Output device

Abstract

To properly support the sales and other activities conducted by financial institutions.SOLUTION: An output device comprises an acquisition unit that acquires information according to a customer's financial situation and an output unit that outputs values according to the customer's financial needs in accordance with the information acquired by the acquisition unit.SELECTED DRAWING: Figure 10

Description

[Technical Field]

[0001] The present invention relates to an output device, an output method, and a program. [Background technology]

[0002] This technology is known to be used by financial institutions such as credit unions and banks.

[0003] For example, Patent Document 1 discloses a system for predicting the probability of bankruptcy using qualitative data. According to Patent Document 1, the system includes the steps of selecting data suitable for model construction from the evaluation data and converting the selected data items into items suitable for data mining, and using the converted data to perform a logistic regression analysis after defining the target event as "bankruptcy" within the target period, and selecting variables that have explanatory power for "bankruptcy" and a method for processing the variables. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2003-216804 Summary of the Invention [Problem to be solved by the invention]

[0005] Financial institutions have a need to provide funding and management support at the right time. However, simply predicting the probability of bankruptcy is not enough to fully meet these needs. This has created the challenge of making it difficult to provide appropriate support for financial institutions' sales and other activities.

[0006] Therefore, an object of the present invention is to provide an output device, an output method, and a program that can solve the above-mentioned problems. [Means for solving the problem]

[0007] In order to achieve this object, an output device according to one embodiment of the present disclosure comprises: an acquisition unit that acquires information according to the financial situation of a customer; an output unit that outputs a value according to the customer's financial needs in accordance with the information acquired by the acquisition unit; have The structure is as follows.

[0008] Furthermore, an output method according to another aspect of the present disclosure includes: The information processing device Obtain information according to the customer's financial situation, Outputs a value according to the customer's financial needs based on the information obtained. The structure is as follows.

[0009] Furthermore, a program according to another aspect of the present disclosure includes: In the information processing device, Obtain information according to the customer's financial situation, Outputs a value according to the customer's financial needs based on the information obtained. It is a program for realizing the processing. [Effects of the Invention]

[0010] According to the above-mentioned configurations, financial institutions can be appropriately supported. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram for explaining an overview of a prediction device described in the present disclosure. [Figure 2] FIG. 1 is a block diagram illustrating an example of the configuration of a prediction device. [Figure 3] FIG. 10 is a diagram illustrating an example of scenario information. [Figure 4] FIG. 10 is a diagram illustrating an example of output. [Figure 5] FIG. 10 is a diagram illustrating an example of output. [Figure 6] FIG. 10 is a diagram illustrating an example of output. [Figure 7]10 is a flowchart illustrating an example of the operation of the prediction device. [Figure 8] FIG. 10 is a block diagram illustrating another example configuration of the prediction device. [Figure 9] FIG. 10 is a diagram illustrating an example of a hardware configuration of a prediction device according to a second embodiment of the present disclosure. [Figure 10] FIG. 1 is a block diagram illustrating an example of the configuration of a prediction device. [Figure 11] 10 is a flowchart illustrating an example of the operation of the prediction device. DETAILED DESCRIPTION OF THE INVENTION

[0012] [First embodiment] A first embodiment of the present disclosure will be described with reference to FIGS. 1 to 8. FIG. 1 is a diagram for explaining an overview of a prediction device 100. FIG. 2 is a block diagram showing an example of the configuration of the prediction device 100. FIG. 3 is a diagram showing an example of scenario information 142. FIGS. 4 to 6 are diagrams showing example outputs. FIG. 7 is a flowchart showing an example of the operation of the prediction device 100. FIG. 8 is a block diagram showing another example of the configuration of the prediction device 100. Note that in the present disclosure, the drawings may be associated with one or more embodiments.

[0013] In the first embodiment of the present disclosure, as shown in FIG. 1, a prediction device 100 will be described, which is an output device (information processing device) that predicts and outputs a customer's financial needs based on information corresponding to the customer's financial situation, such as financial statement information. For example, the prediction device 100 trains a model in advance for each scenario that defines information to be used for prediction among various information corresponding to the customer's financial situation. Then, the prediction device 100 acquires information to be used for prediction indicated by the selected scenario in response to receiving a selection of a scenario to be used for prediction. Thereafter, the prediction device 100 inputs the acquired information into a corresponding model to acquire a score, which is a value corresponding to the customer's financial needs. Note that the prediction device 100 may have at least one scenario.

[0014] In the present disclosure, as an example, a case will be described in which the prediction device 100 makes a prediction using logistic regression analysis, which is a statistical method capable of explaining and predicting the probability of a "binary outcome (objective variable)" occurring from several factors (explanatory variables). For example, the prediction device 100 uses, as explanatory variables, information according to the customer's financial situation, such as the ratio of sales to the previous year and the sales growth rate to the accounts receivable growth rate. Then, the prediction device 100 predicts the probability of a binary outcome, "whether or not there is a need for funds," occurring using the above-mentioned explanatory variables. As described above, the type of information according to the customer's financial situation that is used as an explanatory variable can vary depending on the scenario. Furthermore, the prediction device 100 is not limited to the above-mentioned example, and may predict the need for funds using a model that has been trained by any supervised learning method or the like.

[0015] Fig. 2 shows an example configuration of the prediction device 100. Referring to Fig. 2, the prediction device 100 has, as main components, for example, an operation input unit 110, a screen display unit 120, a communication interface unit 130, a storage unit 140, and a calculation processing unit 150.

[0016] 2 illustrates an example in which the functions of the prediction device 100 are realized using one information processing device. However, the prediction device 100 may be realized using a plurality of information processing devices, for example, on the cloud. Furthermore, the prediction device 100 may not include some of the components exemplified above, such as not having the operation input unit 110 or the screen display unit 120, or may have components other than those exemplified above.

[0017] The operation input unit 110 is made up of operation input devices such as a keyboard, a mouse, etc. The operation input unit 110 detects operations of the operator operating the prediction device 100 and outputs the operations to the calculation processing unit 150.

[0018] The screen display unit 120 is composed of a screen display device such as a liquid crystal display, an organic EL (electro-luminescence) display, etc. The screen display unit 120 can display various information stored in the storage unit 140 on the screen in response to instructions from the arithmetic processing unit 150.

[0019] The communication interface unit 130 is composed of a data communication circuit etc. The communication interface unit 130 performs data communication with an external device connected via a communication line.

[0020] The storage unit 140 is a storage device such as a hard disk or memory. The storage unit 140 stores processing information and programs 145 required for various processes in the calculation processing unit 150. The programs 145 are read into the calculation processing unit 150 and executed to realize various processing units. The programs 145 are read in advance from an external device or recording medium via a data input / output function such as the communication interface unit 130, and are stored in the storage unit 140. Main information stored in the storage unit 140 includes, for example, financial status information 141, scenario information 142, model information 143, and forecast result information 144.

[0021] The financial situation information 141 includes information corresponding to the financial situation of the customer. For example, the financial situation information 141 includes at least a portion of financial statements, financial indicator data, and other information related to the financial situation of the customer. The financial situation information 141 may include any information, such as customer financial data such as sales, profits, and balance trends, transaction data, deposits and withdrawals to and from the main account, and loan balances. The financial situation information 141 is acquired in advance by accepting information through operations using the operation input unit 110, acquiring information from an external device via the communication interface unit 130, or the like, and is stored in the storage unit 140.

[0022] The scenario information 142 defines information to be used for prediction among various types of information according to the financial situation of the client. In other words, the scenario information 142 can indicate information to be used as explanatory variables for each scenario. The scenario information 142 is acquired in advance by accepting information through an operation using the operation input unit 110, acquiring information from an external device via the communication interface unit 130, or the like, and is stored in the storage unit 140.

[0023] FIG. 3 illustrates an example of information included in the scenario information 142. Referring to FIG. 3, the scenario information 142 associates, for example, a scenario name, input information, a conditional expression, and model information. Here, the scenario name is information for identifying the scenario. The scenario name may be any identifier for identifying the scenario. The input information indicates information used as explanatory variables in the associated scenario, among information corresponding to the customer's financial situation. For example, the first line in FIG. 3 indicates that the scenario name "Increased Working Capital 1" uses, as explanatory variables, "sales growth rate vs. accounts receivable growth rate," "CCC (cash conversion cycle) growth rate vs. previous year," and "accounts receivable turnover period." The conditional expression is information used when performing logistic regression analysis to learn regression coefficients, such as when assigning correct data to each sample data during learning. For example, the conditional expression can indicate the values ​​and relationships of the explanatory variables that indicate "there is a need for funds." For example, the conditional expression may be expressed as follows: "1: Sales vs. Previous Year > 105%," "2: Sales Growth Rate vs. Accounts Receivable Growth Rate > 105%, "CCC vs. Previous Year > 105%, "Accounts Receivable Turnover Period > 0.3 months," "Condition = (1 or 2 or 3) & 4," etc. For example, in the case of the above conditional expression, if any of "Sales vs. Previous Year," "Sales Growth Rate vs. Accounts Receivable Growth Rate," and "CCC vs. Previous Year" meet the condition, and "Accounts Receivable Turnover Period" also meets the condition, the prediction device 100 assigns correct answer data of "Financial Need Present" to the sample data. Furthermore, if the above conditions are not met, the prediction device 100 can assign correct answer data of "Financial Need Not." Furthermore, the model information may indicate, for example, the identifier of the model used when inputting explanatory variables and calculating the score.

[0024] The above is an example of information included in the scenario information 142. The input information may indicate that information from multiple years, such as the previous and current periods, is to be used. In other words, the conditions, such as which year's values ​​to use as explanatory variables and how many years' worth of values ​​to use, may differ for each scenario. Furthermore, the scenario information 142 may be composed of only a portion of the above examples, such as not including conditional expressions, or may include information other than those listed above.

[0025] The model information 143 includes information about the trained model, such as parameters such as pre-trained regression coefficients. As described above, the model information 143 may include parameters for each scenario. For example, the model information 143 may associate a model identifier with parameters such as regression coefficients. The model information 143 is acquired in advance from an external device or the like via the communication interface unit 130 or the like, and is stored in the storage unit 140.

[0026] The model included in the model information 143 has been trained in advance by, for example, performing a logistic regression analysis in an external device using a plurality of data items that associate sample data including values ​​of corresponding explanatory variables with correct answer data indicating whether or not there is a need for funds. Here, the sample data may be generated in an external device by extracting necessary information from information similar to information corresponding to the financial situation of the client, such as the financial situation information 141, or by any other means. The correct answer data may be assigned depending on whether the sample data satisfies the above-described conditional expression, or may be assigned manually depending on the actual situation, such as whether or not there was actually a need for funds.

[0027] The prediction result information 144 includes scores, which are values ​​predicted by the prediction device 100 using explanatory variables. The prediction result information 144 may include scores for each customer and each scenario. The prediction result information 144 is updated when the result acquisition unit 154 acquires scores, etc.

[0028] The arithmetic processing unit 150 has an arithmetic device such as a CPU (Central Processing Unit) and its peripheral circuits. The arithmetic processing unit 150 reads and executes a program 145 from the storage unit 140, thereby causing the above hardware and the program 145 to work together to realize various processing units. Major processing units realized by the arithmetic processing unit 150 include, for example, a scenario selection unit 151, an input value acquisition unit 152, an input unit 153, a result acquisition unit 154, and an output unit 155.

[0029] In addition, the arithmetic processing unit 150 may have a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), an MPU (Micro Processing Unit), an FPU (Floating point number Processing Unit), a PPU (Physics Processing Unit), a TPU (Tensor Processing Unit), a quantum processor, a microcontroller, or a combination thereof, instead of the above-mentioned CPU.

[0030] The scenario selection unit 151 accepts a selection of a scenario to be subjected to score calculation from among the scenarios included in the scenario information 142. The scenario selection unit 151 may accept a selection of one or more scenarios. For example, the scenario selection unit 151 may accept a selection of a scenario in response to an operation on the operation input unit 110, or may accept a selection of a scenario in response to an instruction from an external device via the communication interface unit 130.

[0031] Note that the prediction device 100 may be configured not to accept a scenario selection, but to calculate scores for all scenarios included in the scenario information 142. In this case, the prediction device 100 may not have the function of the scenario selection unit 151.

[0032] The input value acquisition unit 152 acquires the values ​​of explanatory variables corresponding to the scenario for which a score is to be calculated, in response to, for example, the scenario selection unit 151 accepting the selection of a scenario. For example, the input value acquisition unit 152 refers to the scenario information 142 to identify explanatory variables corresponding to the selected scenario. Thereafter, the input value acquisition unit 152 acquires the values ​​of explanatory variables corresponding to the scenario, in response to, for example, the financial situation information 141.

[0033] The input value acquiring unit 152 may acquire at least some of the values ​​used as explanatory variables in response to input using the operation input unit 110, instead of acquiring them from the financial situation information 141, etc. For example, the input value acquiring unit 152 may be configured to accept, as explanatory variables, values ​​determined by settlement or the like, as well as estimated values, etc. Furthermore, the input value acquiring unit 152 may be configured to accept, as explanatory variables, any qualitative information in addition to the quantitative information exemplified above.

[0034] The input unit 153 inputs the value acquired by the input value acquisition unit 152 into a pre-trained model indicated by the model information 143. For example, the input unit 153 inputs the value acquired by the input value acquisition unit 152 into a sigmoid function whose regression coefficients have been trained in advance.

[0035] As described above, the prediction device 100 has a trained model for each scenario. Therefore, the input unit 153 can input the values ​​acquired by the input value acquisition unit 152 to the corresponding model. For example, when multiple scenarios are selected by the scenario selection unit 151, the input unit 153 may input the corresponding values ​​to the corresponding models.

[0036] The result acquisition unit 154 acquires a score, which is an output from a model according to an input by the input unit 153. When multiple scenarios are selected by the scenario selection unit 151, the result acquisition unit 154 may acquire the corresponding scores from the corresponding models. In addition, the result acquisition unit 154 can store the acquired scores in the storage unit 140 as prediction result information 144.

[0037] The output unit 155 outputs a score or the like, which is a value according to the financial needs of the client, acquired by the result acquisition unit 154. The output unit 155 may display the score or the like on the screen display unit 120, or may transmit it to an external device or the like via the communication interface unit 130.

[0038] FIG. 4 shows an example output 200 by the output unit 155. As shown in FIG. 4, the output unit 155 can output scores calculated for each scenario for each customer. For example, the output unit 155 outputs scores and the like in a prediction result display field 210 in addition to customer information such as the customer name. At least a portion of the scores corresponding to each scenario selected by the scenario selection unit 151 may be displayed in the prediction result display field 210. In addition to outputting scores and the like, the output unit 155 may also output customer financial data included in the financial status information 141, such as sales, profits, and balance trends, in a financial information display field 220, etc.

[0039] Furthermore, as shown in FIG. 5 , the output unit 155 may output, in addition to the score, information indicating the influence of each explanatory variable, which is the basis for score calculation, on the score calculation, to the influence display field 230. That is, the output unit 155 may output information, which is the basis for score calculation, along with the score. For example, the output unit 155 may output, as information indicating the influence, the value of a regression coefficient corresponding to each explanatory variable or a value obtained by multiplying the value of each explanatory variable by the regression coefficient. Furthermore, as shown in FIG. 5 , the output unit 155 may output the results of visualization processing, such as a bar graph or a line graph, to the influence display field 230. Note that the output unit 155 may display the influence display field 230 together with the prediction result display field 210 and the financial information display field 220, or may be configured to switch which of the prediction result display field 210, the financial information display field 220, the influence display field 230, or the like to be displayed, depending on an operation on the operation input unit 110, or the like.

[0040] 6, instead of outputting a score for each customer as exemplified in output example 200, the output unit 155 may be configured to output score calculation results for multiple customers for each scenario as exemplified in output example 240. For example, the output unit 155 may be configured to output the values ​​of each explanatory variable used when predicting the score and other arbitrary information in addition to the predicted score as shown in output example 240. Note that the output unit 155 may be configured to be switchable between output for each customer and output for each scenario depending on an operation on the operation input unit 110, etc.

[0041] The output unit 155 can output any one of the above examples or a combination of them.

[0042] The above is an example of the configuration of the prediction device 100. Next, an example of the operation of the prediction device 100 will be described with reference to FIG.

[0043] Fig. 7 is a flowchart showing an example of the operation of the prediction device 100. Referring to Fig. 7, the scenario selection unit 151 accepts a selection of a scenario to be subjected to score calculation from among the scenarios included in the scenario information 142 (step S110). The scenario selection unit 151 may accept the selection of one or more scenarios.

[0044] The input value acquisition unit 152 acquires values ​​to be used as explanatory variables according to the scenario selected by the scenario selection unit 151 (step S120). For example, the input value acquisition unit 152 refers to the scenario information 142 to identify explanatory variables according to the selected scenario. Thereafter, the input value acquisition unit 152 refers to the financial situation information 141 to acquire values ​​of the explanatory variables according to the scenario.

[0045] The input unit 153 inputs the value acquired by the input value acquisition unit 152 into a pre-trained model (step S130). For example, the input unit 153 inputs the value acquired by the input value acquisition unit 152 into a sigmoid function whose regression coefficient has been calculated in advance.

[0046] The result acquisition unit 154 acquires a score, which is an output from a model according to the input by the input unit 153 (step S140). When multiple scenarios are selected by the scenario selection unit 151, the result acquisition unit 154 may acquire the corresponding scores from the corresponding models.

[0047] The output unit 155 outputs the score or the like, which is a value according to the financial need of the client, acquired by the result acquisition unit 154 (step S150). The output unit 155 may display the score or the like on the screen display unit 120, or may transmit it to an external device or the like via the communication interface unit 130.

[0048] The above is an example of the operation of the prediction device 100.

[0049] As described above, the prediction device 100 includes an input value acquisition unit 152, an input unit 153, and a result acquisition unit 154. With this configuration, the result acquisition unit 154 can acquire a score, which is a value corresponding to the customer's financial needs, as a result of inputting information corresponding to the customer's financial situation, acquired by the input value acquisition unit 152 as values ​​of explanatory variables, into the model via the input unit 153. As a result, it becomes possible to determine the customer's financial needs based on the acquired score, and sales can be conducted according to the financial needs. In other words, with the above configuration, it is possible to provide appropriate support when proposing loans to customers and conducting various other sales activities.

[0050] The prediction device 100 also has various scenarios with different explanatory variables and can obtain a score for each scenario. As a result, the prediction device 100 can calculate scores according to various situations. For example, the scenario "Increased Working Capital 1" exemplified in this disclosure can address a working capital shortage due to increased sales or a working capital shortage caused by a delay in fund collection due to factors such as transaction type. It can also appropriately grasp needs even when the breakdown of sales increase depends on accounts receivable. In addition to the above-exemplified scenarios, there may be other scenarios according to various situations, such as a "scenario that predicts capital needs based on cash balances at the end of the fiscal year," a "scenario that predicts capital needs based on factors such as inventory," and a "scenario that predicts capital needs based on the ratio of accounts receivable to inventory."

[0051] The configuration of the prediction device 100 is not limited to the example shown in FIG. 2. For example, FIG. 8 shows another example configuration of the prediction device 100. Referring to FIG. 8, the calculation processing unit 150 of the prediction device 100 can have functions as a scenario creation unit 156, a relearning unit 157, a statistical processing unit 158, and the like, in addition to the configuration shown in FIG. 2, by reading and executing the program 145 from the storage unit 140. The prediction device 100 may have at least one of the new functions shown above.

[0052] The scenario creation unit 156 creates a new scenario. The scenario creation unit 156 can also learn regression coefficients and the like by performing logistic regression analysis using sample data extracted from the financial situation information 141 and the like.

[0053] For example, the scenario creation unit 156 accepts inputs such as a scenario name, information on explanatory variables used in calculating a score, a conditional expression, etc. The scenario creation unit 156 may accept the above inputs by accepting information through an operation using the operation input unit 110, by acquiring information from an external device or the like via the communication interface unit 130, etc. The scenario creation unit 156 can also store the accepted various pieces of information in the storage unit 140 as scenario information 142.

[0054] The scenario creation unit 156 also performs learning of regression coefficients and the like based on the received information. For example, the scenario creation unit 156 acquires multiple sample data by extracting values ​​of each explanatory variable received from past information included in the financial situation information 141. The scenario creation unit 156 may receive sample data using a method other than the above, such as receiving sample data from an external device via the communication interface unit 130. The scenario creation unit 156 also assigns correct answer data to each sample data based on whether the sample data satisfies the received conditional expression. For example, the scenario creation unit 156 assigns correct answer data "1" if the conditional expression is satisfied and a judgment is made that "financial needs exist," and assigns correct answer data "0" if the conditional expression is not satisfied and a judgment is made that "financial needs do not exist." The scenario creation unit 156 then standardizes the explanatory variables of each sample data and performs logistic regression analysis to identify regression coefficients in a sigmoid function. Furthermore, the scenario creation unit 156 stores the identified regression coefficients and the like in the storage unit 140 as model information 143. Note that instead of assigning correct answer data according to the conditional formula, the scenario creation unit 156 may assign correct answer data received in response to information input using the operation input unit 110 to the sample data.

[0055] Learning according to the information received by the scenario creation unit 156 may be performed at any timing. For example, the scenario creation unit 156 may start learning in response to the reception of information, or may be configured to perform learning in response to the reception at a predetermined timing, such as at night.

[0056] The relearning unit 157 re-learns the regression coefficients and the like in response to input from a sales representative of the financial institution or the like. For example, the relearning unit 157 accepts corrections to the supervised data assigned in accordance with the conditional formula in response to an operation by a sales representative of the financial institution or the like using the operation input unit 110. In response to this, the relearning unit 157 can re-learn the regression coefficients and the like so as to reflect the corrected supervised data.

[0057] The acceptance of corrections to the correct answer data by the re-learning unit 157 may be performed after actually conducting sales to a customer, or may be performed before conducting sales, etc. By performing re-learning by the re-learning unit 157 before conducting sales, etc., it is possible to calculate a score that reflects the sense of a sales representative of a financial institution, etc.

[0058] The statistical processing unit 158 ​​can perform predetermined statistical processing on the scores included in the prediction result information 144. For example, the statistical processing unit 158 ​​may perform any statistical processing, such as calculating the average value for each customer for the scores of each scenario. The statistical processing unit 158 ​​may also perform statistical processing according to the situation of the scenario, such as performing statistical processing for each scenario in a good phase and a scenario in a bad phase.

[0059] For example, the prediction device 100 may have at least some of the configurations exemplified above. The prediction device 100 may be configured to enable some of the functions exemplified above depending on the installation location of the prediction device 100, the operator operating the prediction device 100, etc.

[0060] [Second embodiment] Next, a second embodiment of the present disclosure will be described with reference to Fig. 9 to Fig. 11. Fig. 9 is a diagram illustrating an example of the hardware configuration of an output device 300. Fig. 10 is a block diagram illustrating an example of the configuration of the output device 300. Fig. 11 is a flowchart illustrating an example of the operation of the output device 300.

[0061] In a second embodiment of the present disclosure, an output device 300 will be described, which is an information processing device that predicts and outputs a customer's financial needs based on information corresponding to the customer's financial situation, such as settlement information. Fig. 9 shows an example of the hardware configuration of the output device 300. Referring to Fig. 9, the output device 300 has, as an example, the following hardware configuration. ·CPU(Central Processing Unit)301(Arithmetic unit) ROM (Read Only Memory) 302 (storage device) RAM (Random Access Memory) 303 (storage device) Programs 304 loaded into RAM 303 A storage device 305 for storing the program group 304 A drive device 306 that reads and writes data from a recording medium 310 outside the information processing device A communication interface 307 for connecting to a communication network 311 outside the information processing device Input / output interface 308 for inputting and outputting data Bus 309 connecting each component

[0062] 10 by the CPU 301 acquiring the program group 304 and executing it. The program group 304 is stored in advance in the storage device 305 or the ROM 302, for example, and is loaded into the RAM 303 or the like by the CPU 301 for execution as needed. The program group 304 may be supplied to the CPU 301 via the communication network 311, or may be stored in advance in the recording medium 310, and the drive device 306 may read out the program and supply it to the CPU 301.

[0063] 9 shows an example of the hardware configuration of the output device 300. The hardware configuration of the output device 300 is not limited to the above-described case. For example, the output device 300 may be configured with only a part of the above-described configuration, such as excluding the drive device 306. Furthermore, the CPU 301 may be a GPU or the like exemplified in the first embodiment.

[0064] The acquiring unit 321 acquires information according to the financial situation of the customer. For example, the acquiring unit 321 may acquire at least a part of financial settlement information, etc., as the information according to the financial situation of the customer.

[0065] The output unit 322 outputs a value according to the financial needs of the client in accordance with the information acquired by the acquisition unit 321. For example, the output unit 322 can output a value according to the financial needs of the client acquired by inputting the information acquired by the acquisition unit 321 into a pre-trained model.

[0066] The above is an example of the configuration of the output device 300. Next, an example of the operation of the output device 300 will be described with reference to FIG.

[0067] Fig. 11 is a flowchart showing an example of the operation of the output device 300. Referring to Fig. 11, the acquisition unit 321 acquires information according to the financial situation of the client (step S210).

[0068] The output unit 322 outputs a value according to the financial need of the customer in accordance with the information acquired by the acquisition unit 321 (step S220). For example, the output unit 322 can output a value according to the financial need of the customer acquired by inputting the information acquired by the acquisition unit 321 into a pre-trained model.

[0069] As described above, the output device 300 has an acquisition unit 321 and an output unit 322. With this configuration, the output unit 322 can output a value corresponding to the customer's financial needs, which is based on the information acquired by the acquisition unit 321. As a result, it becomes possible to determine the customer's financial needs based on the acquired value, and to conduct sales activities according to the financial needs. In other words, with the above configuration, it is possible to provide appropriate support when proposing loans to customers and conducting various other sales activities.

[0070] The output device 300 can be realized by incorporating a predetermined program into an information processing device such as the output device 300. Specifically, a program according to another aspect of the present invention is a program for causing an information processing device such as the output device 300 to realize a process of acquiring information according to a customer's financial situation and outputting a value according to the customer's financial needs in accordance with the acquired information.

[0071] In addition, the output method executed by an information processing device such as the output device 300 described above is a method in which the information processing device acquires information corresponding to the financial situation of the customer and outputs a value corresponding to the financial needs of the customer based on the acquired information.

[0072] Even if the invention is a program having the above-described configuration, or a computer-readable recording medium having the program recorded thereon, or an output method, it can achieve the same functions and effects as the above-described output device 300, and therefore can achieve the above-described object of the present disclosure.

[0073] <Additional Notes> A part or all of the above-described embodiments can be described as follows: An outline of the output device and the like according to the present invention will be described below. However, the present invention is not limited to the following configuration.

[0074] (Appendix 1) an acquisition unit that acquires information according to the financial situation of a customer; an output unit that outputs a value according to the customer's financial needs in accordance with the information acquired by the acquisition unit; have Output device. (Appendix 2) The acquisition unit acquires information according to a financial situation of a customer in accordance with a scenario that defines information to be used for prediction. 10. An output device as described in Appendix 1. (Appendix 3) a selection unit that accepts the selection of the scenario; The acquisition unit acquires information according to the financial situation of the customer according to the scenario selected by the selection unit. 10. An output device as described in Appendix 2. (Appendix 4) a result acquisition unit that acquires a value according to the customer's financial needs in accordance with a result of inputting the information acquired by the acquisition unit into a trained model; The output unit outputs a value according to the customer's financial needs acquired by the result acquisition unit. 10. The output device according to claim 1, wherein the output device is a (Appendix 5) The result acquisition unit acquires a value according to the customer's capital needs based on the result of inputting the information acquired by the acquisition unit into a sigmoid function whose regression coefficients have been learned by performing a logistic regression analysis on sample data and correct answer data. 10. An output device as described in Appendix 4. (Appendix 6) The model is trained for each scenario that defines the information used for prediction. The result acquisition unit acquires a value according to the customer's financial needs in accordance with a result of inputting the information acquired by the acquisition unit into a corresponding model. 10. An output device according to claim 4 or claim 5. (Appendix 7) a scenario creation unit that creates a scenario in response to input of information used for prediction and a conditional expression used when assigning correct data to sample data; The scenario creation unit acquires sample data according to the input information used for prediction, assigns correct answer data to the sample data acquired using the conditional expression, and performs learning using the sample data to which the correct answer data has been assigned. 10. The output device according to claim 1, wherein the output device is a (Appendix 8) The output unit outputs, together with a value according to the customer's capital needs, information that serves as a basis for calculating the value according to the customer's capital needs based on the information acquired by the acquisition unit. 10. The output device according to claim 1, wherein the output device is a (Appendix 9) The information processing device Obtain information according to the customer's financial situation, Outputs a value according to the customer's financial needs based on the information obtained. Output method. (Appendix 10) In the information processing device, Obtain information according to the customer's financial situation, Outputs a value according to the customer's financial needs based on the information obtained. A program to realize the processing.

[0075] Note that some or all of the configurations described in Supplementary Notes 2 to 8 that are dependent on the output device described in Supplementary Note 1 may also be dependent in a similar dependent relationship on the output method described in Supplementary Note 9 and the program described in Supplementary Note 10. Furthermore, not limited to Supplementary Notes 9 and 10, some or all of the configurations described as Supplements may also be dependent on various hardware, software, various recording means for recording software, or systems within the scope of the above-mentioned embodiments.

[0076] The programs described in the above embodiments and appendices may be stored in a storage device or a computer-readable recording medium, such as a portable medium such as a flexible disk, an optical disk, a magneto-optical disk, or a semiconductor memory.

[0077] Although the present invention has been described above with reference to the above-mentioned embodiments, the present invention is not limited to the above-mentioned embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. [Explanation of symbols]

[0078] 100 Prediction Device 110 Operation input section 120 Screen display section 130 Communication interface unit 140 Storage section 141 Financial Status Information 142 Scenario Information 143 Model Information 144 Prediction result information 145 Programs 150 Processing unit 151 Scenario Selection 152 Input value acquisition unit 153 Input section 154 Result acquisition part 155 Output section 156 Scenario Creation Department 157 Re-learning Section 158 Statistical Processing Unit 200 Example output 210 Prediction result display field 220 Financial information display column 230 Impact display field 240 Example output 300 Output Device 301 CPU 302 ROM 303 RAM 304 Programs 305 Storage device 306 Drive Device 307 Communication Interface 308 Input / Output Interface 309 Bus 310 Recording Media 311 Communication Network 321 Acquisition Department 322 Output section

Claims

1. an acquisition unit that acquires information according to the financial situation of a customer; an output unit that outputs a value according to the customer's financial needs in accordance with the information acquired by the acquisition unit; have Output device.

2. The acquisition unit acquires information according to a financial situation of a customer in accordance with a scenario that defines information to be used for prediction. The output device according to claim 1 .

3. a selection unit that accepts the selection of the scenario; The acquisition unit acquires information according to the financial situation of the customer according to the scenario selected by the selection unit. The output device according to claim 2 .

4. a result acquisition unit that acquires a value according to the customer's financial needs in accordance with a result of inputting the information acquired by the acquisition unit into a trained model; The output unit outputs a value according to the customer's financial needs acquired by the result acquisition unit. The output device according to claim 1 .

5. The result acquisition unit acquires a value according to the customer's capital needs based on the result of inputting the information acquired by the acquisition unit into a sigmoid function whose regression coefficients have been learned by performing a logistic regression analysis on sample data and correct answer data. The output device according to claim 4 .

6. The model is trained for each scenario that defines the information used for prediction. The result acquisition unit acquires a value according to the customer's financial needs in accordance with a result of inputting the information acquired by the acquisition unit into a corresponding model. The output device according to claim 4 .

7. a scenario creation unit that creates a scenario in response to input of information used for prediction and a conditional expression used when assigning correct data to sample data; The scenario creation unit acquires sample data according to the input information used for prediction, assigns correct answer data to the sample data acquired using the conditional expression, and performs learning using the sample data to which the correct answer data has been assigned. The output device according to claim 1 .

8. The output unit outputs, together with a value according to the customer's capital needs, information that serves as a basis for calculating the value according to the customer's capital needs based on the information acquired by the acquisition unit. The output device according to claim 1 .

9. The information processing device Obtain information according to the customer's financial situation, Outputs a value according to the customer's financial needs based on the information obtained. Output method.

10. In the information processing device, Obtain information according to the customer's financial situation, Outputs a value according to the customer's financial needs based on the information obtained. A program to realize the processing.

Images