JP2017151527A - Information processing device and information processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To generate need information or risk information on the basis of objective data.SOLUTION: An information processing device comprises: an integration unit 50 for creating integrated information by integrating two or more pieces of individual information; and a generation unit 11 having an artificial intelligence function, with the use of the integrated information, for creating need information on a possibility that a client uses a predetermined financial product or risk information on an irrecoverable risk or a delay risk when the client makes a loan.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 a considerable degree of experience, and various information is used, and it cannot always be based on objective data.

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

An information processing apparatus according to the present invention includes:
An integration unit that integrates two or more pieces of individual information to create integrated information;
A generation unit having an artificial intelligence function, which uses the integrated information, needs information about the possibility of a customer using a predetermined financial product, or risk related to a credit loss risk or arrears risk when money is lent to the customer A generator for generating information;
With
The individual information includes attribute information of the customer, examination information regarding the customer, or transaction information of the customer.

In the information processing apparatus according to the present invention,
The integration unit may create the integration information using the attribute information, the examination information, and the transaction information.

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 individual information has two or more individual information files,
The integration unit may integrate a plurality of individual information files based on key elements to create a sub integrated information file.

In the information processing apparatus according to the present invention,
The integration unit may integrate the plurality of sub integration information files based on key elements to create the integration information file.

In the information processing apparatus according to the present invention,
A sub-integrated information file of the attribute information is created based on the plurality of individual information files of the attribute information, a sub-integrated information file of the examination information is created based on the plurality of the individual information files of the examination information, Alternatively, a sub-integrated information file of the transaction information may be created based on the plurality of individual information files of the transaction information.

In the information processing apparatus according to the present invention,
The individual information has an individual information file,
The integration unit integrates a plurality of individual information files based on key elements, creates an integrated information file or a sub-integrated information file,
When there are a plurality of pieces of information based on the key element in the same individual information file, and the plurality of pieces of information is information that should exist only one, the integration unit is based on a predetermined condition. The integrated information file or the sub integrated information file may be created by deleting information judged to be unnecessary from a plurality of pieces of information.

In the information processing apparatus according to the present invention,
The individual information has an individual information file,
The integration unit integrates a plurality of individual information files based on key elements, creates an integrated information file or a sub-integrated information file,
When there are a plurality of pieces of information based on the key element in the same individual information file and the information is allowed to exist, the integration unit uses the plurality of pieces of information. The integrated information file or the sub integrated information file may be created.

In the information processing apparatus according to the present invention,
The generation unit generates the needs information or the risk information using an adoption variable generated from the integrated information and a coefficient for the adoption variable,
The employment variable and the coefficient may be determined based on past performance data.

In the information processing apparatus according to the present invention,
The integrated information includes unnecessary elements that are not used in the generation unit,
When the integrated information is input to the generation unit, the generation unit may generate the need information or the risk information without using the unnecessary elements.

In the information processing apparatus according to the present invention,
The integration unit may create the integrated information by integrating two or more pieces of the individual information in a plurality of financial institutions.

An information processing method according to the present invention includes:
Integrating two or more pieces of individual information to create integrated information;
Need information on the possibility of the customer using a predetermined financial product by using the integrated information by the generation unit having an artificial intelligence function, or risk information on a credit risk or arrears risk when lending money to the customer Generating
Is provided.

  According to the present invention, integrated information is created by integrating two or more pieces of individual information, and on the basis of the integrated information, customer information regarding the possibility of using a predetermined financial product or when lending money to a customer Risk information about the default or delinquency risk is generated. Since the need information or risk information is generated based on the unified information as described above, the need information or risk information can be generated based on objective data. Moreover, need information or risk information can be easily obtained by generating integrated information in this way.

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. FIG. 6 is a diagram showing an example of a flow until needs information and risk information are obtained from an individual information file in the embodiment of the present invention. FIG. 7 is a diagram showing an example of a flow until an integrated information file or a sub integrated information file is created in the embodiment of the present invention. FIG. 8 is a table showing key elements, unique rules, and behavior in the analysis system when an integrated information file or a sub integrated information file is created in the aspect shown in FIG.

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. 8 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. Further, when an information processing apparatus is configured from a plurality of apparatuses, 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. In this embodiment, “and / or” may be used for explanation, but the word “or” also includes the meaning of “and”. That is, the term A or B is a concept including A alone, B alone, and A and B.

  As shown in FIG. 1, the information processing apparatus according to the present embodiment integrates two or more pieces of individual information to create integrated information (in the form shown in FIG. 7, “integrated information file” and “sub- An integrated information file ”), and a generation unit 11 having an artificial intelligence function, which uses the integrated information to give information on the need for the customer to use a predetermined financial product or money to the customer. It has the production | generation part 11 which produces | generates the risk information regarding the credit risk or the overdue risk at the time of loan, and the output part 30 which outputs the information produced | generated by the production | generation part 11. The individual information includes customer attribute information, customer examination information, and / or customer transaction information.

  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. Factors may be used to generate information on needs related to the possibility of a certain customer using a given financial product and / or risk information on credit or delinquency risk when lending money to a certain customer. . The recruitment variable and the coefficient may be determined by the generation unit 11 based on past performance data. The past result data may include past result data input in advance or a verification result by the verification unit 16 described later. A verification result verified before generating the need information and risk information for the certain customer may be included.

  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.

  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 Need information including a typical numerical value and the like, and risk information including a risk rate, an absolute numerical value related to the risk, etc. are generated (see FIG. 4).

  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.

  The integration unit 50 may create integrated information such as an integrated information file using attribute information, examination information, transaction information, and other information. As an example, information of millions of accounts may be integrated for a plurality of years. The information items per account may reach hundreds of thousands. The information in the integrated information file may be divided and managed every fixed period (for example, one year), or may be managed so as to include all of the target periods.

  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. The name identification information includes a store number, a CIF number (Customer Information File number), a 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. Other examples of examination information include “consumer loan application-related information” such as examination application date and acceptance result, “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 attribute information related to customers is acquired from a store of a financial institution, ATM, or the like, or acquired from the Web, electronic mail, direct mail, telephone or the like. When the customer is a corporation, in addition to the above, information such as attribute information may be acquired by visiting. Note that the examination information, transaction information, etc. of the customer are associated with the attribute information obtained in this way by the financial control unit 60 and stored in the financial storage unit 61. 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, a plurality of systems may be responsible for the functions of the financial storage unit 61 and the financial control unit 60, and on the premise that the financial control unit 60 and the financial storage unit 61 are provided in the financial institution, MCIF, automatic examination described later Any one or more of the 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.

  Individual information including attribute information, examination information, transaction information and / or other information may have two or more individual information files. Moreover, as shown in FIG. 6, each of attribute information, examination information, transaction information, and other information may have a plurality of individual information files. In the mode shown in FIG. 6, the attribute information file 1, the attribute information file 2, the examination information file 1, the examination information file 2, the transaction information file 1, the transaction information file 2, the other information file 1, and the other information file 2 are stored. Each is an individual information file.

  Further, as shown by the upper route in FIG. 6, integrated information such as an integrated information file may be generated based on a plurality of individual information files. Further, as shown in the lower route of FIG. 6, a plurality of individual information files are integrated based on key elements to create sub integrated information such as a sub integrated information file, and the integrated information is generated based on the sub integrated information. Integrated information such as a file may be created.

  In the mode shown in FIG. 7, the attribute information has two individual information files (“attribute information file 1” and “attribute information file 2” in the mode shown in FIG. 7). Also, two individual information files ("attribute information file 1" and "attribute information file 2" in the mode shown in FIG. 7) included in the attribute information are integrated to create a sub integrated information file related to the attribute information.

  When there are a plurality of pieces of information based on key elements in the same individual information file and only one piece of the plurality of pieces of information is to be present, the integration unit 50 selects a plurality of pieces of information based on predetermined conditions. Information determined to be unnecessary among certain information may be deleted to create an integrated information file or a sub integrated information file. In the mode shown in FIG. 7, “customer number” is used as a key element (see also FIG. 8). In the attribute information file 2, the customer number “3” has two addresses, “C village” and “D village”. For this reason, for example, based on a “predetermined condition” that priorities are given to the latest information, priority is given to having an address in “C village”, and deleting the address of customer number “3” in “D village” is deleted. The attribute information sub-integrated information file is created assuming that only the “C village” has an address. In FIG. 8, the age and address are set to “first out” as the unique rule, and the latest information is prioritized.

  Further, when there are a plurality of pieces of information based on key elements in the same individual information file and the information is allowed to exist, the integration unit 50 uses the plurality of pieces of information. Thus, an integrated information file or a sub integrated information file may be created. In the transaction information file 1 shown in FIG. 7, the product “A” and the product “B” are listed for the same customer “1” in the same recording month “2015/3”. Since this information corresponds to “information that is allowed to exist” because it is a purchase history of the product, it is assumed that the customer number “1” purchased the product “A” and the product “B” on “2015/3”. A sub-integrated information file of transaction information has been created. The customer “2” has purchased the product “B” and the product “C”, but since the recording month is different, there is no case where there is a plurality of information based on key elements. The case where there is a plurality of pieces of information based on key elements means that the information falls within the same frame when classified by the item of the target file. In FIG. 8, as a unique rule, the product is a “matrix”, and is in a form that exists in parallel.

  The integrating unit 50 may integrate a plurality of sub integrated information files based on key elements to create an integrated information file. The key element may be an element used when creating the sub integrated information file, or may be another element. In the mode shown in FIG. 7, the customer number is a key element, and the sub-integrated information file of attribute information and the sub-integrated information file of transaction information are integrated to create an integrated information file. It is not limited to such a mode, and the sub integrated information file itself may be integrated information.

  The integrated information may include unnecessary elements that are not used by the generation unit 11. In such an aspect, when integrated information is input into the production | generation part 11, the production | generation part 11 may produce | generate needs information and risk information, without using an unnecessary element. In the aspect shown in FIG. 7, “age” is an unnecessary element, and in the table shown in FIG. 8, “non-target” is set as the behavior of the analysis system. For this reason, even when integrated information such as an integrated information file is input to the generation unit 11, the “age” is not used, and the generation unit 11 generates needs information and risk information. Note that this unnecessary element may be changed to a necessary element. When such an unnecessary element is determined, the generation unit 11 generates needs information or risk information based on the element. For example, when “age” is a necessary element, the generation unit 11 also uses the “age” to generate needs information or risk information.

  As shown in FIG. 2, the information flow is based on customer information obtained from a user such as a customer, and the customer is examined in a financial institution, booked, and stored as transaction information. It is stored in the unit 61 (see FIG. 1). In the present embodiment, all information related to customers is referred to as “customer information”. The “customer information” may be provided from MCIF (Marketing Customer Information File) which is a customer database using a financial institution, an automatic examination system, a backbone system, or the like. The financial control unit 60 and the financial storage unit 61 may be included in the MCIF, automatic examination system, backbone system, and the like.

  For financial institutions, CRM (Customer Relationship Management) system that records and manages customer attributes and contact histories, as well as customer events such as employment, marriage, home purchase, retirement, etc. And an EBM (Event Based Marketing) system for proposing appropriate products and services at the same timing (see FIG. 2). These CRM system and / or 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 aspect shown in FIG. 3, the generation unit 11 can generate a need model and a risk model for a new card loan, an extremely large card loan frame, an education loan, a car loan, a mortgage loan, and other loans. Both needs information and risk information are created. On the other hand, for the insurance and the investment trust, the generation unit 11 generates only the need model, and only the need information is created for these, and the risk information is not created. Note that “AI” in FIG. 3 is an acronym for “artificial intelligence” 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. 5A, as an example, the adoption variable (“Feature” in the figure) and the coefficient (“Gain” in the figure) in the card loan are shown, and in FIG. 5B, as another example, the automobile Employment variables ("Feature" in the figure) and coefficients ("Gain" in the figure) are shown in the loan. By comparing FIG. 5 (a) and FIG. 5 (b), these card loans and automobiles It can be seen that different recruitment variables and different factors are used in the loan.

  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. In the case where such a verification unit 16 is provided, the generation unit 11 adds the verification result by the verification unit 16 in addition to or instead of the information input in advance (more precisely, to a certain customer) Need information and / or risk information may be generated using a verification result verified before generating needs information and 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.

  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. Then, it is proposed to provide financial products to customers via the CRM system or EBM system of the financial institution (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, 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. As an example, the accumulated balance of money lent, and a number obtained by subtracting the cost rate such as the guarantee fee rate, procurement cost rate, and administrative cost rate from the interest rate (for example, interest rate-guarantee fee rate-procurement cost rate-administrative cost rate) and Bank revenue may be calculated from In addition, even if the guarantee company's revenue is calculated from the accumulated balance of the loaned money, 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 administrative cost rate) Good.

  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 integration unit 50 may generate integrated information or sub-integrated information by integrating two or more pieces of individual information in a plurality of financial institutions. That is, the integrated information or the sub integrated information may be generated based on attribute information, examination information, or transaction information in a plurality of financial institutions. 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 of the present embodiment generates and outputs needs information or risk information, the following steps are performed. In addition, since it overlaps with the above, only a brief description will be given, but all the aspects described in the above “configuration” and all the aspects described in the following “action / effect” can be applied in the “method”. .

  The integration unit 50 integrates two or more pieces of individual information to create integrated information (see FIG. 6). The individual information includes attribute information, examination information, or transaction information. The integration unit may create integrated information using attribute information, examination information, and transaction information.

  When the integrated information is created, the generation unit 11 needs information on the possibility that a customer who uses the integrated information may use a predetermined financial product and / or a credit loss risk when lending money to the customer or Risk information about arrears risk is generated.

  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 (a certain customer) (refer FIG. 2).

  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 (see FIG. 1). Further, the subsequent needs information and / or risk information may be generated using the verification result by the verification unit 16.

《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, integrated information is created by integrating two or more pieces of individual information, and based on this integrated information, the customer needs information on the possibility of using a predetermined financial product or lends money to the customer. Risk information about the credit loss risk or delinquency risk is generated. Since the need information or risk information is generated based on the unified information as described above, the need information or risk information can be generated based on objective data. Moreover, need information or risk information can be easily obtained by generating integrated information in this way.

  In particular, when handling a large amount of information such as information on millions of accounts, work efficiency can be improved by creating integrated information in advance by the integration unit 50 as in the present embodiment. In addition, despite the large amount of information, the generation unit 11 having an artificial intelligence function learns using integrated information composed of predetermined items, so that high objectivity can be realized in the learning result, and more reliable High needs information and risk information can be generated.

  Furthermore, when the integrated unit 50 creates integrated information at any time or periodically, the integrated information can be generated based on the latest information, and needs information or risk information can be generated based on more accurate data. . For example, the integration unit 50 may create an integrated information file or a sub integrated information file every day, every week, every month, or the like. The timing at which the integration unit 50 creates the integrated information file may be different from the timing at which the sub-integration information file is created. For example, the integration unit 50 creates a sub-integration information file every day. You may create a file. When creating an integrated information file or sub-integrated information file in this way, an updated integrated information file is created by using only the added information and adding to the existing integrated information file or sub-integrated information file. Alternatively, a sub integrated information file may be created.

  The integration unit 50 may create an integrated information file or a sub integrated information file based on information for a certain period. According to this aspect, every time the integrated information file or the sub-integrated information file is updated, old information may be deleted or not used in the generation unit 50 for the same period as the updated period.

  When the integration unit 50 creates the integrated information file or the sub integrated information file, the type (numerical type, character type, or date type) of the individual information file may be confirmed. According to such an aspect, it is advantageous in that the type of the individual information file can be recognized before the integrated information file or the sub integrated information file is generated, and the integrated information file or the sub integrated information file can be efficiently generated.

  When the integration unit 50 creates the integration information file or the sub integration information file, the size of the number of digits of information included in the individual information file may be confirmed. According to such an aspect, it is advantageous in that the size of the individual information file can be recognized before creating the integrated information file or the sub integrated information file, and the order of creation can be changed as necessary.

  When the integration unit 50 adopts an aspect in which integrated information is created using attribute information, examination information, and transaction information, needs information or risk information can be generated using more types of information. For this reason, needs information or risk information can be generated based on more objective data. In addition, when the integration part 50 employ | adopts the aspect which produces integrated information using attribute information, examination information, transaction information, and other information, needs information or risk information is used using more types of information. Can be generated.

  Also, by integrating different types of information such as attribute information, examination information, and transaction information, the objectivity can be improved as compared with the conventional case. That is, when an operator manually creates information from different types of information such as attribute information, examination information, and transaction information, the person or department in charge of creating data may be different. In this way, if the person in charge or department in charge is different, the viewpoint of the acquired information may differ between attribute information, examination information, and transaction information, and as a result, integrated information that is different from what was originally intended There is a possibility that a file or a sub integrated information file is created. In this regard, according to the aspect in which the integration unit 50 creates the integrated information file or the sub-integrated information file from the attribute information, the examination information, and the transaction information, it is possible to eliminate the deviation of the viewpoint due to the different person in charge or the department in charge. Useful in terms.

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

  When each of the attribute information, the examination information, and the transaction information has a plurality of individual information files, and a plurality of individual information files are integrated based on key elements to create a sub integrated information file, Information can be efficiently integrated even when many and many types of individual information files are used. In addition, since the sub integrated information file is once created, it is advantageous in that analysis using the sub integrated information file can be performed separately.

  Further, a sub-integrated information file of attribute information is created based on a plurality of individual information files of attribute information, a sub-integrated information file of examination information is created based on a plurality of individual information files of examination information, and a plurality of transaction information A sub-integrated information file of transaction information may be created based on the individual information file. Thus, by creating a sub integrated information file according to the type of information, it is possible to efficiently create a sub integrated information file. In addition, by creating a sub integrated information file for each type in this way, the sub integrated information file can also be used for analysis for each type.

  In addition, it is not always necessary to have such an aspect, and a sub integrated information file may be created by mixing two or more of attribute information, examination information, and transaction information. This is because it may be desirable to create a sub integrated information file by mixing two or more of attribute information, examination information, and transaction information as necessary.

  When there is a plurality of pieces of information based on key elements in the same individual information file and only one piece of the plurality of pieces of information should be present, it is unnecessary among the pieces of information that are based on a predetermined condition. When an aspect in which the determined information is deleted is adopted, integrated information can be generated based on appropriate information such as the latest information without using unnecessary information such as old information. For this reason, needs information or risk information can be generated based on more accurate data.

  When there are a plurality of pieces of information based on key elements in the same individual information file and the pieces of information are allowed to exist (in parallel), the plurality of pieces of information are (in parallel) In the case of adopting an aspect that is used as existing, it is possible to generate integrated information using a larger number and more types of information. For this reason, needs information or risk information can be generated based on more accurate data.

  When multiple sub-integrated information files are integrated based on key elements to form an integrated information file, the integrated information file is integrated with the separately created sub-integrated information files. It is useful in that integrated information such as can be created.

  The integrated information may include unnecessary elements that are not used by the generation unit 11. In this case, when integrated information is input to the generation unit 11, it is possible to adopt a mode in which the generation unit 11 generates needs information or risk information without using unnecessary elements. According to this aspect, it is possible to generate needs information or risk information without using information that does not significantly affect the results. As a result, the generation unit 11 can generate needs information or risk information without using unnecessary elements, and can quickly generate needs information or risk information without wasting time.

  The generation unit 11 uses the employment variable generated from any one or more of the attribute information of the customer who uses the financial institution, the examination information about the customer, and the transaction information in the customer's financial institution, and the needs information. In addition, when the risk information is generated and the adoption variable and the coefficient are determined based on the past performance data, the need information and / or the risk information can be output based on the past performance. For this reason, the reliability of information can be improved.

  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. For this reason, more accurate needs information and / 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, it is possible to provide an appropriately customized financial product and to secure an appropriate range of profits.

  When the generation unit 11 generates and outputs needs information and / or risk information for each of a plurality of financial products provided by the financial institution, the operator outputs needs information and / or information about each of the output financial products. Alternatively, risk information can be grasped, and it can be determined by comparing which financial product should be proposed.

  When the integration unit 50 creates integrated information by integrating two or more pieces of individual information from a plurality of financial institutions, it creates integrated information based on the attribute information, examination information, and transaction information of the plurality of financial institutions. it can. As a result, needs information and / or risk information can be generated based on attribute information, examination information, and transaction information in a plurality of financial institutions. Therefore, needs information and / or risk information can be generated based on broader and overall information, and more accurate needs information and / or risk information 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). / Or risk information can be generated and output.

  By the way, there are cases where the need rate of card loans is high, such as when the deposit balance is small or when there is a large amount of withdrawals. 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 50 integration unit 60 financial control unit 61 financial storage unit

Claims (12)

An integration unit that integrates two or more pieces of individual information to create integrated information;
A generation unit having an artificial intelligence function, which uses the integrated information, needs information about the possibility of a customer using a predetermined financial product, or a risk related to a credit loss risk or arrears risk when money is lent to the customer A generator for generating information;
With
The information processing apparatus according to claim 1, wherein the individual information includes attribute information of the customer, examination information about the customer, or transaction information of the customer.   The information processing apparatus according to claim 1, wherein the integration unit creates the integration information using the attribute information, the examination information, and the transaction information.   The information processing apparatus according to claim 1, wherein the generation unit generates the needs information and the risk information. The individual information has two or more individual information files,
The information processing apparatus according to claim 1, wherein the integration unit integrates a plurality of individual information files based on key elements to create a sub integrated information file.   The information processing apparatus according to claim 4, wherein the integration unit integrates a plurality of the sub integration information files based on key elements to create the integration information file.   A sub-integrated information file of the attribute information is created based on the plurality of individual information files of the attribute information, a sub-integrated information file of the examination information is created based on the plurality of the individual information files of the examination information, 6. The information processing apparatus according to claim 4, wherein a sub-integrated information file of the transaction information is created based on the plurality of individual information files of the transaction information. The individual information has an individual information file,
The integration unit integrates a plurality of individual information files based on key elements, creates an integrated information file or a sub-integrated information file,
When there are a plurality of pieces of information based on the key element in the same individual information file, and the plurality of pieces of information is information that should exist only one, the integration unit is based on a predetermined condition. 7. The information processing apparatus according to claim 1, wherein information that is determined to be unnecessary among a plurality of pieces of information is deleted, and the integrated information file or the sub integrated information file is created. . The individual information has an individual information file,
The integration unit integrates a plurality of individual information files based on key elements, creates an integrated information file or a sub-integrated information file,
When there are a plurality of pieces of information based on the key element in the same individual information file and the information is allowed to exist, the integration unit uses the plurality of pieces of information. The information processing apparatus according to claim 1, wherein the integrated information file or the sub integrated information file is created. The generation unit generates the needs information or the risk information using an adoption variable generated from the integrated information and a coefficient for the adoption variable,
The information processing apparatus according to claim 1, wherein the adopted variable and the coefficient are determined based on past performance data. The integrated information includes unnecessary elements that are not used in the generation unit,
The said production | generation part produces | generates the said needs information or the said risk information, without using the said unnecessary element, when the said integration information is input into the said production | generation part, The any one of Claim 1 thru | or 9 characterized by the above-mentioned. The information processing apparatus according to item.   11. The information processing apparatus according to claim 1, wherein the integration unit generates the integrated information by integrating two or more pieces of the individual information in a plurality of financial institutions. Integrating two or more pieces of individual information to create integrated information;
Need information on the possibility of the customer using a predetermined financial product by using the integrated information by the generation unit having an artificial intelligence function, or risk information on a credit risk or arrears risk when lending money to the customer Generating
An information processing method characterized by comprising: