JP4112559B2 - Information processing apparatus, information processing method, and program thereof - Google Patents

Description

  The present invention relates to an information processing apparatus, an information processing method, and a program for managing credit risk such as a bond.

  Conventionally, a bank or the like needs to evaluate credit risk of a loan due to a loan or the like when performing a loan business. The credit risk is evaluated before the loan and is re-evaluated as needed after the loan. The credit risk is quantified and used to obtain an index to show the soundness of management of the bank itself.

  For example, BIS regulations are established as an international standard as an index for showing the soundness of management of banks themselves. This BIS regulation calculates the risk to a bank's capital under certain conditions. According to the new BIS regulation draft announced in June 2004, in addition to the conventional “market risk” and “credit risk” as risk information, “operational risk” generated from banking accidents, etc. An index value indicating the soundness of bank management for the overall risk situation surrounding the bank is calculated.

  By the way, when obtaining the above BIS regulation index values, some calculation rules and data are prepared, but there are also parameters that the bank itself has to prepare independently. For example, in the new BIS regulations, it is necessary to estimate and prepare the parameters of “default (default) rate” and “loss rate at default” when obtaining the above “credit risk” (for example, Non-Patent Document 1). See).

  The above-mentioned parameters of “default (default) rate” and “loss rate at default” have been predicted using statistical methods and subjective methods of each bank. There is an accuracy problem, and each bank is currently trial and error (see Non-Patent Document 2, for example). On the other hand, since the statistical method is based on past data, it can be obtained with higher accuracy than the subjective method. However, as specified in Non-Patent Document 1, as a standard, to estimate the default rate, etc., the data to be used for the estimation are all related to the bank, even though the method is not clearly defined. It is required to cover the data. In other words, it is left to each bank to select which data should be used and what to do even if estimation is performed using statistical methods.

Basel, “New Basel Agreement on Capital”, p. 109-112, [online], January 2001, [October 5, 2004 search], Internet <URL: http://www.boj.or.jp/intl/01/data/bis0101d2.pdf> Koichi Nishioka, 6 others, “Study on Credit Risk”, “Mitsubishi Research Institute Bulletin 40 Special Issue“ Management and IT ””, Mitsubishi Research Institute, Ltd., July 25, 2002, p.36 -37

  Each bank has to estimate the “default rate” and “loss rate at default” in order to comply with the BIS regulations, but as mentioned above, the reality is that the method has not yet been established. is there. For example, the loan situation of a bank changes day by day, so the receivables and risks change with the change. Therefore, when it is desired to obtain the latest estimated value, it is not possible to reuse all the data used in the previous estimation as it is, and it is necessary to extract new data again. However, as mentioned above, in order to estimate the default rate, etc., the data to be used for the estimation is required to cover all the data related to the bank. There is a problem that information processing must be performed. Furthermore, even if these “default rate” and “loss rate at default” can be estimated, it does not end there. For example, an estimated value obtained by adding a subjective factor of the bank to the estimated value obtained statistically. However, the more data that is targeted, the more difficult it was to add subjectivity.

The present invention has been made in consideration of the above-mentioned circumstances , and can appropriately determine a default rate and a default rate of loss, and a subjective factor of a bank with respect to a statistically estimated value. and an object that you identify estimates added.

  Furthermore, the present invention provides an information processing apparatus, an information processing method, and a program thereof that can easily include subjective factors such as banks in estimated values such as “default rate” and “loss rate at default” obtained by a statistical method. The purpose is to do.

This onset Ming is a process or the information processing apparatus to provide support of the process for obtaining the credit risk of receivables from loans, and input means to enter the receivable information, which is information about the previous SL claims, wherein based on the receivable information input by the input means, storing means stored is information about the attributes of the borrower before Symbol receivables are debtors risk characteristics debtor risk characteristic data issues containing specific characteristic value item for and for transactions risk characteristics is information about the type and contract of financial instruments that use by referring to the argument risk characteristics data collected includes a different characteristic value items when performing the loan stored in the storage means, wherein identify combination of the characteristic values of the debtor risk profile and the transaction risk characteristics, based on the combination of the characteristic values of the transaction risk characteristics specified above obligor risk characteristics, stored in the storage means Is in a pre-Symbol obligor risk characteristics are a combination of the characteristic values of the transaction risk characteristics, by referring to the Classification data to be associated with the classification corresponding to the default incidence and default time loss in the claims a segment specifying means for specifying the classification, based on the segment specified by the segment specific hand stage, the estimated value specifying means for specifying an estimate of the default incidence and default time loss in the claims When the change of the correspondence between the classification and the combination of the characteristic value of the obligor risk characteristic and the transaction risk characteristic is instructed via the classification setting screen, the change of the indicated association is performed. And a section changing means for changing the section of the section data .

  As a result, the default rate of default of the receivable can be determined appropriately according to the obligor risk characteristics and the transaction risk characteristics.

Further, the present invention is an information processing method in an information processing apparatus that performs processing for obtaining credit risk of a loan due to financing or supports the processing, and an input step of inputting claim information that is information related to the claim; On the basis of the claim information input in the input step, debtor risk characteristic data including characteristic values for each item of the debtor risk characteristic, which is information relating to the loan destination attribute of the claim stored in the storage means, and With reference to transaction risk characteristic data including characteristic values for each item for transaction risk characteristics that are information related to the types of financial products and contract details used when making the loan stored in the storage means, the debtor A combination of the characteristic values of the risk characteristic and the transaction risk characteristic is identified, and the characteristic of the identified obligor risk characteristic and the transaction risk characteristic is specified. Based on the combination of values, the combination of the characteristic value of the obligor risk characteristic and the transaction risk characteristic stored in the storage means, the default rate of occurrence and the default loss rate in the claim and the default A category identification step for identifying the category by referring to category data corresponding to a category corresponding to the time loss rate, and based on the category identified in the category identification step, the default rate of occurrence in the claim and the Associating the estimated value specifying step for specifying the estimated value of the default rate at default and the combination of the classification and the characteristic value of the obligor risk characteristic and the transaction risk characteristic via the classification setting screen A division change step of changing the division of the division data in response to the change of the designated association when the change of the division is instructed And features.

The present onset Ming program causes a computer to perform a process or support of the process for obtaining the credit risk of loans financed, input means for inputting a receivable information, which is information related to the claims, by the input means Based on the input credit information, the debtor risk characteristic data including the characteristic value for each item and the storage means are stored for the debtor risk characteristic, which is information related to the loan destination attribute of the bond stored in the storage means. The transaction risk characteristic data including item-specific characteristic values for transaction risk characteristics, which are information related to the types of financial products and contract details used when the loan is made, and the debtor risk characteristics and the A combination of the characteristic value with the transaction risk characteristic is specified, and a rating is based on the combination of the characteristic value with the specified debtor risk characteristic and the transaction risk characteristic. The combinations of the characteristic values of the obligor risk characteristic and the transaction risk characteristic stored in the means are classified into categories corresponding to the default rate, default rate, and default rate Based on the category identification means for identifying the category by referring to the associated category data, and the category identified by the category identification means, the default value of the default rate and the default loss rate for the claim When the change of the correspondence between the classification and the combination of the characteristic value of the obligor risk characteristic and the transaction risk characteristic is instructed via the estimated value specifying means for specifying the classification setting screen, It is made to function as a classification change means for changing the classification of the classification data in accordance with the instructed change of association .

According to the onset bright, default rates and default time loss can be appropriately seek, and, that identifies the estimated value by adding a subjective element of the bank with respect to statistically obtained estimates be able to.

Embodiments of the present invention will be described below.
First, as an information processing apparatus (credit risk calculation apparatus) according to an embodiment of the present invention, “default rate” and “loss rate at default” are appropriately obtained based on information on bonds, and “credit risk” in the new BIS regulations is determined. An information processing apparatus that supports the calculation of “ FIG. 1 is a diagram illustrating a functional configuration example of an information processing apparatus according to an embodiment of the present invention. In the following description, the information processing apparatus of this embodiment is referred to as a credit risk calculation apparatus. In addition, as an example, the receivable in this embodiment is a receivable (retail) loaned to an individual by a bank.

  In FIG. 1, reference numeral 1 denotes a credit risk calculation apparatus according to this embodiment, for example, a computer terminal that is not connected to a network. That is, the hardware configuration of the credit risk calculation device 1 is the same as that of a normal computer terminal. For example, a main body including a CPU (Central Processing Unit) and a memory (ROM, RAM, and hard disk), a mouse, a keyboard, and the like The input device and a display device such as a liquid crystal display. Each function shown in FIG. 1 is realized by the CPU executing a program.

  The credit risk calculation apparatus 1 in FIG. 1 calculates “credit risk” in the new BIS regulations. The new BIS regulations define capital adequacy ratio = capital adequacy / (credit risk + market risk + operational risk). Specifically, the credit risk calculation apparatus 1 estimates a “default rate” and a “loss rate at default” of the receivable in order to obtain “credit risk” of the receivable loaned by the bank to the individual. Here, the default rate (PD: Probability of Default) is the probability that the credit will default. Further, the loss rate at default (LGD: Loss Given Default) is a probability that the defaulted debt cannot be recovered.

  The credit risk calculation apparatus 1 estimates the “default rate” and “loss rate at default” of a receivable, and substitutes it into a risk weight function together with the amount of the receivable (remaining loan amount), thereby obtaining a risk asset (“credit risk”). The loan balance after consideration) is used to calculate the capital adequacy ratio under the new BIS regulations. The credit risk calculation apparatus 1 of the present embodiment is characterized in that a reliable “credit risk” can be estimated by appropriately estimating a “default rate” and a “loss rate at default” of a bond.

  Reference numeral 11 denotes a control unit that controls the flow of data in the credit risk calculation apparatus 1 and each unit. A database 12 stores an obligor risk characteristic table 12a, a transaction risk characteristic table 12b, a pool category setting table 12c, and a parameter estimation result table 12d. These obligor risk characteristic table 12a, transaction risk characteristic table 12b, pool category setting table 12c, and parameter estimation result table 12d are stored in the database 12 for each “default rate” and “loss rate at default” of the bond. Has been.

  FIG. 2 is a diagram illustrating a configuration example of the obligor risk characteristic table 12a, the transaction risk characteristic table 12b, and the pool category setting table 12c regarding the “loss rate at default”. The configurations of the obligor risk characteristic table 12a, the transaction risk characteristic table 12b, and the pool category setting table 12c relating to the “default rate” may be the same as or different from those in FIG. In particular, the configuration of the pool category setting table 12c sets the pool category so that the “default rate” is different. That is, it is assumed that the division of FIG. 2 is a division obtained by dividing the groups having a difference in the “loss rate at default” and grouping the groups having no difference.

  The obligor risk characteristic table 12a shown in FIG. 1 is information related to a loan destination of a receivable, and is information related to an attribute of an individual of the loan destination (hereinafter referred to as a debtor). Specifically, the obligor's attribute information is information on multiple items such as the obligor's job type, age, annual income, assets, gender, and family structure, and each item is divided into two or more ranks. . And the code | cord | chord (obligor risk characteristic subcode) which identifies the combination of each rank of each item is provided.

  In the example of the obligor risk characteristic table 12a regarding the “loss rate at default” shown in FIG. 2, the item “job class” has three ranks of LOW risk, MID risk, and HIGH risk, and the item “age”. Has 4 ranks of 30 years old or younger, 31-40 years old, 41-50 years old, 51 years old or older. The codes A01 to A03, A11 to A13, and A21 to A24 are given according to the combination of the ranks of the items. The information stored in the obligor risk characteristic table 12a shown in FIG. 1 is not limited to the above information, and the obligor's attribute information is necessary for estimating the obligor's ability to pay receivables. Or it is suitable including the information of the item used as a reference, and the information of arbitrary ranking in the item.

  The transaction risk characteristic table 12b shown in FIG. 1 is information on the types of financial products and contract details used when a loan is made. Specifically, the information related to the type of financial product is information for identifying a financial product handled by a bank, such as a mortgage loan, a car purchase loan, or a personal loan. In addition, the information on the contract content includes information on the interest rate and interest rate method, payment start date, elapsed years, number of delinquencies, number of repayments, information on collateral, presence of past arrears, and information on guarantors. In addition, information (such as the number of elapsed years and the number of repayments) specified in the numerical range among the information on the contract contents is classified into a plurality of ranges. The interest rate and interest rate method may be determined by the type of financial product in addition to the contract details.

  The example of the transaction risk characteristic table 12b regarding “loss rate at default” shown in FIG. 2 includes an item of “product type” for storing a code for specifying the type of financial product and an item of “elapsed years”. In the item “Elapsed years”, categorization of ˜6 years, 7 years to 15 years, 15 years to 4 years to 12 years is performed. A code (transaction risk characteristic subcode) is assigned to each combination of classification of “product type” and “elapsed years”. The information stored in the transaction risk characteristic table 12b shown in FIG. 1 is not limited to the information described above. As the transaction risk characteristic information, a loan method (which financial product is used is assumed. As long as the information is related to the contract, it is preferable to include various information.

  The pool category setting table 12c in FIG. 1 is a table in which a specific pool category is associated with a combination of a debtor risk characteristic management unit and a transaction risk characteristic management unit. As shown in FIG. 2, the pool category setting table 12c regarding the “loss rate at default” is a table in which a combination of the above two codes (obligor risk characteristic subcode and transaction risk characteristic subcode) is associated with a specific pool category. It is. In FIG. 2, the same estimated value of “loss rate at default” is estimated for bonds having the obligor risk characteristic subcode and the transaction risk characteristic subcode associated with the same pool category. Specifically, an estimated value of “loss rate at default” corresponding to each pool classification is defined in a parameter estimation result table 12d described later.

  The parameter estimation result table 12d in FIG. 1 is a table in which each pool classification is associated with estimated values of “default rate” and “loss rate at default”. FIGS. 3A and 3B are diagrams showing examples of parameter estimation result tables of PD (default rate) and LGD (loss rate at default). As shown in FIG. 3A, an estimated PD value (%) is associated with a PD pool category. Further, as shown in FIG. 3B, an estimated value (%) of LGD is associated with the LGD pool category.

Above, the description about the database 12 is finished, and the description of other functions in FIG. 1 is continued.
In FIG. 1, reference numeral 13 denotes a data input processing unit for inputting information relating to a claim for which “credit risk” is to be obtained. Specifically, as information necessary for specifying an estimated value of PD (default rate) and LGD (loss rate at default), information on the subject loan, the obligor risk characteristic table 12a and the transaction Information regarding each item of the risk characteristic table 12b is input. In the example of FIG. 2, information (for example, HIGH risk), age class (for example, 30 years old or younger), financial product code (for example, 1103), and elapsed years specified from the occupation of the debtor. Information such as (for example, up to 6 years) is input. Note that the specific input processing by the data input processing unit 13 may be input processing from an input device such as a keyboard, or input processing such as reading from a recording medium on which the information is recorded.

  14 is a classification specifying processing unit, which refers to the obligor risk characteristic table 12a and the transaction risk characteristic table 12b on the basis of information about each item input by the data input processing unit 13 and refers to the creditor risk characteristic subcode. By specifying the transaction risk characteristic subcode, the pool classification of PD (default rate) and LGD (default loss rate) in the pool classification setting table 12c is specified.

  In the example of FIG. 2, for example, if the occupation class is “HIGH risk” and the age class is “30 years or younger”, the classification specifying processing unit 14 specifies creditor risk characteristic subcode = A21. . Further, for example, if the code of the financial product is “1103” and the elapsed year is “˜6 years”, the category identification processing unit 14 identifies the transaction risk characteristic subcode = B11. Then, the category identification processing unit 14 refers to the pool category setting table 12c, and the LGD (loss rate at default) corresponding to the creditor risk characteristic subcode = A21 and the transaction risk characteristic subcode = B11 = PB11. Is identified. The classification specifying processing unit 14 also specifies the PD (default rate) pool classification by the same process.

  Reference numeral 15 denotes a parameter identification processing unit, which is based on the PD (default rate) and LGD (default loss rate) pool categories identified by the category identification processing unit 14 as shown in FIG. Referring to Fig. 4, the estimated values of PD (default rate) and LGD (default loss rate) are specified. Reference numeral 16 denotes a BIS processing unit, which takes into account “credit risk” using a risk weight function based on PD (default rate) and LGD (default loss rate) estimates obtained by the parameter identification processing unit 15. To calculate the capital adequacy ratio according to the new BIS regulations.

  With the configuration described above, the credit risk calculation apparatus 1 according to the present embodiment has the appropriate PD (default rate) and LGD (default loss rate) values in consideration of the debtor risk characteristics and transaction risk characteristics in retail claims. Can be estimated. As a result, it is possible to accurately obtain a “credit risk” indicating the possibility that the loan money in the retail loan cannot be collected. In particular, when the capital ratio according to the new BIS regulations is obtained, the capital risk ratio reflecting the accurate “credit risk” can be easily obtained by using the credit risk calculating apparatus 1 of the present embodiment.

Next, the processing operation of the credit risk calculation apparatus 1 shown in FIG. 1 will be described.
FIG. 4 is a flowchart showing the processing operation of the credit risk calculating apparatus 1 shown in FIG. As shown in FIG. 4, in step S <b> 1, the data input processing unit 13 performs an input process of necessary data of a bond that is a target for which “credit risk” is requested in the new BIS regulations.

  Next, in step S2, the category identification processing unit 14 refers to the obligor risk characteristic table 12a and the transaction risk characteristic table 12b on the basis of the data input by the data input processing unit 13, and performs the creditor risk characteristic sub- By specifying the code and the transaction risk characteristic subcode and referring to the pool classification setting table 12c based on the code and the transaction risk characteristic subcode, the pool classification of PD (default rate) and LGD (loss rate at default) is specified.

  Next, in step S3, the parameter identification processing unit 15 refers to the parameter estimation result table 12d based on the PD and LGD pool categories identified by the category identification processing unit 14, and estimates the PD and LGD values (parameters). )

  Next, in step S4, the BIS processing unit 16 obtains a risk asset that takes “credit risk” into account based on the PD and LGD estimation values obtained by the parameter identification processing unit 15, and complies with the new BIS regulations. Calculate capital adequacy ratio.

In the present embodiment, the credit risk calculation apparatus 1 is configured by a single computer terminal, but the function shown in FIG. 1 may be realized by a system via a network. For example, a configuration is conceivable in which input data is received via a network, or a database server that manages the database 12 is provided independently, and the database server is accessed via the network.

Next, an embodiment for constructing the above-described database 12 will be described.
FIG. 5 is a diagram illustrating a functional configuration example of an information processing apparatus (data table construction apparatus) that constructs the database 12 illustrated in FIG. 1. In FIG. 5, reference numeral 3 denotes a data table construction device according to the present embodiment, for example, a computer terminal that can be connected to the network 4. The hardware configuration of the data table construction device 3 in FIG. 5 is the same as that of the credit risk calculation device 1 in FIG.

  The data table construction device 3 shown in FIG. 5 can communicate with the credit risk calculation device 1 shown in FIG. That is, it is assumed that the credit risk calculation apparatus 1 in FIG. 1 further includes a function for connecting to the network 4. Further, the data table construction device 3 stores the obligor risk characteristic table 12a, the transaction risk characteristic table 12b, the pool category setting table 12c, and the parameter estimation result table 12d (in the database 12 of the credit risk calculation device 1 via the network 4. Hereinafter, it is simply referred to as an information table).

  Reference numeral 31 denotes a control unit that controls the flow of data in the data table construction device 3 and each unit. 32 is a receivable information database for information on PD (default rate) and LGD (default loss rate) in the past, information on obligors, financial products, and contracts (hereinafter referred to as receivable information). Store. The bond information is also stored in the bond information database 2 which is an external device. The data table construction device 3 can access the bond information database 2 via the network 4.

  Reference numeral 33 denotes a data acquisition processing unit, which acquires receivable information as a past record from the receivable information database 32 and the receivable information database 2 described above. Reference numeral 34 denotes an item extraction processing unit that extracts information as items of the obligor risk characteristic table 12a and the transaction risk characteristic table 12b from the bond information acquired by the data acquisition processing unit 33. Further, the item extraction processing unit 34 refers to the obligor risk characteristic determination table and the transaction risk characteristic determination table (hereinafter simply referred to as a determination table), and specifies the value and rank (characteristic value) of each item. For example, the item extraction processing unit 34 determines the items of the PD (default rate) and LGD (loss rate at default) debtor risk characteristic table 12a and transaction risk characteristic table 12b from various information included in the bond information. This information is extracted, and each item is classified and classified using a determination table. For example, the occupation layer described above can be classified into three stages from LOW risk to HIGH risk according to the type of occupation by referring to the determination table. Similarly, the age and the like can be classified in an appropriate range of about 10 years old as described above. As described above, the items and characteristic values of the obligor risk characteristic table 12a and the transaction risk characteristic table 12b are determined separately for PD (default rate) and LGD (loss rate at default).

  A classification determination processing unit 35 combines the characteristic values of each item in the obligor risk characteristic table 12a and the transaction risk characteristic table 12b extracted by the item extraction processing unit 34, and assigns them to specific pool classifications by PD and LGD. Process. Thereby, the pool classification setting table 12c is configured. Each pool category is associated with an estimated value of a predetermined PD or LGD as shown in FIG. Here, a specific example of the allocation process will be described. For example, if the default rate of a certain obligor risk characteristic and transaction risk characteristic item and class combination is 6 to 15%, PD pool category P001: PD estimated value = Assign to 10%. Do the following process. Similarly, if the default rate is 16 to 25%, PD pool category P002: PD estimated value = 20%, and if the default rate is 26 to 35%, PD pool category P003: PD estimated value = 30%,. The allocation process is performed as described above. However, if the estimated value is the same, it does not have to be the same pool category, but if you want to review it later or change the category range or some estimated value depending on the type of receivable or the type of financial product. It is preferable to prepare and collect them in a certain unit.

  Reference numeral 36 denotes a classification determination processing unit that determines whether the PD pool classification and the LGD pool classification determined by the classification determination processing unit 35 are significant. Specifically, the category determination processing unit 36 determines whether there is a predetermined difference in the estimated PD value or the estimated LGD value between different categories. In this embodiment, the PD and LGD pool divisions are determined, but other data may be used. For example, a withdrawal amount of an empty frame called CCF (Credit Conversion Factor) is used. It is a ratio that increases until the default time, and data that is obtained from the additional withdrawal amount / initial vacancy may be used. Even in the case of CCF, similarly to PD and LGD, the obligor risk characteristic table 12a, transaction risk characteristic table 12b, pool category setting table 12c, and parameter estimation result table 12d are created and the same processing is performed.

  37 is a section edit screen processing section, which displays a section area edit screen for displaying the section area determined by the section determination processing section 35 in a editable state by the user on the display screen of the data table construction device 3. . FIG. 7 is a diagram showing an example of a divided area editing screen in the present embodiment. As shown in FIG. 7, in the segmented area editing screen 70, items of transaction risk characteristics are arranged in the vertical direction, and items of creditor risk characteristics are arranged in the horizontal direction. In addition, pool classifications PA01, PA12, PB11, and PC01 are illustrated. In the partition area editing screen 70, the boundary lines and areas of these pool sections PA01, PA12, PB11, and PC01 can be changed by a user's mouse operation or the like. That is, in this embodiment, the pool classification is specified by statistical processing based on the past data actually financed, but there are cases where it is better to change the classification due to various circumstances such as changes in the situation. come. Some of them want to reflect the subjective factors of the bank. Therefore, in this embodiment, it is devised so that the user can change the classification as needed while using the classification specification based on statistical processing as a base. The partition edit screen processing unit 37 updates and displays the partition region edit screen 70 in accordance with this change, and reflects the change in the contents of the pool partition setting table 12c. As described above, the final pool classification setting table 12c is determined.

  In FIG. 7, the pool sections PA01, PA12, PB11, and PC01 are all divided into rectangular areas, but this is an example, and the sections may be specified in other forms. For example, an uneven shape may be used, and furthermore, one section may exist in several places.

  Reference numeral 38 denotes an information reflection processing unit, which is based on information about the obligor risk characteristic table 12a and the transaction risk characteristic table 12b extracted by the item extraction processing unit 34, and processing such as the classification determination processing unit 35 and the classification editing screen processing unit 37. Information related to the determined pool category setting table 12c is transmitted to the credit risk calculation apparatus 1 via the network 4 to request to be reflected in the database 12 of the credit risk calculation apparatus 1.

  The parameter processing unit 39 uses parameters (PD and LGD data) stored in the parameter estimation result table 12d based on the information related to the pool segment setting table 12c determined by the processing of the segment determination processing unit 35, the segment editing screen processing unit 37, and the like. Update the estimate). In the above-described embodiment, an example in which the boundary line or area of the pool partition is changed by the user's mouse operation on the partitioned region edit screen 70 is not limited to this example. Since the pool category setting table 12c of FIG. 2 is shown visually, the pool category may be changed by editing the pool category setting table 12c.

Next, the processing operation of the data table construction device 3 shown in FIG. 5 will be described.
FIG. 6 is a flowchart showing the processing operation of the data table construction device 3 shown in FIG. As shown in FIG. 6, first, in step S <b> 11, the data acquisition processing unit 33 acquires bond information related to retail with a past PD or LGD track record.

  Next, in step S12, the item extraction processing unit 34 extracts information that becomes items of the obligor risk characteristic table 12a and the transaction risk characteristic table 12b from the bond information acquired by the data acquisition processing unit 33, and makes a determination. Refer to the table and specify the characteristic value of each item. Next, in step S <b> 13, the category determination processing unit 35 performs a process of determining the PD pool category and the LGD pool category by combining the characteristic values of each item of the risk characteristics extracted by the item extraction processing unit 34.

  Next, in step S14, the category determination processing unit 36 determines whether the PD pool category and the LGD pool category determined by the category determination processing unit 35 are significant categories. Here, if there is a category that determines that each category is not a significant category, the process returns to step S13, and the category is determined again for that portion. If it is determined that each category is a significant category, the category editing screen processing unit 37 displays the category region editing screen 70 on the display screen of the data table construction device 3 in step S15. As a result, the user can edit the PD pool category and the LGD pool category on the category editing screen 70.

  Next, in step S16, the information reflection processing unit 38, the information regarding the obligor risk characteristic table 12a and the transaction risk characteristic table 12b extracted by the item extraction processing unit 34, the classification determination processing unit 35, and the classification editing screen processing unit 37. A process of reflecting the information related to the pool category setting table 12c determined by such processes to the database 12 via the network 4 is performed. Further, the parameter processing unit 39 updates the parameters stored in the parameter estimation result table 12d based on the information regarding the pool category setting table 12c determined by the processing of the category determination processing unit 35, the category editing screen processing unit 37, and the like. .

  As described above, according to the data table construction device 3 of the present embodiment, the debtor risk characteristic table 12a, the transaction risk characteristic table 12b, the pool category setting table 12c, and the parameter estimation result table are automatically stored in the database 12. 12d can be constructed. In other words, based on past loans accumulated in the database, statistical processing was performed to classify risks related to debtors and risks related to transaction forms as combinations thereof, thereby creating an index with little error based on actual values.

  In addition, in order to make it easy to grasp this index, by providing the segmented area editing screen 70, the user can visually recognize the PD pool segment and the LGD pool segment, and further on the segmented area editing screen 70, Categories can be edited directly. Thereby, the obligor risk characteristic table 12a, transaction risk characteristic table 12b, and pool category setting table 12c that are more optimal for each user can be constructed.

  By using the database 12 constructed as described above, the credit risk calculation apparatus 1 according to the present embodiment enables an appropriate PD (default rate) and LGD in consideration of debtor risk characteristics and transaction risk characteristics in retail loans. The value of (default loss rate) can be estimated according to user needs. As a result, it is possible to accurately obtain a “credit risk” indicating the possibility that the loan money in the retail loan cannot be collected. In particular, when calculating the capital ratio in accordance with the new BIS regulations, the credit risk calculation device 1 of the present embodiment is used to calculate the “credit risk” that reflects the user's needs and to calculate the capital ratio. Can be used.

  In this embodiment, the data table construction device 3 and the credit risk calculation device 1 are connected via the network 4. However, the present invention is not limited to this, and the information table constructed by the data table construction device 3 can be carried. You may make it store in a medium and read the said recording medium with the credit risk calculation apparatus 1. FIG.

  Moreover, although each process part of the credit risk calculation apparatus 1 of FIG. 1 and the data table construction apparatus 3 of FIG. 5 demonstrated the case where it implement | achieves when CPU runs a program, some or all of these each process part is demonstrated. May be configured by dedicated hardware.

  In addition, a program for realizing the functions of the respective processing units of the credit risk calculation apparatus 1 in FIG. 1 and the data table construction apparatus 3 in FIG. 5 is recorded on a computer-readable recording medium and recorded on this recording medium. Each processing may be performed by reading the program into a computer system and executing the program. Here, the “computer system” includes an OS and hardware such as peripheral devices. Specifically, after a program read from a storage medium is written to a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, the program is read based on the instructions of the program. It includes the case where the CPU of the function expansion board or function expansion unit performs part or all of the actual processing, and the functions of the above-described embodiments are realized by the processing.

  The “computer-readable recording medium” refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, and a CD-ROM, and a storage device such as a hard disk built in the computer system. Further, the “computer-readable recording medium” refers to a volatile memory (RAM) in a computer system that becomes a server or a client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line. In addition, those holding a program for a certain period of time are also included.

  The program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the “transmission medium” for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.

  The program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

A program product such as a computer-readable recording medium in which the above program is recorded can also be applied as an embodiment of the present invention. The above program, recording medium, transmission medium, and program product are included in the scope of the present invention.
The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes designs and the like that do not depart from the gist of the present invention.

It is a figure which shows the function structural example of the information processing apparatus in one Embodiment of this invention. It is a figure which shows the structural example of the obligor risk characteristic table 12a regarding the "loss rate at the time of default", the transaction risk characteristic table 12b, and the pool division | segmentation setting table 12c. It is a figure which shows the parameter estimation result table example of PD (default rate) and LGD (loss rate at the time of default). It is a flowchart which shows the processing operation of the credit risk calculation apparatus 1 shown in FIG. It is a figure which shows the function structural example of the information processing apparatus (data table construction apparatus) which builds the database 12 shown in FIG. It is a flowchart which shows the processing operation of the data table construction apparatus 3 shown in FIG. It is a figure which shows the division area edit screen example in this embodiment.

Explanation of symbols

1 Credit risk calculation device (information processing device)
2 Debt information database 3 Data table construction device 4 Network 11 Control unit 12 Database 12a Obligor risk characteristic table 12b Transaction risk characteristic table 12c Pool classification setting table 12d Parameter estimation result table 13 Data input processing section 14 Classification identification processing section 15 Parameter identification Processing unit 16 BIS processing unit 31 Control unit 32 Claim information database 33 Data acquisition processing unit 34 Item extraction processing unit 35 Item determination processing unit 36 Classification determination processing unit 37 Classification editing screen processing unit 38 Information reflection processing unit 40 Transmission / reception processing unit 70 Classification Area edit screen

Claims (8)

A process or the information processing apparatus to provide support of the process for obtaining the credit risk of loans financed,
And input means to enter the credit information which is information relating to the previous Symbol receivables,
Based on the receivable information input by said input means, debtor risk profile debtor risk characteristic bonds containing a different characteristic value item for which is information on borrowers attribute before Symbol receivables stored in the storage means transactions risk characteristics is information about the type and contract financial instruments utilized when performing the loan stored in the data and storing means with reference to the pull risk characteristics data collected includes a different characteristic value items, A combination of the characteristic values of the obligor risk characteristic and the transaction risk characteristic is specified, and stored in the storage means based on the combination of the characteristic value of the identified obligor risk characteristic and the transaction risk characteristic. Subdivision of the combination of the characteristic values of the previous SL debtor risk profile and the transaction risk characteristics, associated to a segment in accordance with the default incidence and default time loss in the claims which are A segment specifying means for specifying the segment by referring to the data,
Based on the classification specified in the classification particular hand stage, the estimated value specifying means for specifying an estimate of the default incidence and default time loss in the claims,
When the change of the correspondence between the classification and the combination of the characteristic value of the obligor risk characteristic and the transaction risk characteristic is instructed via the classification setting screen, the change of the instructed correspondence is performed. In response, an information processing apparatus comprising: a section changing unit that changes the section of the section data . Before Symbol estimate specifying means, and said section are stored in the storage means, determining a correspondence between any one of a plurality of estimates to estimate the default incidence and default time loss in the loan estimate by referring to the value data, claims, characterized in that said section based on said section identified by the specific hand stage, to identify an estimate of the default incidence and default time loss in the claims The information processing apparatus according to 1. Based on the estimated value of the default incidence and default time loss in the claims specified in the estimate specific hand stage, credit risk calculation means for calculating a numerical value related to credit risk of the loans using risk weight function The information processing apparatus according to claim 1, further comprising: When the partitioned data to be associated with the classification corresponding to the prior SL default incidence and default time loss rate and the first segment data, the classification data to be associated with the classification corresponding to the default time loss in the loan first The classification data associated with the classification according to the credit conversion coefficient in the bond is the third classification data, and at least one of the first to third classification data is stored in the storage means. ,
The classification specifying means refers to at least one of the first to third classification data based on a combination of the characteristic values of the specified debtor risk characteristics and the transaction risk characteristics. Specify one of the first to third categories,
The estimated value specifying means, based on at least one of the first to third categories specified by the category specifying means, the estimated value of the default rate of occurrence in the claim, the loss at default The information processing apparatus according to claim 1, wherein one of an estimated value of a rate and an estimated value of the credit conversion coefficient is specified . Before Symbol a first section, a first estimate data defining the correspondence between any one of a plurality of estimates to estimate the default incidence in the claims,
Second estimated value data defining a correspondence between the second category and any one of a plurality of estimated values for estimating the default loss rate in the claim;
Third estimated value data defining a correspondence between the third category and any one of a plurality of estimated values for estimating the credit conversion coefficient in the bond;
Is further stored in the storage means,
The estimated value specifying means specifies the estimated value by referring to the first to third estimated value data and based on the first to third classifications specified by the classification specifying means.
The information processing apparatus according to claim 4 . Based on the estimated values identified in the previous Symbol estimate specifying means, according to claim 5, further comprising a credit risk calculation means for calculating a numerical value related to credit risk of the loans using risk weight function Information processing device. An information processing method in an information processing apparatus for performing processing for obtaining credit risk of a loan due to financing or supporting the processing,
  An input step of inputting claim information which is information on the claim;
  On the basis of the claim information input in the input step, debtor risk characteristic data including characteristic values for each item of the debtor risk characteristic, which is information relating to the loan destination attribute of the claim stored in the storage means, and With reference to transaction risk characteristic data including characteristic values for each item for transaction risk characteristics that are information related to the types of financial products and contract details used when making the loan stored in the storage means, the debtor The debt stored in the storage means based on the combination of the characteristic value of the identified debtor risk characteristic and the transaction risk characteristic by identifying a combination of the characteristic value of the risk characteristic and the transaction risk characteristic The combination of the characteristic value of the risk characteristic of the person and the transaction risk characteristic is defined as the default rate of occurrence and the default loss rate and the default loss for the claim. A classification specifying step of specifying the segment by referring to the partitioned data to be associated with the classification corresponding to the rate,
  Based on the classification specified in the classification specifying step, an estimated value specifying step for specifying an estimated value of the default rate of occurrence and the default rate of loss in the claim;
  When the change of the correspondence between the classification and the combination of the characteristic value of the obligor risk characteristic and the transaction risk characteristic is instructed via the classification setting screen, the change of the instructed correspondence is performed. In response, a category change step for changing the category of the category data;
  An information processing method comprising: A computer for processing for obtaining credit risk of a loan due to loan or supporting the processing,
  Input means for inputting claim information, which is information about the claim,
  On the basis of the claim information input by the input means, debtor risk characteristic data including characteristic values for each item of the debtor risk characteristics, which is information relating to the loan recipient attributes stored in the storage means, and With reference to transaction risk characteristic data including characteristic values for each item for transaction risk characteristics that are information related to the types of financial products and contract details used when making the loan stored in the storage means, the debtor The debt stored in the storage means based on the combination of the characteristic value of the identified debtor risk characteristic and the transaction risk characteristic by identifying a combination of the characteristic value of the risk characteristic and the transaction risk characteristic A combination of the characteristic values of the risk characteristic of the person and the transaction risk characteristic, the default rate of occurrence and the default rate of loss and the default rate of loss A segment specifying means for specifying the segment by referring to the partitioned data to be associated with the corresponding piecewise,
  Based on the classification specified by the classification specifying means, estimated value specifying means for specifying an estimated value of the default rate and the default loss rate in the claim,
  When the change of the correspondence between the classification and the combination of the characteristic value of the obligor risk characteristic and the transaction risk characteristic is instructed via the classification setting screen, the change of the instructed correspondence is performed. In response, a category changing means for changing the category of the category data;
A program characterized by making it function.

Images