolute Needs information including specific figures,
Risk information including the risk rate and absolute numerical values related to the risk is generated.

In order to output the probability that a target event will occur for the target customer, the generation unit 11 performs “learning” of the need model and the risk model for each product. Here, “learning” identifies the “features” that you want to find from the data, that is, needs events such as the purchase of financial products and risk events such as arrears on loans, and this “feature” can be best classified This means that such adoption variables (elements) and their coefficients (weights) are determined by automatic trial and error. That is, in the generation unit 11, information such as attribute information, examination information, and transaction information based on past performance data is aggregated, and repeated learning is performed so as to minimize the error while changing parameters (a tree model is adopted). In this case, a plurality of trees are created, and learning is repeatedly performed so that an error from past performance data is reduced), and a need model and a risk model to be applied to the target customer are determined. Then, by applying the determined adoption variable (element) and its coefficient (weight) to data related to the target customer, needs information and risk information for each product related to the customer are calculated.

Examples of the parameter to be changed include, for example, the number of iteration learning (for example, the number of trees in the tree model), and a coefficient used when the feature amount obtained immediately before the iteration learning is used in the next learning ( (Weight), percentage of data used during learning (meaning the amount of data used, for example, the ratio of whether 100,000 or 200,000 are used out of 1 million parameters) And the depth level at the time of learning (for example, the number of branches of the tree in the tree model). For example, when the number of iteration learning is large, the number of trees in the tree model is increased. On the other hand, when the number of iteration learning is small, the number of trees in the tree model is decreased. Further, when the depth level during learning is deep, the number of tree branches in the tree model increases, and when the depth level during learning is shallow, the number of tree branches in the tree model decreases. Note that the above-described parameters are merely examples, and the present invention is not limited to this, and the above-described parameters can be reduced or other elements can be used as parameters.

Examples of the attribute information used (see FIG. 3) include a name, sex, date of birth, age, and address.

The attribute information may include name identification information for collectively managing the same customer. A single financial institution can have multiple accounts. By using this name identification information, a plurality of account holders can be identified as a single customer and managed or used in subsequent processes. As name identification information, store number, CIF number (Customer Information File
Number), personal name identification number, and the like.

Further, the attribute information may include information on a person belonging to the same household, such as information related to the customer's family. Examples of the family include a person other than the person described in the various application forms such as the loan, a person other than the person having the same address, and a person other than the person having the same telephone number. Collecting information on persons belonging to the same household can be called household name identification. According to this household name identification, when a household has multiple accounts at one financial institution, information about the account is identified as that of one household, and the needs model and risk model are created using the results. Can do.

The examination information used (see FIG. 3) may include one or more of information related to a customer's borrowing application to a financial institution and customer credit information. More specifically, the examination information can include, for example, occupation, place of work, place of work, annual income, and the like. As examination information, other items such as “consumer loan application related information” such as the application date and result of acceptance,
“In-bank credit information” such as black information, debtor classification, and debtor rating.

The transaction information used (see FIG. 3) may include any one or more of deposit transaction information, loan transaction information, contract information with a financial institution, use information of services provided by the financial institution, and settlement information. More specifically, examples of transaction information include information relating to deposit, withdrawal, transfer, arrears and the like. Transaction information includes deposit balance by current fixed amount, deposit / withdrawal details, deposit / withdrawal summary column, etc., deposit balance information, loan balance, current credit limit, loan delinquency status, etc., loan presence / absence "Contract information" / "Usage information" such as card loan contract presence / absence, use / non-use of internet banking service, etc., "Payment information" such as whether or not public debiting is possible. The above-mentioned deposit / withdrawal details can include information on the deposit frequency, deposit amount, withdrawal frequency, withdrawal amount, transfer destination, transfer amount, and the like.

Other information used (see FIG. 3) can include information (proposal availability information) regarding whether or not direct mail or telephone contact is desired. If contact is not desired, the need information may not be created from the beginning, or the offer of the financial product may be prevented from being made to the customer although the need information is created.

The customer may be an individual or a corporation. Information such as customer attribute information
Obtained from financial institutions, ATMs, etc., Web, e-mail, direct mail,
It is acquired from the telephone etc. When the customer is a corporation, in addition to the above, information such as attribute information may be acquired by visiting. Note that the financial control unit 60 associates the customer's examination information, transaction information, and the like with the attribute information acquired in this way, and the financial storage unit 61.
Is remembered. As shown in FIG. 1, in this embodiment, the financial institution is described using an aspect in which a financial control unit 60 and a financial storage unit 61 are provided. However, the present invention is not limited to this, and financial control is performed. The unit 60 and / or the financial storage unit 61 may be provided in an external organization.

In addition, the functions of the financial storage unit 61 and the financial control unit 60 may be performed by a plurality of systems, and the assumption that the financial institution is provided with the financial control unit 60 and the financial storage unit 61 will be described later.
Any one or more of the MCIF, the automatic examination system, the backbone system, the CRM system, and the EBM system may be responsible for the functions of the financial storage unit 61 and the financial control unit 60.

As shown in FIG. 2, the information flow is based on the customer information acquired from the customer, the customer is examined in the financial institution, booked, and stored in the financial storage unit 61 as transaction information or the like. Will be. In the present embodiment, all information related to customers is referred to as “customer information”. “Customer information” is a customer database that uses financial institutions, MCIF (Ma
rketing Customer Information File), automatic screening system, backbone system, etc. These financial control unit 60 and financial storage unit 6 are included in these MCIF, automatic examination system, backbone system, etc.
1 may be included.

Financial institutions include CRM (Customer Relationshi), which records and manages customer attributes and contact history.
p Management) system and what happened to customers such as employment, marriage, home purchase, retirement, etc.
E) for inferring events) and proposing appropriate products and services at the optimal timing
A BM (Event Based Marketing) system is provided (see FIG. 2). These CR
The M system and / or the EBM system may include the financial storage unit 61 and the financial control unit 60 described above.

Examples of the predetermined financial products include card loans, education loans, mortgages, car loans, insurance, investment trusts and the like for individuals. On the other hand, for corporations, working capital loans, capital investment loans, insurance, operational products and the like can be cited.

Whether to create needs information and risk information may be determined according to the contents of the financial product. In the mode shown in FIG. 3, a need model and a risk model are generated for a new card loan, a card loan extremely increased frame, an education loan, a car loan, a mortgage loan and other loans.
1 can be generated, and for these, both needs information and risk information are created. On the other hand, only the needs model is generated for insurance and investment trust.
1 is generated, and only the need information is created for these, and the risk information is not created. Note that “AI” in FIG. 3 is “artificial intelli”.
It is an acronym for “gence” and means “artificial intelligence”.

The generation unit 11 may generate needs information and risk information for different financial products using different employment variables and different coefficients. For example, different recruitment variables and different coefficients are used for different financial products such as card loans, education loans, mortgages, car loans, insurance, investment trusts, working capital loans, capital investment loans, and investment products. May be. In FIG. 5 (a), as an example, the adopted variable in the card loan (“Fe in the figure)
”and coefficient (“ Gain ”in the figure) are shown, and in FIG. 5B, as another example, a variable used in an automobile loan (“ Feature ”in the figure) and coefficient (“ Gain ”in the figure) By comparing FIG. 5 (a) and FIG. 5 (b), it can be understood that different adoption variables and different coefficients are used in these card loans and automobile loans.

As illustrated in FIG. 1, the information processing apparatus may include a calculation unit 15 that calculates predetermined data. The calculation unit 15 may have a function of calculating profits for the customer by using the borrowing amount of the target customer, interest rate and expense information for the borrowing, and the like. Further, in addition to or instead of this function, the calculation unit 15 determines the creditable amount for the target customer and / or the target customer from the risk information generated by the generation unit 11. It may have a function of calculating an applicable interest rate. In addition, when the calculation unit 15 has a function of calculating the profit, the borrowing amount is determined within the range of the creditable amount determined based on the risk information for the target customer, The interest rate (= applicable interest rate) may also be determined based on the risk information. When the borrowing amount or interest rate is changed, risk information for the target customer may be generated again based on the changed borrowing amount and interest rate. Within the range of creditable amount may be the maximum amount of creditable amount or any amount less than that. The calculation unit may determine the borrowing amount with a plurality of amounts and calculate the profit for each borrowing amount.

As shown in FIG. 1, the information processing apparatus includes whether or not a predetermined financial product is actually used by a customer (including “whether or not an application has been made for a predetermined financial product”). You may further have the verification part 16 which verifies whether it was actually overdue when the money was lent to a customer, or overdue. When such a verification unit 16 is provided,
In addition to or instead of the information input in advance, the generation unit 11 may verify the verification result by the verification unit 16 (more precisely, verification verified before generating needs information and risk information for the customer) Results) may be used to generate needs information and / or risk information. In addition, the verification result by the verification unit 16 regarding the “certain customer” is used as past performance data regarding the need information and / or risk information generated after the verification result is issued.

In the information processing apparatus, the generation unit 11 may generate needs information and / or risk information for each of a plurality of financial products provided by a financial institution. Each of the plurality of needs information and risk information generated in this way may be output as a list by the output unit 30. Referring to the embodiment shown in FIG. 3, needs information and risk information about a new card loan, an extremely large card loan frame, an education loan, a car loan, a mortgage loan and other loans, and needs information about insurance and investment trust May be output as a list by the output unit 30.

The output needs information and risk information are sent to a financial institution as shown in FIG. 2, and are stored in the financial storage unit 61 (see FIG. 1) of the financial institution. And the CRM of financial institutions
It is proposed to provide financial products to customers via a system, an EBM system, or the like (see FIG. 2). This proposal may be made to a person in charge of a financial institution or directly to a customer. When a proposal is made to a person in charge of a financial institution, the person in charge from the person in charge of the financial institution through a bank contact, call center, ATM, etc., online banking on the Web, e-mail, direct mail, etc. The use of the product is proposed. On the other hand, when the above proposal is made directly to the customer, the use of the financial product is automatically proposed to the customer by ATM, net banking on the web, e-mail, direct mail or the like.

Whether or not there has been an application for a proposed financial product from a proposed customer (within a certain period of time), and whether or not a loan was actually made or delinquent when lending money to the customer It is managed and stored by an institution's automatic examination system, CRM system, EBM system, and the like. In addition, the above information (whether there has been an application for a proposed financial product from a customer who has made a proposal, and whether or not a loan has actually been delinquent or arrears when lending money to a customer) has been verified by a financial institution Sent to the unit 16 (included in “customer information” in FIG. 2), and verified by the verification unit 16. Such verification may be performed at any time, or may be performed collectively at regular intervals (for example, every week, every month, etc.). The verification result is stored in the device storage unit 20.

The generation unit 11 may randomly select a target customer and generate needs information and risk information for the customer. All the results may be output by the output unit 30, but only those that satisfy certain requirements may be output by the output unit 30. As an example, the output unit 30 may provide an absolute value related to a customer whose needs value, such as a need rate, an absolute numerical value related to needs, etc. is equal to or greater than a certain threshold (needs threshold), and / or a risk rate, risk. Only customers whose risk values such as numerical values are below a certain threshold (risk threshold) may be output. In particular, according to an aspect in which only customers whose need value is equal to or greater than the need threshold value and whose risk value is equal to or less than the risk threshold value are targeted for output, the operator must select carefully selected customers who should provide financial products. This is beneficial in that it can be confirmed at a glance. It should be noted that even if a customer who satisfies the above requirements and is an output target does not wish to contact, the customer may not be offered to provide financial products.

The calculation unit 15 determines how much revenue will be obtained if a loan is made to the customer based on the changes in the customer's borrowing amount and the balance in the account, the applicable interest rate applied to the customer, the expenses required for processing, the risk of credit loss, etc. You may calculate whether you can expect the amount. In addition, when the credit risk exceeds the first threshold, the calculation unit 15 calculates a specific applicable interest rate and / or credit amount by resetting the applied interest rate higher or reducing the credit amount. Also good. Conversely, when the credit loss risk falls below the second threshold (where the second threshold <the first threshold), the calculation unit 15 resets the applicable interest rate or increases the credit amount. Alternatively, a specific applicable interest rate and / or credit amount may be calculated. When calculating the applicable interest rate and / or credit amount, a specific interest rate and / or amount may be calculated, or an interest rate and / or amount having a certain range may be calculated.

Further, when the financial institution has, for example, a bank and a guarantee company as a group, the calculation unit 15 may calculate the group profit from the expected bank profit and the guarantee company profit. For example, the accumulated balance of money lent, the interest rate, the guarantee fee rate, the procurement cost rate,
Bank revenue may be calculated from a number obtained by subtracting a cost rate such as an office cost rate (for example, interest rate−guarantee fee rate−procurement cost rate−office cost rate). In addition, the accumulated balance of money lent and the number obtained by subtracting the cost rate such as the administrative cost rate from the guarantee fee rate (for example, the guarantee fee rate-
The profit of the guarantee company may be calculated from the office work cost rate) and the credit cost.

When the calculation unit 15 has a function of calculating profit, the expected profit may be calculated, and the expected return and the expected return when credited may be output (see FIG. 3).

The generation unit 11 uses the recruitment variable generated from the attribute information, the examination information, and the transaction information based on the name-identified customer or the household to which the customer belongs, and the coefficient for the recruitment variable and the needs information and risk information. Each may be generated as a “list”, and the output unit 30 may output the “list”. At this time, needs information and risk information for a plurality of financial products may be generated as a “list”, and the output unit 30 may output the “list” (see FIG. 4). By making a “list” in this way, the operator can confirm at a glance which financial product should be proposed to the target customer.

As shown in FIG. 4, for example, a needs rate and a needs rating may be output as the needs information. For example, a risk rate and a risk rating may be output as the risk information. Further, the need rate and the risk rate may be indicated by “%”, but may be indicated in a graph format so as to be understood at a glance. The needs rating and the risk rating are assigned so that the customer can easily recognize the rating. Further, when the calculation unit 15 calculates the creditable amount and the applicable interest rate, as shown in FIG. 4, the creditable amount and the applicable interest rate may be output as a list. In the mode shown in FIG. 4, the needs rate and needs rating, the risk rate and risk rating, and the creditable amount (shown as “preliminary credit amount” in FIG. 4) and application for each customer and each financial product. Interest rates (shown as “applicable interest rates” in FIG. 4) are shown.

The generation unit 11 generates an employment variable and a coefficient for the employment variable from any one or more of attribute information, examination information, and transaction information in “multiple” financial institutions, and uses the employment variable and the coefficient to Information and / or risk information may be generated. At this time, not only financial institutions that are affiliated but also financial institutions that have no capital relationship may use each other.

"Method"
When the information processing apparatus according to the present embodiment generates and outputs needs information and / or risk information, the following steps are performed. It should be noted that since this overlaps with the above, only a brief description will be given, but all aspects described in the above “configuration” can be applied in the “method”.

The generation unit 11 uses the employment variable generated from any one or more of the customer attribute information, the examination information about the customer, and the transaction information at the customer's financial institution, and the target customer. Need information and / or risk information for each financial product is generated. The adoption variable and the coefficient are determined by the generation unit 11 based on past performance data.

  Then, the information generated by the generation unit 11 is output by the output unit 30.

And based on the output information, provision of a financial product is proposed with respect to the target customer.

Whether or not a given financial product was actually used by a target customer, or whether or not a loan was actually made or delinquent when lending money to a target customer The result may be verified by the verification unit 16. And this verification part 16
Subsequent needs information and / or risk information may be generated using the verification result obtained by.

《Action ・ Effect》
Next, operations and effects according to the present embodiment having the above-described configuration, which have not been described yet, will be mainly described.

According to the present embodiment, the generation unit 11 having an artificial intelligence function is generated from any one or more of attribute information of a customer who uses a financial institution, examination information about the customer, and transaction information at the customer's financial institution. Using the recruitment variable and the coefficient for the recruitment variable, needs information and / or risk information for the target customer (= a certain customer) is generated, and the result is output unit 3.
Output by zero. Employment variables and coefficients to be used are determined based on past performance data. For this reason, needs information and / or risk information can be output based on objective data.

Moreover, when the production | generation part 11 produces | generates both needs information and risk information, the information regarding both of these can be obtained.

Further, when the generation unit 11 uses the attribute information, the examination information, and the transaction information to generate the adoption variable and the coefficient, the need information and / or the risk information using all of the attribute information, the examination information, and the transaction information. Therefore, more accurate needs information and / or risk information can be output. If there is information that does not exist (for example, examination information) for the target customer, the information is processed as not existing.

If the attribute information includes name identification information for managing the same customer collectively, even if the customer has multiple accounts, manage them as a single customer and collect information can do. For this reason, since needs information and / or risk information can be produced | generated based on more information, more highly accurate needs information and / or risk information can be output.

When the attribute information includes information about the household such as the customer's family, the needs information and / or risk information can be generated based on the information in the same household. Can output. When using family information in this way, needs information and / or risk information is generated based on individual customer information, and needs information and / or risk information is generated based on customer family information. Also good. According to such an aspect, the result based on the need information and / or risk information of two patterns can be output.

Transaction information includes deposit transaction information, loan transaction information, contract information with financial institutions, usage information of services provided by financial institutions, or settlement information, but by selecting appropriately from many types of information, Accurate needs information and / or risk information can be output.

The examination information includes information related to the customer's borrowing application to the financial institution or customer credit information. By appropriately selecting from various types of information, more accurate needs information and / or risk information can be output. .

In general, as the amount of information increases, it can be expected that highly accurate needs information and / or risk information can be obtained. However, if the amount of information is too large, processing may take time or unimportant information may be captured. It should be noted that a certain degree of pawl is necessary because of the possibility.

When the artificial intelligence function of the generation unit 11 generates needs information and / or risk information using different employment variables and different coefficients for different financial products, more appropriate employment variables and coefficients according to the financial products Can be used. Therefore, more accurate needs information and / or
Or risk information can be output.

When the calculation unit 15 calculates revenue by using the borrowing amount of the target customer, interest rate and expense information at the time of the borrowing, etc., the operator can also obtain information on the revenue It is possible to determine whether or not to provide a financial product based on information related to profits. In addition, if the borrowing amount is determined within the creditable amount determined based on the risk information for the customer and the interest rate (= applicable interest rate) is also determined based on the risk information for the customer, it is appropriate In addition to providing customized financial products, we can expect to secure profits within an appropriate range.

In addition, when the calculation unit 15 calculates the creditable amount for the customer and / or the applicable interest rate for the customer from the risk information generated by the generation unit 11, the calculation unit 15 determines the customer based on the creditable amount and / or the applicable interest rate. It is possible to propose to provide financial products. For this reason,
Providing appropriately customized financial products and securing an appropriate range of profits.

The generation unit 11 needs information and / or information on each of a plurality of financial products provided by the financial institution.
Alternatively, when generating and outputting risk information, the operator can grasp the needs information and / or risk information for each of the output financial products and compare which financial products should be proposed. Can be judged.

The generation unit 11 is not limited to information of one financial institution, but attribute information in a plurality of financial institutions,
In the case where a recruitment variable and a coefficient for the recruitment variable are generated from one or more of the examination information and transaction information, and the needs information and / or risk information is generated using the recruitment variable and the coefficient, the customer Since needs information and / or risk information can be generated based on broader and overall information about the information, needs information and / or risk information with higher accuracy can be output.

When the verification unit 16 verifies whether or not a predetermined financial product is actually used by the customer, or whether or not the loan is actually delinquent or delinquent when lending money to the customer Since the updated verification result can be used as past performance data, it is possible to generate and output needs information and / or risk information based on information with higher reliability. As described above, needs information and risk information may be generated based only on data within a certain period (for example, within two years). /
Alternatively, risk information can be generated and output.

By the way, when the need rate of card loans is high, if the deposit balance is small,
An example is when there are many withdrawals with a small amount. As for the need rate of education loans, if the transfer account contains the words "junior high school" or "high school", there may be a child of an age that is likely to require an education loan for customers due to household identification The case where it understands can be mentioned. An example of a case where the mortgage needs rate is high is that a mortgage with a high interest rate is currently being paid.

Lastly, the description of the embodiments and the disclosure of the drawings described above are merely examples for explaining the invention described in the claims, and the description of the embodiments or the disclosure of the drawings described above is included. The invention described in the scope of claims is not limited by this. For example, even information that provides information other than needs information and risk information falls under the information processing apparatus in the present application.

10 device control unit 11 generation unit 15 calculation unit 16 verification unit 20 device storage unit 30 output unit 60 financial control unit 61 financial storage unit

Claims (16)

A generation unit having an artificial intelligence function, the adoption variable generated from any one or more of attribute information of a customer who uses a financial institution, examination information about the customer, and transaction information of the customer at the financial institution, and A generation unit that generates a need information on a possibility that a certain customer uses a predetermined financial product or a risk information on a credit loss risk or arrears risk when lending money to the certain customer by using a coefficient for the employment variable;
An output unit for outputting information generated by the generation unit;
With
The information processing apparatus, wherein the adopted variable and the coefficient are determined based on past performance data. A verification unit that verifies whether or not the predetermined financial product was actually used by the customer, or whether or not the loan was actually delinquent or arrears occurred when lending money to the customer; ,
The information processing method according to claim 1, wherein the verification result by the verification unit is used as the past performance data with respect to the needs information or the risk information generated after the verification result is issued. apparatus. The information processing apparatus according to claim 1, wherein the generation unit generates the needs information and the risk information. The information processing apparatus according to claim 1, wherein the generation unit generates the adopted variable and the coefficient using the attribute information, the examination information, and the transaction information. The artificial intelligence function of the generation unit generates the needs information or the risk information using different adoption variables and different coefficients for different financial products. The information processing apparatus according to item. 6. The information processing apparatus according to claim 1, further comprising a calculation unit that calculates a profit using the borrowing amount of the certain customer, interest rate and expense information for the borrowing, and the like. . The borrowing amount is determined within a creditable amount determined based on the risk information for the certain customer;
The information processing apparatus according to claim 6, wherein the interest rate is determined based on the risk information. 2. The apparatus according to claim 1, further comprising a calculating unit that calculates a creditable amount for the certain customer or an applicable interest rate for the certain customer from the risk information generated by the generating unit.
The information processing apparatus according to any one of 1 to 7. The information processing apparatus according to claim 1, wherein the attribute information includes name identification information for collectively managing the same customer. 10. The attribute information includes information related to the customer's family.
The information processing apparatus according to any one of the above. 2. The transaction information includes deposit transaction information, loan transaction information, contract information with the financial institution, service usage information or settlement information provided by the financial institution.
The information processing apparatus according to any one of 0. The information processing apparatus according to any one of claims 1 to 11, wherein the examination information includes information related to the customer's borrowing application to the financial institution or credit information of the customer. For each of a plurality of financial products provided by the financial institution, the generation unit generates the needs information or the risk information,
The information processing apparatus according to claim 1, wherein the output unit outputs the need information or the risk information related to each of a plurality of financial products. The generation unit generates the adopted variable and a coefficient for the adopted variable from any one or more of the attribute information, the examination information, and the transaction information in a plurality of financial institutions, and uses the adopted variable and the coefficient 14. The information processing apparatus according to claim 1, wherein the need information or the risk information is generated. The output unit has a needs value included in the needs information equal to or greater than a needs threshold.
The information processing apparatus according to claim 1, wherein only customers whose risk value included in the risk information is a risk threshold value or less are output. A hiring variable generated from any one or more of attribute information of a customer who uses a financial institution, examination information about the customer, and transaction information of the customer in the financial institution by the generating unit having an artificial intelligence function, and the hiring Using a coefficient for a variable, generation information is generated by the generation unit regarding the need information regarding the possibility that the certain customer uses the predetermined financial product or the risk of credit loss or the delinquency risk when lending money to the certain customer. And
Outputting the information generated by the generator by an output unit;
With
The information processing method, wherein the adopted variable and the coefficient are determined based on past performance data.