New product demand prediction apparatus, new product demand prediction method, and new product demand prediction program

Abstract

To provide a new product demand prediction device for accurately predicting the long-term demand of a new product whose promotion period has passed.SOLUTION: A new product demand prediction apparatus includes a first acquisition unit that acquires new product information including at least information on a promotion of a new product that is a target of demand prediction, a second acquisition unit that acquires first similar product information representing a sales record of a first similar product selected based on at least one element of a scale of the promotion, a characteristic of the product, and a sales method, a third acquisition unit that acquires second similar product information representing a sales record of a second similar product selected based on a category of the product, and a prediction unit that predicts sales in a predetermined period including a period after a promotion period of the new product based on the new product information, the first similar product information, and the second similar product information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a new product demand forecasting device, a new product demand forecasting method, and a new product demand forecasting program. [Background technology]

[0002] Technologies for performing demand forecasting are known. One example of a technology for performing demand forecasting is the technology described in Patent Document 1. Patent Document 1 describes a technology for improving the accuracy of demand forecasting for products for which no training data exists, in which a learning device learns a prediction model based on training data including the period elapsed since the product went on sale, words contained in the product name, and the demand quantity of the product since the product went on sale, and the predictor predicts the demand quantity of a target product for which no training data exists. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2017 / 163278 Summary of the Invention [Problem to be solved by the invention]

[0004] Demand forecasts for new products often focus on the first few months after release, such as promotion periods. Meanwhile, time-series forecasts for existing products, which use past levels, trends, and seasonality, require at least one year of past performance data. As a result, demand forecasts for the period up to one year after the promotion period tend to be highly subjective, resulting in low forecast accuracy. This, for example, increases the likelihood of stockouts and excess inventory.

[0005] The present disclosure has been made in consideration of the above-mentioned problems, and one exemplary purpose thereof is to provide a technology that can accurately predict long-term demand for new products after their promotion period has passed. [Means for solving the problem]

[0006] A new product demand forecasting device according to an exemplary aspect of the present disclosure includes a first acquisition unit that acquires new product information including at least information regarding the promotion of the new product that is the subject of demand forecasting, a second acquisition unit that acquires first similar product information representing the sales performance of a first similar product selected based on at least one element of the scale of the promotion, the characteristics of the product, and the sales method, a third acquisition unit that acquires second similar product information representing the sales performance of a second similar product selected based on the product category, and a prediction unit that predicts sales for a predetermined period including a period after the promotion period of the new product based on the new product information, the first similar product information, and the second similar product information.

[0007] A new product demand forecasting method according to an exemplary aspect of the present disclosure includes a first acquisition process in which at least one processor acquires new product information including at least information regarding the promotion of the new product that is the subject of the demand forecast; a second acquisition process in which at least one processor acquires first similar product information representing the sales performance of a first similar product selected based on at least one element of the scale of the promotion, the characteristics of the product, and the sales method; a third acquisition process in which at least one processor acquires second similar product information representing the sales performance of a second similar product selected based on the product category; and a prediction process in which at least one processor predicts sales for a predetermined period that includes a period after the promotion period of the new product based on the new product information, the first similar product information, and the second similar product information.

[0008] A new product demand forecasting program according to an exemplary aspect of the present disclosure is a program for causing a computer to function as a new product demand forecasting program, and causes the computer to function as a first acquisition means for acquiring new product information including at least information regarding the promotion of the new product that is the subject of the demand forecast; a second acquisition means for acquiring first similar product information representing the sales performance of a first similar product selected based on at least one element of the scale of the promotion, the characteristics of the product, and the sales method; a third acquisition means for acquiring second similar product information representing the sales performance of a second similar product selected based on the product category; and a prediction means for predicting sales for a predetermined period including a period after the promotion period of the new product based on the new product information, the first similar product information, and the second similar product information. [Effects of the Invention]

[0009] According to one exemplary aspect of the present disclosure, an exemplary effect is provided in that a technology can be provided that accurately predicts long-term demand for new products after their promotion period has expired. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing a configuration of a new product demand forecasting device according to the present disclosure. [Figure 2] 1 is a flow chart showing the flow of a new product demand forecasting method according to the present disclosure. [Figure 3] 1 is a diagram illustrating a configuration of a demand forecasting system according to the present disclosure. [Figure 4] 1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 5] FIG. 2 is a block diagram illustrating a configuration of a user terminal according to the present disclosure. [Figure 6] 1 is a flow diagram showing an example of the flow of a new product demand forecasting method according to the present disclosure. [Figure 7] FIG. 10 is a diagram illustrating an example of a display screen for prediction results according to the present disclosure. [Figure 8] FIG. 10 is a diagram illustrating an example of a display screen for prediction results according to the present disclosure. [Figure 9] FIG. 1 is a sequence diagram illustrating an example of the flow of a new product demand forecasting method according to the present disclosure. [Figure 10] FIG. 1 is a block diagram illustrating a configuration of a computer that functions as an information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0011] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technologies (part or all of the products or methods) employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technologies employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, the effects mentioned in the exemplary embodiments shown below are examples of effects expected in the exemplary embodiments, and do not define the scope of the present invention. In other words, embodiments that do not exhibit the effects mentioned in the exemplary embodiments shown below may also be included in the scope of the present invention.

[0012] First Exemplary Embodiment A first exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is the basic form of each exemplary embodiment described later. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise. Furthermore, each technology shown in the drawings referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise.

[0013] (Configuration of new product demand forecasting device) The configuration of the new product demand forecasting device 1 will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the new product demand forecasting device 1. As shown in Fig. 1, the new product demand forecasting device 1 includes a first acquisition unit 11, a second acquisition unit 12, a third acquisition unit 13, and a prediction unit 14.

[0014] The first acquisition unit 11 acquires new product information including at least information regarding the promotion of the new product that is the target of demand forecasting. The second acquisition unit 12 acquires first similar product information representing the sales performance of a first similar product selected based on at least one element of the scale of the promotion, the product characteristics, and the sales method. The third acquisition unit 13 acquires second similar product information representing the sales performance of a second similar product selected based on the product category. The prediction unit 14 predicts sales for a predetermined period including a period after the promotion period of the new product based on the new product information, the first similar product information, and the second similar product information.

[0015] (Effect of new product demand forecasting device) As described above, the new product demand forecasting device 1 is configured to include a first acquisition unit 11 that acquires new product information including at least information about the promotion of the new product that is the target of the demand forecast, a second acquisition unit 12 that acquires first similar product information that represents the sales performance of a first similar product selected based on at least one element of the promotion scale, product characteristics, and sales method, a third acquisition unit 13 that acquires second similar product information that represents the sales performance of a second similar product selected based on the product category, and a forecasting unit 14 that forecasts sales for a predetermined period that includes a period after the promotion period of the new product based on the new product information, the first similar product information, and the second similar product information. Therefore, the new product demand forecasting device 1 has the effect of being able to accurately forecast long-term demand for new products after the promotion period has passed.

[0016] (Flow of new product demand forecasting method) The flow of the new product demand forecasting method S1 will be described with reference to Fig. 2. Fig. 2 is a flow diagram showing the flow of the new product demand forecasting method S1. As shown in Fig. 2, the new product demand forecasting method S1 includes a first acquisition process S11, a second acquisition process S12, a third acquisition process S13, and a forecasting process S14.

[0017] In a first acquisition process S11, at least one processor acquires new product information including at least information regarding the promotion of the new product that is the target of demand forecasting. In a second acquisition process S12, at least one processor acquires first similar product information representing the sales performance of a first similar product selected based on at least one element of the scale of the promotion, the product characteristics, and the sales method. In a third acquisition process S13, at least one processor acquires second similar product information representing the sales performance of a second similar product selected based on the product category. In a prediction process S114, at least one processor predicts sales for a predetermined period including a period after the promotion period of the new product based on the new product information, the first similar product information, and the second similar product information.

[0018] (Effects of new product demand forecasting methods) As described above, new product demand forecasting method S1 employs a configuration in which at least one processor performs the following steps: a first acquisition process for acquiring new product information including at least information about the promotion of the new product that is the target of the demand forecast; a second acquisition process for acquiring first similar product information representing the sales performance of a first similar product selected based on at least one of the promotion scale, product characteristics, and sales method; a third acquisition process for acquiring second similar product information representing the sales performance of a second similar product selected based on the product category; and a forecasting process for forecasting sales for the new product for a predetermined period that includes a period after the promotion period, based on the new product information, the first similar product information, and the second similar product information. Therefore, new product demand forecasting method S1 has the effect of enabling accurate long-term demand forecasting for new products after the promotion period has passed.

[0019] Second Exemplary Embodiment A second exemplary embodiment, which is one example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same functions as those described in the above exemplary embodiment will be assigned the same reference numerals, and their description will be omitted as appropriate. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs. Furthermore, each technology shown in each drawing referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs.

[0020] (Demand forecasting system configuration) The configuration of a demand forecasting system 100A according to the present disclosure will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the configuration of the demand forecasting system 100A. The demand forecasting system 100A is a system that forecasts demand for a product, and includes an information processing device 1A and a user terminal 2A. The information processing device 1A and the user terminal 2A are communicatively connected via a communication line N. Although the specific configuration of the communication line N does not limit the present embodiment, examples of the communication line N include a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or a combination thereof.

[0021] The information processing device 1A is a device having a function for predicting product demand, such as a general-purpose server. The information processing device 1A may also be a personal computer such as a laptop computer or a tablet terminal. The user terminal 2A is a terminal used by a user (e.g., a planner) who uses the above service, such as a personal computer such as a laptop computer or a tablet terminal.

[0022] (Configuration of information processing device) The configuration of the information processing device 1A will be described with reference to Fig. 4. Fig. 4 is a block diagram showing the configuration of the information processing device 1A. The information processing device 1A includes a control unit 10A, a storage unit 20A, a communication unit 30A, an input unit 40A, and an output unit 50A. The communication unit 30A communicates with devices external to the information processing device 1A (such as a user terminal 2A) via a communication line. The communication unit 30A transmits data supplied from the control unit 10A to other devices, and supplies data received from other devices to the control unit 10A.

[0023] (Input and output sections) The input unit 40A is configured to receive input to the information processing device 1A, and includes, for example, input devices such as a keyboard, mouse, touch panel, camera, and microphone. The input unit 40A may also be configured to receive data from the input devices via an interface such as a USB (Universal Serial Bus). The output unit 50A is configured to perform output from the information processing device 1A, and includes, for example, output devices such as a display, printer, touch panel, and speaker. The output unit 50A may also be configured to include, for example, an interface such as a USB, and output data to the output device via the interface.

[0024] (Storage part) The storage unit 20A stores various types of information referenced by the control unit 10A. One example of such information is a database 201. The database 201 is a database that accumulates product information for each product. Examples of the product information include (a) product master information, (b) sales channel information, (c) sales performance information, (d) sales month information, (e) marketing information, (f) external environment information, and (g) information related to product characteristics.

[0025] (a) Product master information includes, for example, information indicating the product category and information indicating the sales price. An example of the information indicating the product category is information indicating the product category such as "drinking water" or "fresh food." (b) Sales channel information includes, for example, information indicating the type of channel through which the product is sold and information indicating the product sales method. An example of the information indicating the product sales method includes information indicating whether the product is released in limited quantities. (c) Sales performance information is information indicating the product sales performance, and includes, for example, information indicating the sales performance for each unit period (each week, each month). (d) Sales month information is information indicating the month in which the product is sold.

[0026] (e) Marketing information is information related to the marketing of a product, and includes, for example, information indicating the promotional measures implemented, the scale of the promotion, the promotion period, sales results during the promotion period, etc. (f) External environment information at the time of sale includes the external environment at the time of sale (average temperature, number of foreign visitors to Japan, etc.). (g) Information related to product characteristics includes, for example, information indicating whether the product is a refill product, information indicating whether the product is a seasonal product, etc. However, product information is not limited to the above examples, and product information may include other information related to the product.

[0027] Database 201 may store product information about a new product. In this case, the product information about the new product does not include information indicating sales performance. In addition, although the example of FIG. 4 has been described in which database 201 is included in storage unit 20A of information processing device 1A, database 201 may also be included in another device connected to information processing device 1A via communication line N. In this case, information processing device 1A accesses database 201 by communicating with the other device via communication line N.

[0028] (Control unit) The control unit 10A includes a first acquisition unit 11A, a second acquisition unit 12A, a third acquisition unit 13A, a prediction unit 14A, a determination unit 15A, an output control unit 16A, and a generation unit 17A. The first acquisition unit 11A is an example of a first acquisition means according to the present disclosure. The second acquisition unit 12A is an example of a second acquisition means according to the present disclosure. The third acquisition unit 13A is an example of a third acquisition means according to the present disclosure. The prediction unit 14A is an example of a prediction means according to the present disclosure. The determination unit 15A is an example of a determination means according to the present disclosure. The output control unit 16A is an example of an output control means and a presentation means according to the present disclosure. The generation unit 17A is an example of a generation means according to the present disclosure. Each unit of the control unit 10A is realized by the control unit 10A reading and executing instructions of a program stored in the memory unit 20A.

[0029] (1st acquisition part) The first acquisition unit 11A acquires product information (an example of new product information) of a new product that is the target of demand forecasting. The product information of the new product acquired by the first acquisition unit 11A includes at least information related to promotion of the new product. As an example, the first acquisition unit 11A receives data indicating a user's instruction or selection from the user terminal 2A, thereby accepting a selection of the new product that is the target of demand forecasting, and acquires the product information by reading out product information of the new product corresponding to the accepted selection from the database 201. The first acquisition unit 11A may also accept a selection input by the user to the input unit 40A, and read out product information of the new product corresponding to the accepted selection from the database 201. Hereinafter, a new product that is the target of demand forecasting may also be simply referred to as a "new product."

[0030] Furthermore, the first acquisition unit 11A may receive product information of a new product from another device via the communication unit 30A. Furthermore, the first acquisition unit 11A may acquire product information of a new product input to the input unit 40A. Furthermore, the first acquisition unit 11A may acquire the product information of a new product by reading the product information from a storage location (which may be a storage device within the information processing device 1A or a storage device external to the information processing device 1A) designated by the user of the information processing device 1A.

[0031] (Second acquisition part, similar to rising weight) The second acquisition unit 12A acquires product information of a launch weight similar product selected as a similar product to the new product. A launch weight similar product is a product selected based on at least one of the following factors: promotion scale, product characteristics, and sales method. A launch weight similar product is an example of a first similar product according to the present disclosure. In the present disclosure, launch weight refers to the ratio of sales performance during the launch promotion period to sales performance over a predetermined period (e.g., one year) from release. Products with similar factors, such as promotion scale, product characteristics, and sales method, often have similar launch weights. The forecasting unit 14A, described below, uses the sales performance of the launch weight similar products selected based on these factors to forecast sales of the new product.

[0032] As an example, the second acquisition unit 12A receives data indicating a user instruction or selection from the user terminal 2A, thereby accepting a selection of a standing-up weight-like product, and acquires product information of the standing-up weight-like product by reading out product information of the standing-up weight-like product corresponding to the accepted selection from the database 201. The second acquisition unit 12A may also accept a selection input by the user to the input unit 40A, and read out product information of the standing-up weight-like product corresponding to the accepted selection from the database 201.

[0033] The second acquisition unit 12A may also receive product information on a rising weight-like product from another device via the communication unit 30A. The second acquisition unit 12A may also acquire product information on a rising weight-like product input to the input unit 40A. The second acquisition unit 12A may also acquire the product information by reading the product information on a rising weight-like product from a storage location specified by the user of the information processing device 1A (which may be a storage device within the information processing device 1A or a storage device external to the information processing device 1A).

[0034] The second acquisition unit 12A may select one product or multiple products as the rising weight similar product. In other words, the second acquisition unit 12A may acquire product information on multiple rising weight similar products.

[0035] (Third Acquisition Section / Seasonal Similar Products) The third acquisition unit 13A acquires product information on seasonally similar products selected as similar products to the new product. Seasonal similar products are products selected based on product categories and are an example of second similar products according to the present disclosure. Product demand varies depending on various factors such as trends and seasons, but the long-term fluctuation pattern of product demand often depends on the product category. The forecasting unit 14A, which will be described later, uses the sales performance of seasonally similar products selected based on the product category to forecast sales of the new product.

[0036] As an example, the third acquisition unit 13A receives data indicating a user instruction or selection from the user terminal 2A, thereby accepting a selection of a seasonal similar product, and acquires product information of the seasonal similar product by reading out product information of the seasonal similar product corresponding to the accepted selection from the database 201. The third acquisition unit 13A may also accept a selection input by the user to the input unit 40A, and read out product information of the seasonal similar product corresponding to the accepted selection from the database 201.

[0037] The third acquisition unit 13A may also receive product information on seasonally similar products from another device via the communication unit 30A. The third acquisition unit 13A may also acquire product information on seasonally similar products input to the input unit 40A. The third acquisition unit 13A may also acquire the product information on seasonally similar products by reading the product information from a storage location specified by the user of the information processing device 1A (which may be a storage device within the information processing device 1A or a storage device external to the information processing device 1A).

[0038] The third acquisition unit 13A may select one product or multiple products as the seasonal similar product. In other words, the third acquisition unit 13A may acquire product information of multiple seasonal similar products.

[0039] (Prediction Department) The prediction unit 14A predicts sales of the new product for a predetermined period based on the product information of the new product, the product information of the similar products with a launch weight, and the product information of the similar products with a seasonality. Here, the predetermined period is a period including the period after the promotion period of the new product (e.g., one year from the release). Also, the promotion period is the period covered by the promotion of the new product (e.g., several months from the release).

[0040] For example, the prediction unit 14A predicts the total sales value of the new product for the predetermined period using the sales performance of the new product for the promotion period and the start-up weight of the start-up weight similar product (the ratio of the sales performance for the promotion period to the sales performance for the predetermined period). More specifically, for example, the prediction unit 14A predicts the total sales value of the new product for the predetermined period by dividing the sales performance of the new product for the promotion period by the start-up weight of the start-up weight similar product.

[0041] The prediction unit 14A also predicts the sales of the new product for each unit period in the predetermined period using the total sales value and the sales results of the seasonally similar products for each unit period included in the predetermined period. More specifically, as an example, the prediction unit 14A predicts the sales of the new product for each unit period by multiplying the predicted total value by the ratio of the sales results for each unit period to the sales results of the seasonally similar products for the predetermined period.

[0042] When multiple start-up weight similar products are selected, the prediction unit 14A predicts the sales of the new product in a predetermined period using the statistical values ​​of the sales performance of each start-up weight similar product. Also, when multiple seasonal similar products are selected, the prediction unit 14A predicts the sales of the new product in a predetermined period based on the statistical values ​​of the sales performance of each seasonal similar product. Here, examples of statistical values ​​include, but are not limited to, the average, median, mode, geometric mean, and root mean square of the sales performance of multiple products.

[0043] (Output control section) The output control unit 16A outputs the sales forecast result of the new product forecasted by the forecasting unit 14A. As an example, the output control unit 16A outputs data indicating the sales forecast result to a display and causes the forecast result to be displayed on the display. As an example, the display is the display of the user terminal 2A. In this case, the output control unit 16A transmits data indicating the forecast result to the user terminal 2A via the communication unit 30A and causes the screen to be displayed on the display of the user terminal 2A. In this specification, the output control unit 16A transmitting data indicating the forecast result to the user terminal 2A and displaying the forecast result on the display of the user terminal 2A is also referred to as "the output control unit 16A displaying the forecast result."

[0044] The output control unit 16A may also output data indicating the prediction result to a display connected to the output unit 50A, thereby displaying the prediction result on the display. The output control unit 16A may also output the data by writing it to a storage destination (which may be a storage device within the information processing device 1A or a storage device external to the information processing device 1A) designated by the user of the information processing device 1A. The output control unit 16A may also transmit the data to another device via the communication unit 30A, or may output the data to an output device such as a speaker or a printer.

[0045] (Decision section) The determination unit 15A determines products that are candidates for a launch weighted similar product and a seasonal similar product, or for a launch weighted similar product and a seasonal similar product. As an example, the determination unit 15A refers to the database 201 and determines products that are the same as or similar to the new product in at least one element of the promotion scale, product characteristics, and sales method as candidates for a launch weighted similar product or a launch similar product. In addition, as an example, the determination unit 15A may refer to the database 201 and determine products that belong to the product category of the new product as candidates for a seasonal similar product or a seasonal similar product.

[0046] The determination unit 15A may also determine an optimal solution for selecting a start-up weight similar product and a seasonal similar product by using an objective function generated in advance by inverse reinforcement learning based on the decision-making history regarding the selection of a start-up weight similar product and a seasonal similar product, and the product information of the new product acquired by the first acquisition unit 11A. Details of the process by which the determination unit 15A determines the optimal solution using the objective function will be described later.

[0047] When the determination unit 15A determines the optimal solution, the second acquisition unit 12A acquires product information of the rising weight similar product based on the optimal solution determined by the determination unit 15A. Also, the third acquisition unit 13A acquires product information of the seasonal similar product based on the optimal solution determined by the determination unit 15A.

[0048] In this case, the output control unit 16A may present the user with multiple candidates for rising weight similar products and multiple candidates for seasonal similar products based on the optimal solution determined by the determination unit 15A. In this case, the second acquisition unit 12A acquires product information for a rising weight similar product selected from the multiple candidates for rising weight similar products based on a user operation. In addition, the third acquisition unit 13A acquires product information for a seasonal similar product selected from the multiple candidates for seasonal similar products based on a user operation.

[0049] (Generation part) The generation unit 17A generates the objective function referenced by the determination unit 15A by inverse reinforcement learning based on the decision-making history regarding the selection of the rising weight similar product and the seasonal similar product. Details of the process by which the generation unit 17A generates the objective function will be described later. Hereinafter, when there is no need to distinguish between the rising weight similar product and the seasonal similar product, they will simply be referred to as "similar product."

[0050] (User terminal configuration) 5 is a block diagram showing the configuration of the user terminal 2A. The user terminal 2A includes a control unit 210A, a storage unit 220A, a communication unit 230A, an input unit 240A, and an output unit 250A. The user terminal 2A is, for example, a general-purpose computer. The storage unit 220A stores various types of information referenced by the control unit 210A. The communication unit 230A communicates with devices external to the user terminal 2A (such as the information processing device 1A) via a communication line N.

[0051] (Input and output sections) The input unit 240A is configured to receive input to the user terminal 2A, and includes, for example, input devices such as a keyboard, mouse, touch panel, camera, and microphone. The input unit 240A may also be configured to receive data from the input devices via an interface such as USB. The output unit 250A is configured to perform output from the user terminal 2A, and includes, for example, output devices such as a display, printer, touch panel, and speaker. The output unit 250A may also be configured to include, for example, an interface such as USB, and to output data to the output device via the interface.

[0052] (Control unit) The control unit 210A includes an application execution unit 21A. The application execution unit 21A is realized by the control unit 210A reading and executing instructions of an application program stored in the storage unit 220A. The application execution unit 21A executes the application program stored in the storage unit 220A, and performs processing to transmit information indicating the selected rising weight similar product and information indicating the seasonal similar product to the information processing device 1A, and processing to display the sales forecast results of the new product. The application implemented by the application execution unit 21A is, for example, a general-purpose web browser, but is not limited to this. The application execution unit 21A may also be a dedicated application for communicating with the information processing device 1A and forecasting sales of the new product.

[0053] The application execution unit 21A includes a reception unit 211A and a display control unit 212A. The reception unit 211A receives user specifications, selections, etc. The display control unit 212A displays various screens on the display based on data received from the information processing device 1A.

[0054] (Example 1 of a new product demand forecasting method) FIG. 6 is a flow diagram showing an example of the flow of a new product demand forecasting method executed by the demand forecasting system 100A. In the example of FIG. 6, a case will be described in which the forecast result is displayed on the display of the user terminal 2A. When the user of the user terminal 2A performs an operation to start an application using an input device, the application execution unit 21A displays a screen for specifying or selecting a new product. The user performs an operation to specify or select a new product using the input device. The application execution unit 21A transmits data indicating the new product specified or selected by the user to the information processing device 1A. As an example, the data includes identification information that identifies the new product.

[0055] (Step S21) In step S21, the first acquisition unit 11A of the information processing device 1A acquires product information of the new product. As an example, the first acquisition unit 11A acquires the product information of the new product indicated by the data received from the user terminal 2A by reading the product information from the database 201.

[0056] (Step S22) In step S22, the determination unit 15A selects a rising weight similar product and a seasonal similar product from among the multiple products registered in the database 201. As an example, the determination unit 15A may receive data indicating the rising weight similar product and the seasonal similar product selected by the user from the user terminal 2A, and select the rising weight similar product and the seasonal similar product based on the received data.

[0057] As another example, the determination unit 15A determines an optimal solution for selecting a start-up weight similar product and a seasonal similar product using an objective function generated in advance by inverse reinforcement learning based on the decision-making history regarding the selection of a start-up weight similar product and a seasonal similar product, and the product information of the new product acquired by the first acquisition unit 11A, and selects the start-up weight similar product and the seasonal similar product based on the determined optimal solution. Details of the process by which the determination unit 15A determines the optimal solution using the objective function will be described later.

[0058] (Steps S23 and S24) In step S23, the second acquisition unit 12A acquires product information of the rising weight similar product selected by the determination unit 15A. In addition, in step S24, the third acquisition unit 13A acquires product information of the seasonal similar product selected by the determination unit 15A.

[0059] (Step S25) In step S25, the prediction unit 14A predicts the sales of the new product for a predetermined period based on the product information of the new product, the product information of the similar products with a launch weight, and the product information of the similar products with a seasonality. More specifically, as an example, the prediction unit 14A predicts the total sales value of the new product for a predetermined period using the sales record of the new product during the promotion period and the launch weight of the similar products with a launch weight. The prediction unit 14A also predicts the sales of the new product for each unit period in the predetermined period using the predicted total sales value and the sales record of the similar products with a seasonality for each unit period included in the predetermined period.

[0060] (Step S26) In step S26, the output control unit 16A transmits data including the prediction result predicted by the prediction unit 14A to the user terminal 2A, and causes the prediction result to be displayed on the display of the user terminal 2A. As an example, the data may include, in addition to the data indicating the prediction result, product information on new products, product information on start-up weight-like products, and product information on seasonally similar products.

[0061] (Example of a screen displaying prediction results) 7 and 8 are diagrams showing examples of display screens for prediction results. Screen SC11 in FIG. 7 and screen SC12 in FIG. 8 may be displayed as a single screen, or may be displayed separately. Screen SC11 in FIG. 7 includes a first display area A111, a second display area A112, a third display area A113, and a button B114. Product information for new products is displayed in the first display area A111. Product information for similar products with rising weights is displayed in the second display area A112. Product information for similar products with seasonality is displayed in the third display area A113. Button B114 is a button for displaying sales prediction results based on the selected similar products.

[0062] A user of the demand forecasting system 100A selects a rising weight similar product and a seasonal similar product on the screen of Fig. 7, and also performs an operation of selecting button B114. When button B114 is selected by the user, the display control unit 212A displays the forecast result on the display.

[0063] As an example, screen SC12 in Fig. 8 is displayed below screen SC11 in Fig. 7 when button B114 is selected. Screen SC12 includes button B114, a rising weight display area A115, a graph display area A116, button B117, and an adjustment area A118. A bar graph showing the rising weight of a rising weight analogue is displayed in rising weight display area A115.

[0064] A graph showing the sales forecast results for the new product is displayed in the graph display area A116. In the graph displayed in the graph display area A116, the horizontal axis indicates the period since release, and the vertical axis indicates actual sales or sales forecast. In the example of FIG. 8, the monthly sales forecast values ​​of the line graph g11 showing the sales forecast for the new product are values ​​calculated by the prediction unit 14A using the start-up weight of the selected start-up weight similar product and the monthly sales actual of the selected seasonal similar product. Therefore, as shown in FIG. 8, the fluctuation pattern of the sales forecast for the new product over a predetermined period (one year) correlates with the fluctuation pattern of the sales actual of the seasonal similar product over a predetermined period.

[0065] The pull-down list L118 is a pull-down list for selecting a category of products similar to the rising weight. When the user selects a category using the pull-down list L118, the display control unit 212A displays information about products belonging to the selected category in the second display area A112. The adjustment area A118 displays a table showing the predicted monthly sales of the new product. The user can correct the predicted monthly sales values ​​displayed in the adjustment area A118 using the input unit 240A. The button B117 is a button for reflecting the corrected predicted values ​​in the prediction results. When the button B117 is selected, the application execution unit 21A displays a graph reflecting the corrected sales values ​​in the graph display area A116.

[0066] (Selection of similar products based on past decision-making history) The following describes in detail the process performed by the determination unit 15A when selecting similar products based on the decision-making history regarding the selection of start-up weight similar products and seasonal similar products. In this case, the determination unit 15A determines an optimal solution regarding the selection of similar products using a pre-generated objective function. The objective function is pre-generated by inverse reinforcement learning based on the decision-making history regarding the selection of start-up weight similar products and seasonal similar products.

[0067] The decision-making history includes, for example, status data regarding the new product and behavioral data regarding the selected similar product. The status data regarding the new product includes, for example, product information regarding the new product, policy information indicating the policy targeted at the new product, and external environmental information (temperature, etc.) at the time of release of the new product. The behavioral data regarding the selected similar product includes, for example, product information regarding the selected similar product, policy information indicating the policy targeted at the similar product, and external environmental information (temperature, etc.) at the time of release of the similar product. These data are, for example, stored in database 201.

[0068] An example of the objective function is expressed by the following equation (1). f(x)=λ1x1+λ2x2+λ3x3+…+λ n x n …(1) In formula (1), x i (i=1, 2, …, n) are explanatory variables, and n is the total number of explanatory variables. Explanatory variables x1, x2, …, x n λ is data corresponding to each item included in the state data or behavior data. i is a weighting coefficient.

[0069] The objective function is generated by the generation unit 17A, for example. In this case, the generation unit 17A generates the objective function by inverse reinforcement learning using a past decision-making history. More specifically, for example, the generation unit 17A calculates the weighting coefficient λ in the above-mentioned equation (1) by inverse reinforcement learning using a set of state data and action data, which are the past decision-making history. i (i=1, 2, ..., n) to generate the objective function. iis an index that indicates how much importance is attached to the items corresponding to each explanatory variable, and can also be said to reflect the intentions of users who made decisions in the past.

[0070] The determination unit 15A selects similar products using the product information of the new product and the objective function. More specifically, as an example, the determination unit 15A determines an optimal solution for selecting similar products using the product information of the new product and the objective function of equation (1).

[0071] (Example 2 of new product demand forecasting method) 9 is a sequence diagram showing another example of the flow of the new product demand forecasting method executed by the demand forecasting system 100 A. In this example, the determination unit 15A of the information processing device 1A presents a plurality of similar product candidates to the user, and the forecasting unit 14A forecasts sales of the new product using a similar product selected from the presented plurality of candidates.

[0072] When the user of the user terminal 2A performs an operation to start an application using an input device, the application execution unit 21A displays a screen for accepting designation or selection of a new product and accepts the designation or selection of the new product on the screen in step S101. Upon accepting the designation or selection of the new product by the user, the application execution unit 21A transmits information indicating the new product to the information processing device 1A in step S102.

[0073] In step S103, the determination unit 15A selects similar product candidates. As an example, the determination unit 15A selects similar product candidates by finding an optimal solution using product information about the new product and the above-mentioned objective function. In step S104, the determination unit 15A transmits data indicating the selected similar product candidates to the user terminal 2A. At this time, the output control unit 16A may output a weighting coefficient included in the objective function used to select the similar product candidates, in addition to the data indicating the similar product candidates.

[0074] In step S105, the application execution unit 21A displays similar product candidates on the display based on the received data. At this time, the application execution unit 21A may display, on the display, weighting factors included in the objective function used to select the similar product candidates based on the received data. The user performs an operation to select a rising weight similar product and a seasonal similar product from the displayed similar product candidates. In step S106, the application execution unit 21A selects a rising weight similar product and a seasonal similar product based on the user operation. In step S107, the application execution unit 21A transmits data indicating the selected rising weight similar product and seasonal similar product to the information processing device 1A.

[0075] In step S108, the prediction unit 14A predicts sales of the new product for a predetermined period using product information on the new product, product information on similar products with a rising weight, and product information on similar products with a seasonality. In step S109, the output control unit 16A transmits data indicating the prediction result to the user terminal 2A. At this time, the output control unit 16A may output a weighting factor included in the objective function used to select similar products, in addition to the data indicating the prediction result. In step S110, the display control unit 212A displays a screen indicating the prediction result (such as the screen exemplified in FIG. 8) on the display based on the data received from the information processing device 1A. At this time, the display control unit 212A may display a weighting factor included in the objective function on the display, in addition to the prediction result.

[0076] (Effects of information processing devices) As described above, in the information processing device 1A, the prediction unit 14A predicts the total sales value of the new product for a specified period using the sales performance of the new product during the promotion period and the ratio of the sales performance of the promotion period to the sales performance of the start-up weight similar product for a specified period, and also predicts the sales of the new product for each unit period in the specified period using the predicted total sales value and the sales performance of the seasonal similar product for each unit period (e.g., each month) included in the specified period.

[0077] As described above, the launch weight similar product is a product selected as a similar product from the perspective of the similarity of the launch weight, and the seasonal similar product is a product selected as a similar product from the perspective of the similarity of the demand fluctuation pattern. By selecting two types of similar products from different perspectives in this way and forecasting the sales of a new product using both the launch weight of the launch weight similar product and the sales performance of the seasonal similar product per unit period, it is possible to more accurately forecast the long-term demand for the new product after the promotion period has passed.

[0078] The information processing device 1A further includes a determination unit 15A that determines an optimal solution for selecting a start-up weight similar product and a seasonal similar product using an objective function previously generated by inverse reinforcement learning based on a decision-making history regarding the selection of start-up weight similar products and seasonal similar products and product information on new products acquired by the first acquisition unit 11A, and the second acquisition unit 12A acquires product information on start-up weight similar products based on the optimal solution determined by the determination unit 15A, and the third acquisition unit 13A acquires product information on seasonal similar products based on the optimal solution determined by the determination unit 15A. Therefore, the information processing device 1A can easily select start-up weight similar products and seasonal similar products.

[0079] Furthermore, the information processing device 1A employs a configuration including a generation unit 17A that generates an objective function for determining an optimal solution in the selection of a rising weight analogue and a seasonal analogue by inverse reinforcement learning based on a decision-making history regarding the selection of a rising weight analogue and a seasonal analogue. By using the objective function generated by the generation unit 17A, the selection of a rising weight analogue and a seasonal analogue can be easily performed.

[0080] Furthermore, the information processing device 1A is configured to include an output control unit 16A that outputs the sales forecast results for the new product. Therefore, the information processing device 1A allows the user to easily understand the sales forecast results for the new product.

[0081] The information processing device 1A is further configured to include an output control unit 16A that presents a plurality of candidates for rising weight similar products and a plurality of candidates for seasonal similar products to the user based on the optimal solution determined by the determination unit 15A, a second acquisition unit 12A that acquires product information for a product selected from the plurality of candidates for rising weight similar products based on a user operation, and a third acquisition unit 13A that acquires product information for a product selected from the plurality of candidates for seasonal similar products based on a user operation. Thus, the information processing device 1A can easily select similar products that reflect the user's preferences.

[0082] Furthermore, the information processing device 1A is configured such that the second acquisition unit 12A acquires product information representing the sales performance of multiple start-up weight similar products, the third acquisition unit 13A acquires product information representing the sales performance of multiple seasonal similar products, and the prediction unit 14A predicts sales of the new product for a predetermined period based on the statistical values ​​of the sales performance of the multiple start-up weight similar products and the statistical values ​​of the sales performance of the multiple seasonal similar products. Therefore, the information processing device 1A can accurately predict long-term demand for new products after the promotion period has passed.

[0083] [Software implementation example] Some or all of the functions of the new product demand forecasting device 1, the information processing device 1A, and the user terminal 2A (hereinafter also referred to as "the above-mentioned devices") may be realized by hardware such as an integrated circuit (IC chip), or by software.

[0084] In the latter case, each of the above devices is realized by, for example, a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in Figure 10. Figure 10 is a block diagram showing the hardware configuration of computer C that functions as each of the above devices.

[0085] The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to operate as each of the above-mentioned devices. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing the functions of each of the above-mentioned devices.

[0086] The processor C1 may be, for example, a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0087] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, mouse, display, and printer.

[0088] Furthermore, the program P can be recorded on a non-transitory tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0089] Furthermore, the functions of each of the devices may be realized by a single processor provided in a single computer, by multiple processors provided in a single computer working in cooperation, or by multiple processors provided in each of multiple computers working in cooperation. Furthermore, the programs for causing each of the devices to realize the functions may be stored in a single memory provided in a single computer, or may be distributed and stored in multiple memories provided in a single computer, or may be distributed and stored in multiple memories provided in each of multiple computers.

[0090] [Appendix 1] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0091] [Appendix A] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0092] (Appendix A1) a first acquisition means for acquiring new product information including at least information regarding promotion of the new product that is the target of demand forecasting; a second acquiring means for acquiring first similar product information representing sales performance of the first similar product selected based on at least one element of the scale of the promotion, the characteristics of the product, and the sales method; a third acquiring means for acquiring second similar product information representing sales performance of second similar products selected based on the product category; a prediction means for predicting sales for a predetermined period including a period after a promotion period for the new product based on the new product information, the first similar product information, and the second similar product information; A new product demand forecasting device comprising:

[0093] (Appendix A2) The prediction means predicting a total sales value of the new product during the predetermined period using the sales performance of the new product during the promotion period and the ratio of the sales performance of the first similar product during the promotion period to the sales performance of the first similar product during the predetermined period; predicting the sales of the new product for each unit period in the predetermined period using the total sales amount and the sales record of the second similar product for each unit period included in the predetermined period; A new product demand forecasting device as described in Appendix A1.

[0094] (Appendix A3) a determination means for determining an optimal solution in the selection of the first similar product and the second similar product by using an objective function generated in advance by inverse reinforcement learning based on a decision-making history regarding the selection of the first similar product and the second similar product and the new product information acquired by the first acquisition means, the second acquisition means acquires the first similar product information based on the optimal solution determined by the determination means; the third acquisition means acquires the second similar product information based on the optimal solution determined by the determination means. A new product demand forecasting device according to appendix A1 or A2.

[0095] (Appendix A4) a generation means for generating an objective function for determining an optimal solution in the selection of the first similar product and the second similar product by inverse reinforcement learning based on a decision-making history regarding the selection of the first similar product and the second similar product; A new product demand forecasting device as described in Appendix A3.

[0096] (Appendix A5) further comprising an output control means for outputting the sales forecast result; A new product demand forecasting device according to any one of appendices A1 to A4.

[0097] (Appendix A6) a presentation unit that presents a plurality of candidates for the first similar product and a plurality of candidates for the second similar product to a user based on the optimal solution determined by the determination unit, the second acquisition means acquires first similar product information of a first similar product selected from a plurality of candidates of the first similar product based on a user operation; the third acquisition means acquires second similar product information of a second similar product selected from the plurality of second similar product candidates based on a user operation; A new product demand forecasting device as described in Appendix A3 or A4.

[0098] (Appendix A7) the second acquisition means acquires first similar product information representing sales records of the plurality of first similar products; the third acquisition means acquires second similar product information representing sales records of the plurality of second similar products; the prediction means predicts the sales of the new product in the predetermined period based on a statistical value of sales performance for each of the first similar products indicated by the first similar product information and a statistical value of sales performance for each of the second similar products indicated by the second similar product information. 10. A new product demand forecasting device according to any one of appendices A1 to A6.

[0099] [Appendix B] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0100] (Appendix B1) a first acquisition process in which at least one processor acquires new product information including at least information regarding a promotion of the new product that is the target of the demand forecast; a second acquisition process in which the at least one processor acquires first similar product information representing sales performance of the first similar product selected based on at least one element of a promotion scale, product characteristics, and sales method; a third acquisition process in which the at least one processor acquires second similar product information representing sales performance of second similar products selected based on product categories; a prediction process in which the at least one processor predicts sales for a predetermined period including a period after a promotion period for the new product based on the new product information, the first similar product information, and the second similar product information; New product demand forecasting methods, including:

[0101] (Appendix B2) In the prediction process, the at least one processor predicting a total sales value of the new product during the predetermined period using the sales performance of the new product during the promotion period and the ratio of the sales performance of the first similar product during the promotion period to the sales performance of the first similar product during the predetermined period; predicting the sales of the new product for each unit period in the predetermined period using the total sales amount and the sales record of the second similar product for each unit period included in the predetermined period; A method for forecasting demand for new products as described in Appendix B1.

[0102] (Appendix B3) The method further includes a determination process performed by the at least one processor to determine an optimal solution in the selection of the first similar product and the second similar product using an objective function previously generated by inverse reinforcement learning based on a decision-making history regarding the selection of the first similar product and the second similar product and the new product information acquired by the first acquisition process; In the second acquisition process, the at least one processor acquires the first similar product information based on the optimal solution determined in the determination process; In the third acquisition process, the at least one processor acquires the second similar product information based on the optimal solution determined in the determination process. A method for forecasting demand for a new product as described in Appendix B1 or B2.

[0103] (Appendix B4) The method further includes a generation process in which the at least one processor generates an objective function that determines an optimal solution in the selection of the first similar product and the second similar product by inverse reinforcement learning based on a decision-making history regarding the selection of the first similar product and the second similar product. The new product demand forecasting method described in Appendix B3.

[0104] (Appendix B5) The at least one processor further includes an output control process for outputting the sales forecast result. A new product demand forecasting method according to any one of appendices B1 to B4.

[0105] (Appendix B6) The at least one processor further includes a presentation process for presenting a plurality of candidates for the first similar product and a plurality of candidates for the second similar product to a user based on the optimal solution determined by the determination process; In the second acquisition process, the at least one processor acquires first similar product information of a first similar product selected from a plurality of candidates of the first similar product based on a user operation; In the third acquisition process, the at least one processor acquires second similar product information of a second similar product selected from a plurality of candidates of the second similar product based on a user operation. A method for forecasting demand for a new product as described in Appendix B3 or B4.

[0106] (Appendix B7) In the second acquisition process, the at least one processor acquires first similar product information representing sales records of the plurality of first similar products; In the third acquisition process, the at least one processor acquires second similar product information representing sales records of the plurality of second similar products; In the prediction process, the at least one processor predicts sales of the new product in the predetermined period based on a statistical value of sales performance for each of the first similar products indicated by the first similar product information and a statistical value of sales performance for each of the second similar products indicated by the second similar product information. 1. A method for forecasting demand for a new product as set forth in any one of Appendices B1 to B6.

[0107] [Appendix C] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0108] (Appendix C1) A program for causing a computer to function as a new product demand forecasting device, the program comprising: a first acquisition means for acquiring new product information including at least information regarding promotion of the new product that is the target of demand forecasting; a second acquiring means for acquiring first similar product information representing sales performance of the first similar product selected based on at least one element of the scale of the promotion, the characteristics of the product, and the sales method; a third acquiring means for acquiring second similar product information representing sales performance of second similar products selected based on the product category; a prediction means for predicting sales for a predetermined period including a period after a promotion period for the new product based on the new product information, the first similar product information, and the second similar product information; A new product demand forecasting program to function as a

[0109] (Appendix C2) The prediction means predicting a total sales value of the new product during the predetermined period using the sales performance of the new product during the promotion period and the ratio of the sales performance of the first similar product during the promotion period to the sales performance of the first similar product during the predetermined period; predicting the sales of the new product for each unit period in the predetermined period using the total sales amount and the sales record of the second similar product for each unit period included in the predetermined period; A new product demand forecasting program as described in Appendix C1.

[0110] (Appendix C3) The computer further functioning as a decision means for determining an optimal solution in the selection of the first similar product and the second similar product, using an objective function generated in advance by inverse reinforcement learning based on a decision-making history regarding the selection of the first similar product and the second similar product, and the new product information acquired by the first acquisition means; the second acquisition means acquires the first similar product information based on the optimal solution determined by the determination means; the third acquisition means acquires the second similar product information based on the optimal solution determined by the determination means. A new product demand forecasting program as described in Appendix C1 or C2.

[0111] (Appendix C4) The computer a generating means for generating an objective function for determining an optimal solution in the selection of the first similar product and the second similar product by inverse reinforcement learning based on a decision-making history regarding the selection of the first similar product and the second similar product; A new product demand forecasting program as described in Appendix C3.

[0112] (Appendix C5) The computer and further functioning as an output control means for outputting the sales forecast result. A new product demand forecasting program according to any one of appendices C1 to C4.

[0113] (Appendix C6) The computer further functioning as a presentation means for presenting to a user a plurality of candidates for the first similar product and a plurality of candidates for the second similar product based on the optimal solution determined by the determination means; the second acquisition means acquires first similar product information of a first similar product selected from a plurality of candidates of the first similar product based on a user operation; the third acquisition means acquires second similar product information of a second similar product selected from the plurality of second similar product candidates based on a user operation; A new product demand forecasting program as described in Appendix C3 or C4.

[0114] (Appendix C7) the second acquisition means acquires first similar product information representing sales records of the plurality of first similar products; the third acquisition means acquires second similar product information representing sales records of the plurality of second similar products; the prediction means predicts the sales of the new product in the predetermined period based on a statistical value of sales performance for each of the first similar products indicated by the first similar product information and a statistical value of sales performance for each of the second similar products indicated by the second similar product information. 1. A new product demand forecasting program as set forth in any one of appendices C1 to C6.

[0115] [Appendix D] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0116] (Appendix D1) at least one processor, a first acquisition process for acquiring new product information including at least information regarding promotion of the new product that is the target of demand forecasting; a second acquisition process for acquiring first similar product information representing sales performance of the first similar product selected based on at least one element of the scale of the promotion, the characteristics of the product, and the sales method; a third acquisition process for acquiring second similar product information representing sales performance of second similar products selected based on the product category; a prediction process for predicting sales for a predetermined period including a period after a promotion period for the new product based on the new product information, the first similar product information, and the second similar product information; A new product demand forecasting device that performs

[0117] The new product demand forecasting device may further include a memory, and the memory may store a program for causing the at least one processor to execute each of the processes.

[0118] (Appendix D2) In the prediction process, the at least one processor predicting a total sales value of the new product during the predetermined period using the sales performance of the new product during the promotion period and the ratio of the sales performance of the first similar product during the promotion period to the sales performance of the first similar product during the predetermined period; predicting the sales of the new product for each unit period in the predetermined period using the total sales amount and the sales record of the second similar product for each unit period included in the predetermined period; 1. A new product demand forecasting device as described in Appendix D1.

[0119] (Appendix D3) the at least one processor: further executing a decision process for determining an optimal solution in the selection of the first similar product and the second similar product using an objective function previously generated by inverse reinforcement learning based on a decision-making history regarding the selection of the first similar product and the second similar product and the new product information acquired by the first acquisition process; In the second acquisition process, the at least one processor acquires the first similar product information based on the optimal solution determined in the determination process; In the third acquisition process, the at least one processor acquires the second similar product information based on the optimal solution determined in the determination process. A new product demand forecasting device according to appendix D1 or D2.

[0120] (Appendix D4) the at least one processor: further performing a generation process of generating an objective function that determines an optimal solution in the selection of the first similar product and the second similar product by inverse reinforcement learning based on a decision-making history regarding the selection of the first similar product and the second similar product; 1. A new product demand forecasting device as described in Appendix D3.

[0121] (Appendix D5) the at least one processor: and further executing an output control process for outputting the sales forecast result. A new product demand forecasting device according to any one of appendices D1 to D4.

[0122] (Appendix D6) the at least one processor: further executing a presentation process of presenting a plurality of candidates for the first similar product and a plurality of candidates for the second similar product to a user based on the optimal solution determined by the determination process; In the second acquisition process, the at least one processor acquires first similar product information of a first similar product selected from a plurality of candidates of the first similar product based on a user operation; In the third acquisition process, the at least one processor acquires second similar product information of a second similar product selected from a plurality of candidates of the second similar product based on a user operation. A new product demand forecasting device according to appendix D3 or D4.

[0123] (Appendix D7) In the second acquisition process, the at least one processor acquires first similar product information representing sales records of the plurality of first similar products; In the third acquisition process, the at least one processor acquires second similar product information representing sales records of the plurality of second similar products; In the prediction process, the at least one processor predicts sales of the new product in the predetermined period based on a statistical value of sales performance for each of the first similar products indicated by the first similar product information and a statistical value of sales performance for each of the second similar products indicated by the second similar product information. A new product demand forecasting device according to any one of appendices D1 to D6.

[0124] [Appendix E] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0125] (Appendix E1) A program for causing a computer to function as a new product demand forecasting device, the program comprising: a first acquisition process for acquiring new product information including at least information regarding promotion of the new product that is the target of demand forecasting; a second acquisition process for acquiring first similar product information representing sales performance of the first similar product selected based on at least one element of the scale of the promotion, the characteristics of the product, and the sales method; a third acquisition process for acquiring second similar product information representing sales performance of second similar products selected based on the product category; a prediction process for predicting sales for a predetermined period including a period after a promotion period for the new product based on the new product information, the first similar product information, and the second similar product information; A non-transitory recording medium on which a new product demand forecasting program for executing the above is recorded. [Explanation of symbols]

[0126] 1. New product demand forecasting device 1A Information processing equipment 2A User terminal 10A, 210A control unit 11, 11A 1st acquisition part 12, 12A 2nd acquisition part 13, 13A 3rd acquisition part 14, 14A Forecasting Section 15A Decision section 16A generation section 17A Output control section 20A, 220A memory section 21A Application Execution Unit 30A, 230A communication department 40A, 240A input section 50A, 250A output section 100A Demand Forecasting System

Claims

1. a first acquisition means for acquiring new product information including at least information regarding promotion of the new product that is the target of demand forecasting; a second acquiring means for acquiring first similar product information representing sales performance of the first similar product selected based on at least one element of the scale of the promotion, the characteristics of the product, and the sales method; a third acquiring means for acquiring second similar product information representing sales performance of second similar products selected based on the product category; a forecasting means for forecasting sales for a predetermined period including a period after a promotion period for the new product based on the new product information, the first similar product information, and the second similar product information; A new product demand forecasting device comprising:

2. The prediction means predicting a total sales value of the new product during the predetermined period using the sales performance of the new product during the promotion period and the ratio of the sales performance of the first similar product during the promotion period to the sales performance of the first similar product during the predetermined period; predicting the sales of the new product for each unit period in the predetermined period using the total sales amount and the sales record of the second similar product for each unit period included in the predetermined period; The new product demand forecasting device according to claim 1.

3. a determination means for determining an optimal solution in the selection of the first similar product and the second similar product by using an objective function generated in advance by inverse reinforcement learning based on a decision-making history regarding the selection of the first similar product and the second similar product and the new product information acquired by the first acquisition means, the second acquisition means acquires the first similar product information based on the optimal solution determined by the determination means; the third acquisition means acquires the second similar product information based on the optimal solution determined by the determination means.

3. The new product demand forecasting device according to claim 1 or 2.

4. a generation means for generating an objective function for determining an optimal solution in the selection of the first similar product and the second similar product by inverse reinforcement learning based on a decision-making history regarding the selection of the first similar product and the second similar product; The new product demand forecasting device according to claim 3.

5. further comprising an output control means for outputting the sales forecast result; 3. The new product demand forecasting device according to claim 1 or 2.

6. a presentation unit that presents a plurality of candidates for the first similar product and a plurality of candidates for the second similar product to a user based on the optimal solution determined by the determination unit, the second acquisition means acquires first similar product information of a first similar product selected from a plurality of candidates of the first similar product based on a user operation; the third acquisition means acquires second similar product information of a second similar product selected from a plurality of second similar product candidates based on a user operation; The new product demand forecasting device according to claim 3.

7. the second acquisition means acquires first similar product information representing sales records of the plurality of first similar products; the third acquisition means acquires second similar product information representing sales records of the plurality of second similar products; the prediction means predicts the sales of the new product in the predetermined period based on a statistical value of sales performance for each of the first similar products indicated by the first similar product information and a statistical value of sales performance for each of the second similar products indicated by the second similar product information.

3. The new product demand forecasting device according to claim 1 or 2.

8. At least one processor a first acquisition process for acquiring new product information including at least information regarding promotion of the new product that is the target of demand forecasting; a second acquisition process for acquiring first similar product information representing sales performance of the first similar product selected based on at least one element of the scale of the promotion, the characteristics of the product, and the sales method; a third acquisition process for acquiring second similar product information representing sales performance of second similar products selected based on the product category; a prediction process for predicting sales for a predetermined period including a period after a promotion period for the new product based on the new product information, the first similar product information, and the second similar product information; New product demand forecasting methods, including:

9. A program for causing a computer to function as a new product demand forecasting device, the program comprising: a first acquisition means for acquiring new product information including at least information regarding promotion of the new product that is the target of demand forecasting; a second acquiring means for acquiring first similar product information representing sales performance of the first similar product selected based on at least one element of the scale of the promotion, the characteristics of the product, and the sales method; a third acquiring means for acquiring second similar product information representing sales performance of second similar products selected based on the product category; a forecasting means for forecasting sales for a predetermined period including a period after a promotion period for the new product based on the new product information, the first similar product information, and the second similar product information; A new product demand forecasting program to function as a

Images