Information processing device and information processing method

Abstract

Provided is an information processing device that can calculate an interpretation index for each explanatory variable in the process of calculating a risk score, thereby making it possible to reduce the calculation load. [Solution] An accounting audit support device 1 detects risks detectable from accounting-related data using a machine learning model. The system is equipped with a learning model generation unit 32 that uses a plurality of training records combining a plurality of explanatory variables and a target variable selected from the financial data to generate a shape function indicating the relationship between each explanatory variable and the target variable as a machine learning model, a learning model storage unit 41 that stores the shape function for each explanatory variable generated by the learning model generation unit, and a risk calculation unit 34 that calculates an interpretation index for each explanatory variable using the shape function for a new record that is to be subject to risk detection, and calculates a risk score from the plurality of interpretation indexes.

Description

[Technical field]

[0001] The present invention relates to an information processing device and an information processing method that detect risks such as accounting fraud that can be detected from accounting-related data by using a machine learning model. [Background technology]

[0002] In accounting audit work such as internal audits and external audits, the contents of accounting documents such as financial statements are analyzed and checked to see if there are any fraudulent transactions, such as fictitious transactions (see Patent Documents 1 and 2, etc.).

[0003] Also, as disclosed in Patent Literature 3, there are attempts to use the results of machine learning to evaluate the risk of accounting fraud through computer processing. Here, the calculations performed in the learning process of machine learning are complex, and while there is an advantage in that highly accurate evaluation can be realized, it is often difficult for humans to easily understand the basis for the evaluation.

[0004] Therefore, in the information processing device of Patent Document 3, it is possible to determine which account items, which are explanatory variables used in machine learning, are abnormal for the evaluation output by the machine learning model by calculating a SHAP value. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 7052135 [Patent Document 2] JP 2019-179531 A [Patent Document 3] Patent No. 7216854 Summary of the Invention [Problem to be solved by the invention]

[0006] However, in the information processing device described in Patent Document 3, in addition to the process of bagging the outputs from multiple weak learners to calculate an index (risk score) indicating inappropriateness, a process of calculating a SHAP value for interpreting which account item is abnormal is required. And, since the amount of calculation for the theoretical value of this SHAP value increases exponentially according to the number of explanatory variables, in practice, an approximate calculation is performed.

[0007] Therefore, an object of the present invention is to provide an information processing device and an information processing method that are capable of calculating an interpretation index for each explanatory variable in the process of calculating a risk score, thereby making it possible to reduce the calculation load. [Means for solving the problem]

[0008] In order to achieve the above-mentioned object, the information processing device of the present invention is an information processing device that detects risks detectable from accounting-related data using a machine learning model, and is characterized in that it includes a learning model generation unit that uses a plurality of training records that combine a plurality of explanatory variables and a target variable selected from the accounting-related data to generate a shape function indicating the relationship between each of the explanatory variables and the target variable as a machine learning model, a learning model memory unit that stores the shape function for each of the explanatory variables generated by the learning model generation unit, and a risk calculation unit that calculates an interpretation index for each of the explanatory variables using the shape function stored in the learning model memory unit for a new record that is to be subject to risk detection, and calculates a risk score from the plurality of interpretation indexes.

[0009] Here, the risk score can be calculated based on an intercept value set when generating the machine learning model and a value of the interpretation index for each of the explanatory variables. The explanatory variables used to generate the shape function may include a group of items of the accounting-related data that are affected by the content of the risk. The accounting-related data may be financial data, and the risk to be detected may be accounting fraud.

[0010] Moreover, the invention of an information processing method is an information processing method for detecting risks detectable from accounting-related data using a machine learning model through computer processing, and is characterized in that it includes the steps of: using a plurality of training records in which a plurality of explanatory variables are selected from the accounting-related data and combined with a target variable, generating shape functions indicating the relationship between each of the explanatory variables and the target variable through machine learning; calculating an interpretation index for each of the explanatory variables using the generated shape functions for new records that are to be subject to risk detection; and calculating a risk score based on the calculated plurality of interpretation indexes. Effect of the Invention

[0011] The information processing device and information processing method of the present invention thus configured use a plurality of training records each combining a plurality of explanatory variables and a target variable selected from accounting-related data to generate a machine learning model represented by a shape function for each explanatory variable. Then, for a new record to be subjected to risk detection, an interpretation index for each explanatory variable is calculated using the shape function, and a risk score is calculated from the values ​​of the plurality of interpretation indexes.

[0012] In this way, since the interpretation index for each explanatory variable is calculated in the process of calculating the risk score, there is no need to perform a separate calculation after calculating the risk score, and the calculation load can be reduced. [Brief description of the drawings]

[0013] [Figure 1] 1 is a block diagram illustrating a configuration of an accounting audit support device according to an embodiment of the present invention. [Diagram 2] 1 is a flowchart illustrating a process flow of an accounting audit support method according to an embodiment of the present invention. [Diagram 3] FIG. 1 is a diagram for explaining an outline of an EBM model, in which (a) is an explanatory diagram showing a schematic diagram of a flow up to calculation of a score, and (b) is an explanatory diagram showing an example of a shape function. [Figure 4] FIG. 2 is an illustrative diagram illustrating an example data set of training records. [Diagram 5] FIG. 1 is an explanatory diagram illustrating explanatory variables of training records used in machine learning. [Figure 6] FIG. 11 is a diagram illustrating shape functions, where (a) is an explanatory diagram of the shape function and output of explanatory variable x1, (b) is an explanatory diagram of the shape function and output of explanatory variable x2, and (c) is an explanatory diagram of the shape function and output of explanatory variable x3. [Figure 7] 13 is an explanatory diagram illustrating an example of a calculation result of an interpretation index of a new record; [Figure 8] FIG. 11 is an explanatory diagram illustrating a process of calculating a risk score from an interpretation index. [Figure 9] FIG. 2 is an explanatory diagram illustrating a data set of grouped training records in the first embodiment. [Figure 10] FIG. 11 is an explanatory diagram illustrating calculation results of interpretation indices and risk scores of new records in the first embodiment. [Figure 11] FIG. 11 is a diagram for explaining the process of checking the interpretation index within a variable group of interest, in which (a) is an explanatory diagram illustrating an example of explanatory variables included in the variable group, and (b) is an explanatory diagram illustrating an example of the calculation results of the interpretation index for each explanatory variable. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Fig. 1 is a block diagram illustrating the configuration of an accounting audit support device 1 which is an information processing device according to this embodiment, and Fig. 2 is a flowchart illustrating the process flow of an accounting audit support method which is an information processing method according to this embodiment.

[0015] The accounting audit support device 1 of this embodiment is an information processing device for detecting the risk of accounting fraud using a machine learning model for new records (for example, by fiscal year and month) of a company that is the subject of an accounting audit such as an internal audit or an external audit. Here, detecting the risk of accounting fraud includes both the detection of fraud at the present time and the prediction of future fraud.

[0016] In the accounting audit support device 1 of this embodiment, as shown in FIG. 1, a calculation processing unit 3 performs computer processing based on data input from an input device 2, a memory unit 4, etc., and displays detection results, etc. on a display device 5, etc.

[0017] The calculation processing unit 3 of the accounting audit support device 1 is mainly composed of a training data setting unit 31 that sets training data to be used for machine learning, a learning model generation unit 32 that generates a machine learning model using training records included in the training data, an interpretation index calculation unit 33 that calculates interpretation indexes for new records, a risk score calculation unit 34 that calculates risk scores from the interpretation indexes, and a display control unit 35 that controls the display contents on the display device 5. Here, the interpretation index calculation unit 33 and the risk score calculation unit 34 correspond to the risk calculation unit.

[0018] The input device 2 for inputting various data is a data input means connected to or equipped on a personal computer (PC), a notebook computer, a tablet terminal, a wearable terminal, a smartphone, etc. Examples of the input device 2 include a keyboard, a mouse, a touch panel, a touch pad, a scanner, a microphone for voice input, a camera, etc.

[0019] On the other hand, the display device 5 may be a liquid crystal display, an organic EL (Electro-Luminescence) display, a printer, or the like.

[0020] Furthermore, the storage unit 4 is a storage medium for recording training data used in processing in the arithmetic processing unit 3, data generated by arithmetic processing, etc., and corresponds to a hard disk, a solid state drive (SSD), a flash memory (such as an SD memory card), a magnetic disk, an optical disk, etc. Also, an external online storage (cloud storage) such as a server connected via a network can be used as the storage unit 4. In the following, the area of ​​the storage medium for storing the machine learning model generated by the learning model generation unit 32 will be described by distinguishing it by assigning it the reference symbol "learning model storage unit 41."

[0021] The arithmetic processing unit 3 is configured with a central processing unit (CPU), a micro-processing unit (MPU), a graphics processing unit (GPU), etc. as computer hardware, and is equipped with memories such as random access memory (RAM) and read only memory (ROM).

[0022] The arithmetic processing unit 3 can execute various functions by applications (programs) installed in a computer. In addition, a server connected via a network such as the Internet can execute part or all of the arithmetic processing unit 3. The network is composed of part or all of the Internet, a Wide Area Network (WAN), a wired Local Area Network (LAN), a wireless LAN (Wi-Fi), a provider device, a wireless base station, a dedicated line, etc.

[0023] As described above, the calculations performed in the learning process of machine learning are becoming more complex, and it is often difficult for humans to easily understand the basis for results such as risk assessment values ​​(scores) detected using machine learning models. Therefore, in the accounting audit support device 1 and accounting audit support method of the present embodiment, an interpretation index is calculated for each explanatory variable, making it possible to understand the influence of each explanatory variable on the score and to use it in business decision-making.

[0024] Specifically, a method called Explainable Boosting Machine (EBM) is applied. In this method, an estimation model called an EBM model is first generated by machine learning, and the interpretation index and score (risk score) of each explanatory variable are calculated using the EBM model. Figure 3 is a diagram for explaining the outline of the EBM model.

[0025] To create an EBM model, as shown on the left side of Figure 3(a), multiple explanatory variables (x1, x2, x3) used to predict the dependent variable are selected, and multiple training records combining the selected explanatory variables and dependent variable are used to generate a shape function indicating the relationship between each explanatory variable and dependent variable as a machine learning model. Specifically, the value of the intercept (β0) described below and the shape function of each explanatory variable are estimated. Figure 3(b) is an explanatory diagram illustrating an example of the shape function f1(x1) estimated for the dependent variable x1.

[0026] The shape function is nonlinear and is generated for each explanatory variable, resulting in a model (f1(x1), f2(x2), f3(x3)) that combines shallow decision trees that use only one corresponding explanatory variable. It is also possible to create a shape function that incorporates an interaction term between explanatory variables. For example, when using an interaction term between two explanatory variables, a model (f 1,2 (x1,x2)).

[0027] Once an EBM model has been created, it can be used to calculate the interpretation index and risk score of a new record that is the target of risk detection. For example, the data (x1 (a) ,x2 (a) ,x3 (a) ) into the EBM model, the interpretation index (f1(x1 (a) ), f2(x2 (a) ), f3(x3 (a) The risk score is calculated by the intercept (β0) and the output of the shape function of each explanatory variable (interpretation index (f1(x1 (a) ), f2(x2 (a) ), f3(x3 (a) ))) can be obtained by, for example, performing a logistic transformation.

[0028] The method of interpreting the results output using the EBM model is to output the shape function of each explanatory variable for each record, and to regard this output as the interpretation index for that explanatory variable for that record. The interpretation index is given in terms of how much the explanatory variable increases or decreases the log odds (logit) of the score (probability of fraud). As mentioned above, the interpretation index (f 1,2 (x1,x2) can also be calculated.

[0029] A feature of the EBM method is that the interpretation index is calculated in advance during the score calculation process, so there are no additional development and maintenance costs for calculating the interpretation index. Also, no additional calculation time is required just to calculate the interpretation index. Furthermore, the impact of the explanatory variable value on the score is given by a nonlinear shape function, so the model is highly flexible. And the impact on the score when the explanatory variable value is 0 is determined by a specific impact based on the shape function (for example, f1(x1 (a) =0), and the impact does not become 0.

[0030] In addition, with the EBM method, even if there are outliers in the explanatory variables, they are not adversely affected when creating the model or calculating the score. Also, for unknown data (such as new categorical values ​​that do not exist at the time of model learning) of categorical variables (such as the manager's address or educational background), the influence of the explanatory variable on the score can be eliminated by setting the output value of the explanatory variable to 0 (for example, f1(x1=U)=0). Furthermore, for missing data of numerical variables, the influence of the explanatory variable on the score can be eliminated by setting the output value of the explanatory variable to 0 (for example, f1(x1=NA)=0).

[0031] In order to apply such an EBM method, the training data setting unit 31 of the calculation processing unit 3 extracts and uses a plurality of training records combining a plurality of explanatory variables and a target variable from the accounting-related data (records) stored in the storage unit 4 that can be used for machine learning. For example, if the accounting-related data is financial data, some of the items listed in the financial statements are selected as explanatory variables. Then, the record combining the selected explanatory variables and target variable is set as the training record to be used for generating a machine learning model.

[0032] FIG. 4 is an explanatory diagram illustrating an example of a training record dataset. Records from the same company can be used as separate training records if their accounting fiscal years and months are different. A training record is a combination of the values ​​of explanatory variables (x1-x3) selected from the items in the financial statements and a fraud label y assigned to that training record. In short, it is training data in which the solution when the values ​​of the explanatory variables (x1-x3) are input is the fraud label y. Here, the fraud label y assigned to records in which accounting fraud has occurred is set to 1, and the fraud label y assigned to records in which there has been no accounting fraud is set to 0.

[0033] Figure 5 shows examples of items that are considered to be effective as explanatory variables for training records used in machine learning when detecting accounting fraud risks. In Figure 5, items that can be explanatory variables listed in financial statements are grouped according to the following criteria:

[0034] First, when creating groups, we decided to select groups from the perspective of grouping explanatory variables at the financial indicator level that are affected by common fraudulent content.

[0035] Specifically, when inventory-related fraud occurs, the inventory turnover period, inventory net asset ratio, and inventory total asset ratio are all affected, so these explanatory variables are combined into one group called "inventory valuation."

[0036] In addition, items such as the rate of change in accounts receivable, sales growth rate, and the ratio of the rate of change in accounts receivable divided by the sales growth rate were all included in the "sales overstatement evaluation" group. Furthermore, items such as the goodwill net asset ratio and the goodwill balance exceeding operating profit were all included in the "goodwill evaluation" group.

[0037] Each item listed in these financial statements can be used as an explanatory variable, and as will be described later, the above-mentioned groups can also be selected as explanatory variables.

[0038] The training data setting unit 31 can set records including the selected explanatory variables and objective variables from among the records that are accounting-related data stored in the storage unit 4 as training records to be used for machine learning. For example, the data set to be used for training is set by sampling from all usable records (data set). Bootstrap sampling or the like can be used as a sampling method.

[0039] The learning model generation unit 32 creates an EBM model using the training records set by sampling. In the following explanation, a data set (see FIG. 4) is taken as an example, in which the three selected explanatory variables X (x1, x2, x3) are combined with the objective variable (fraudulent label y).

[0040] First, a base model F(X)=β is created to model the relationship between explanatory variables X(x1, x2, x3) and the objective variable (false label y) using a data set of sampled training records. This β is the intercept of the EBM model. Examples of β include the mean value of the objective variable in the case of a regression model, and the log odds of the objective variable in the case of a classification model.

[0041] Then, the model F(X) based on the intercept β is updated based on the information (training records) of each explanatory variable. In detail, the following steps (a) to (c) are carried out in order for each explanatory variable.

[0042] (a) Creating a decision tree for x1 Create a decision tree for x1 by setting the explanatory variables and objective variables as follows. Explanatory variable: x1 only Response variable: Residual y - F(X) between the actual response variable y and the model's predicted result F(X) This decision tree is a model that expresses the relationship between explanatory variable x1 and objective variable y. The created decision tree is multiplied by an arbitrary learning rate to give h1(x1), and F(X) is updated by adding h1(x1) to the original model F(X). F(X) := F(X) + h1(x1)

[0043] (b) Creating a decision tree for x2 A decision tree is created by setting the explanatory variable to x2 and the objective variable to the residual y - F(X), and multiplying this by an arbitrary learning rate to obtain h2(x2). F(X) is then updated by adding h2(x2) to the original model F(X). F(X) := F(X) + h2(x2)

[0044] (c) Creating a x3 decision tree A decision tree is created by setting the explanatory variable to x3 and the objective variable to the residual y - F(X), and multiplying this by an arbitrary learning rate to obtain h3(x3). F(X) is then updated by adding h3(x3) to the original model F(X). F(X) := F(X) + h3(x3)

[0045] The above steps (a) to (c) are repeated until the value of the loss function between the model prediction result F(X) and the objective variable y converges. Examples of loss functions include mean square error in the case of a regression model and cross entropy in the case of a classification model. In this way, the decision tree model h for each explanatory variable is iterated for the number of times. n (x n ) is created, where n=1,2,3.

[0046] Therefore, for each explanatory variable, a decision tree model h n (x n) are integrated. One way to integrate them is to average all the decision trees created. The integration results in a shape function for each explanatory variable generated using multiple training records.

[0047] The above-mentioned process of setting training records by sampling and generating shape functions from the training records is repeated M times. As a result, M shape functions h n (x n ) will be created.

[0048] Therefore, M shape functions h n (x n ) to obtain the integrated shape function f n (x n ) The integration method here can also be the averaging of all the decision trees created. The integrated shape function (integrated shape function f n (x n )) can be said to represent the relationship between each explanatory variable and the objective variable (see Figure 6).

[0049] The shape function (integrated shape function f n (x n )) are stored in the learning model storage unit 41. Then, they are read and used during calculations by the interpretation index calculation unit 33, which will be described later, and the like.

[0050] The interpretation index calculation unit 33 calculates the shape function (integrated shape function f n (x n )) to calculate the interpretation index for each explanatory variable. Figure 6 shows the integrated shape function f n (x n ) is an explanatory diagram illustrating an example.

[0051] Fig. 6(a) is an explanatory diagram illustrating a shape function f1(x1) of explanatory variable x1 and a value of 0.3 output for a new record. Fig. 6(b) is an explanatory diagram illustrating a shape function f2(x2) of explanatory variable x2 and a value of -0.2 output for a new record. Fig. 6(c) is an explanatory diagram illustrating a shape function f3(x3) of explanatory variable x3 and a value of 0.1 output for a new record.

[0052] The values ​​output by the shape functions for each of these explanatory variables become the values ​​of the interpretation indexes for each explanatory variable. Figure 7 is an explanatory diagram showing an example of the calculation results of the interpretation indexes for a new record. When the interpretation indexes are calculated for each explanatory variable in this way, it becomes possible to grasp the degree of influence of each explanatory variable.

[0053] The risk score calculation unit 34 calculates a risk score based on the interpretation index of each explanatory variable calculated by the interpretation index calculation unit 33 and the value of the intercept (β0: see FIG. 7). FIG. 8 is an explanatory diagram illustrating a process of calculating a risk score from an interpretation index. The fraud score, which is the risk score, can be obtained by, for example, logistic transformation using a logistic function.

[0054] For example, the transformation can be performed using the following logistic function σ(z): σ(z) = 1 / (1+exp(-z)) Risk of fraud score = 1 / (1+exp(-(-0.5+0.3-0.2+0.1)) = 0.426

[0055] The display control unit 35 controls the output format (see Figure 8) of the interpretation index calculated by the interpretation index calculation unit 33 and the fraud score (risk score) calculated by the risk score calculation unit 34 to the display device 5.

[0056] The process flow of the accounting audit support method according to this embodiment will be described below with reference to the flowchart shown in FIG.

[0057] First, in step S1, several items are selected as explanatory variables from among the items listed in the financial statements, which are financial data. Then, a record in which the selected explanatory variables and the objective variable are combined is set as a training record to be used for generating a machine learning model (step S2).

[0058] Specifically, the training records are set by reading all data sets that can be used for machine learning from the data stored in the storage unit 4, and setting the training records by sampling.

[0059] In the next step S3, an EBM model is created using the training records set by sampling. As described above, the setting of the training records by sampling in step S2 and the generation of the EBM model in step S3 are repeated a preset number of times (M times in the above example).

[0060] Then, in step S4, each interpretation index for each explanatory variable of the new record to be audited is calculated. The example in Figure 7 shows that the new record to be audited is financial data extracted from the financial statements of Company Z with the fiscal year ending March 2023.

[0061] For new records, the value of the interpretation index output from the shape function f1(x1) of the explanatory variable x1 was calculated to be 0.3, the value of the interpretation index output from the shape function f2(x2) of the explanatory variable x2 was calculated to be -0.2, and the value of the interpretation index output from the shape function f3(x3) of the explanatory variable x3 was calculated to be 0.1. In addition, the value of the intercept β0 was calculated to be -0.5.

[0062] In step S5, a risk score is calculated based on the values ​​of the interpretation index and the intercept values ​​of each explanatory variable calculated in this manner. As shown in Fig. 8, the fraud score (risk score) is calculated as 0.426 by logistic transformation. The analysis results obtained by computer processing as shown in Fig. 8 are displayed on the display device 5.

[0063] This fraud score can be considered an assessment of the risk of accounting fraud, with 1 being the presence of accounting fraud. However, it is difficult to specifically examine the possible methods by which accounting fraud may be committed using this number alone.

[0064] Therefore, those performing accounting audits can refer to the interpretation indicators for each explanatory variable calculated in the process of calculating the fraud score to understand which items of financial data they should focus on, which will enable them to take specific audit actions for new records.

[0065] Next, the operation of the accounting audit support device 1 and the accounting audit support method according to this embodiment will be described. The accounting audit support device 1 and accounting audit support method of this embodiment, configured as described above, use multiple training records that combine multiple explanatory variables and target variables selected from accounting-related data, and generate a machine learning model represented by a shape function for each explanatory variable in the learning model generation unit 32.

[0066] Then, for new records that are to be subject to risk detection, the interpretation index calculation unit 33 calculates interpretation indexes for each explanatory variable using a shape function, and the risk score calculation unit 34 calculates a risk score from the values ​​of the multiple interpretation indexes and the intercept values.

[0067] In this way, since the interpretation index for each explanatory variable is calculated in the process of calculating the risk score, there is no need to perform a separate calculation after calculating the risk score, and the calculation load can be reduced.

[0068] Furthermore, even if the person performing the accounting audit cannot easily understand the basis for the prediction based on the fraud score (risk score value) alone, the influence of the financial data items that have become explanatory variables can be grasped from the value of the interpretation index, making it possible to use it in business decision-making.

[0069] In addition, with the accounting audit support device 1 and accounting audit support method of this embodiment, the computational load can be reduced, so that a machine learning model using many variables can be created to improve the accuracy of the model, and variables that have a significant effect on the fraud score can be instantly identified, thereby making the audit procedure more efficient.

[0070] Furthermore, by applying the EBM method, the negative impact of outliers in the training records can be reduced, so the model can be created and the fraud scores calculated without being influenced by the financial figures of a very small number of very large companies. Also, the model is not influenced by extreme outliers in division indicators (such as turnover period). EXAMPLES

[0071] Another embodiment of the accounting audit support device 1 according to the embodiment described above will be described below with reference to Figures 9 to 11. Note that the same terms or the same reference numerals will be used to describe the same or equivalent parts as those described in the embodiment described above.

[0072] In the above embodiment, one explanatory variable is associated with one item of financial data. However, as described in the above embodiment, multiple items of financial data can be grouped together and one variable group can be treated as one explanatory variable.

[0073] In the description of the embodiment given above with reference to FIG. 5, a variable group has been exemplified that is created from the viewpoint of grouping explanatory variables that are affected by a common fraudulent content, among explanatory variables at the financial indicator level.

[0074] Fig. 9 is an explanatory diagram illustrating a data set of grouped training records in Example 1. The groups (a, b, c) in Fig. 9 correspond to groups such as "inventory valuation," "sales overstatement valuation," and "goodwill valuation" illustrated in Fig. 5, and the explanatory variables (x1-x6) correspond to items of financial data belonging to each group.

[0075] The process of creating an EBM model for each variable group and calculating interpretation indicators is basically the same as the process for each item described above. In other words, multiple financial data items are grouped together into variable groups, and an EBM model is created for each variable group. Then, interpretation indicators are calculated for each variable group using shape functions.

[0076] By grouping in this way, when a fraud occurs, it becomes possible to prevent the importance of explanatory variables related to the fraud from being dispersed among each other, resulting in a decrease in the importance of the group that should be the focus of attention. In other words, it becomes possible to create and interpret an EBM model by eliminating multicollinearity between similar features (financial indicators) without excluding one of them, and without overlapping explanatory variable information between variable groups.

[0077] FIG. 10 is an explanatory diagram illustrating the calculation results of the interpretation index and risk score of the new record in Example 1. That is, for the new record of the audit target company z whose fiscal year ends in March 2023, the interpretation index and fraud score that are the output of the shape function of each variable group are shown. As can be seen from this result, the interpretation index is output on a variable group basis, and the influence on the fraud score can be grasped on a variable group basis.

[0078] When the interpretation index is calculated for each variable group in this way, it is also possible to further specify a variable group of interest and create and calculate an EBM model for each individual variable in the group. FIG. 11 is a diagram explaining the process of checking the interpretation index in the variable group of interest. FIG. 11(a) is an explanatory diagram illustrating an example of a data set of training records of explanatory variables (x3, x4, x5) included in the group b of interest. FIG. 11(b) is an explanatory diagram illustrating an example of the calculation result of the interpretation index output by the shape function of each explanatory variable included in group b.

[0079] When grouping is performed in this manner, it becomes possible to identify the variable group of interest based on the output of the shape function of the variable group, and further to create an EBM model using only the items that make up the variable group of interest and to calculate interpretation indices, etc.

[0080] Specifically, in the event of inventory-related fraud, the significance of a group of inventory valuations that includes the inventory turnover period, the net inventory asset ratio, and the total inventory asset ratio can be assessed, and further, interpretation indicators for the inventory turnover period, the net inventory asset ratio, and the total inventory asset ratio can be calculated, respectively.

[0081] Other configurations and functions and effects are substantially the same as those of the above-described embodiment, and therefore description thereof will be omitted.

[0082] Although the embodiments of the present invention have been described in detail above with reference to the drawings, the specific configurations are not limited to these embodiments and examples, and design changes that do not deviate from the gist of the present invention are included in the present invention.

[0083] For example, in the above embodiment, a case has been described in which financial data is used as accounting-related data to detect the risk of accounting fraud, but the present invention is not limited to this. In addition to financial data, accounting-related data includes corporate governance data, bank account transaction history, credit card transaction history, etc. Risks that can be detected from these data include money laundering, fraudulent card use, and deterioration of business performance (bankruptcy, default, etc.).

[0084] In addition, in the above embodiment, the items listed in the financial statements are used as explanatory variables, but this is not limited to this, and various data items or groups listed in various accounting documents can be used as explanatory variables.

[0085] Furthermore, in the above embodiment, a method for calculating a risk score by performing a general logistic transformation on the sum of an intercept and an interpretation index of each explanatory variable has been described. However, this is not limited to this, and any method, such as a method for further adjusting the logistic transformation, can be applied to calculate a risk score from multiple interpretation indexes. [Explanation of symbols]

[0086] 1: Accounting audit support device (information processing device) 32: Learning model generation unit 33: Interpretation index calculation unit 34: Risk score calculation section 41: Learning model memory unit

Claims

1. An information processing device that detects risks detectable from accounting-related data using a machine learning model, a learning model generation unit that uses a plurality of training records each combining a plurality of explanatory variables and a target variable selected from the accounting-related data to generate a shape function indicating a relationship between each of the explanatory variables and the target variable as a machine learning model; a learning model storage unit in which the shape function for each of the explanatory variables generated by the learning model generation unit is stored; a risk calculation unit that calculates an interpretation index for each of the explanatory variables by the shape function stored in the learning model storage unit for a new record that is a risk detection target, and calculates a risk score from a plurality of the interpretation indexes, The explanatory variables used to generate the shape function include a variable group obtained by grouping together items of the accounting-related data that have a common content of the risk that they are affected by, The learning model generation unit generates a shape function for each variable group of the variable groups, The information processing device is characterized in that the risk calculation unit calculates an interpretation index for each of the variable groups.

2. The information processing device according to claim 1 , wherein the risk score is calculated based on an intercept value set when the machine learning model is generated and a value of the interpretation index for each of the explanatory variables.

3. An information processing device as described in claim 1 or 2, characterized in that the items of the accounting-related data that constitute the variable group having the largest value of the interpretation index for the variable group unit are used as explanatory variables, and further generate a shape function, calculate an interpretation index, and calculate a risk score.

4. 3. The information processing apparatus according to claim 1, wherein the accounting-related data is financial data, and the risk to be detected is accounting fraud.

5. An information processing method for detecting risks detectable from accounting-related data using a machine learning model by computer processing, comprising: generating, by machine learning, a shape function indicating a relationship between each of the explanatory variables and the objective variable using a plurality of training records in which a plurality of explanatory variables are selected from the accounting-related data and combined with the objective variable; A step of calculating an interpretation index for each of the explanatory variables by the generated shape function for a new record that is a risk detection target; and calculating a risk score based on the calculated plurality of interpretation indicators; The explanatory variables used to generate the shape function include a variable group obtained by grouping together items of the accounting-related data that have a common content of the risk that they are affected by, The information processing method is characterized in that, for the variable groups, a shape function is generated for each variable group, and an interpretation index is calculated for each variable group.

6. The information processing method described in claim 5, characterized in that the items of the accounting-related data that constitute the variable group having the largest value of the interpretation index for the variable group unit are used as explanatory variables, and further a shape function is generated, an interpretation index is calculated, and a risk score is calculated.

Images