JP2024066788A - Information processing system, computer program, and information processing method - Google Patents

Abstract

To provide a technology capable of outputting a contribution degree of a plurality of factors related to sales results.SOLUTION: The value of at least one index about a sales activity plan of products in a store is acquired as a plan value of a first index (S120). The value of at least one index about sales activity results of the products in the store is acquired as a record value of a second index (S140). Contribution degrees of the first index and the second index to the record results are calculated on the basis of the plan value and the result values (S170). The calculated contribution degrees of the first index and the second index are outputted (S180).SELECTED DRAWING: Figure 2

Description

This disclosure relates to an information processing system, a computer program, and an information processing method.

A system for finding methods that contribute to increasing product sales in retail stores is known (see Patent Document 1). In the conventional system, the degree of influence of each item on sales, specifically the standardized partial regression coefficient, is calculated based on the actual measured values of multiple items, such as the product's shelf position, number of faces, and POP status, and the sales amount.

JP 2003-337885 A

The display status of a product in a store is influenced by the sales activity plan for that product. Therefore, there is room for improvement in the conventional method of evaluating the influence of multiple factors on sales based simply on the relationship between the display status and sales that is actually measured.

Therefore, according to one aspect of the present disclosure, it is desirable to provide a new technology that can output the contribution of multiple factors related to sales results to sales results as information useful for improving sales activities.

According to one aspect of the present disclosure, an information processing system is provided. The information processing system includes a first acquisition unit, a second acquisition unit, a calculation unit, and an output unit. The first acquisition unit is configured to acquire the value of at least one index related to a sales activity plan for a product in a store as a planned value of a first index.

The second acquisition unit is configured to acquire the value of at least one index related to the sales activity performance of the product in the store as a performance value of the second index. The calculation unit is configured to calculate the contribution of the first index and the second index to the sales performance of the product based on the planned value and the performance value. The output unit is configured to output the calculated contribution of the first index and the second index.

According to one aspect of the present disclosure, the information processing system can output the degree of contribution to sales results of multiple indicators corresponding to plans and results related to product sales activities. Based on this information on the degree of contribution, the user can consider improvements to store operations, including improvements to the plan itself.

Therefore, according to one aspect of the present disclosure, it is possible to provide an information processing system capable of outputting the contribution of multiple factors related to sales results as information useful for improving sales activities.

According to one aspect of the present disclosure, the sales activity plan may include a plan regarding product display. The first acquisition unit may acquire the value of at least one indicator including an indicator regarding product display in the sales activity plan as a planned value of the first indicator. The second acquisition unit may acquire the value of at least one indicator regarding product display performance as a performance value of the second indicator.

According to one aspect of the present disclosure, the calculation unit may calculate the contribution rate through construction of a regression model having the first index and the second index as explanatory variables and the sales performance as a response variable. According to one aspect of the present disclosure, the calculation unit may calculate the Shapley values of the first index and the second index using the regression model.

By treating the first indicator related to the sales activity plan and the second indicator related to performance as variables that explain sales results and constructing a regression model, the contribution of these indicators to sales results can be appropriately calculated.

According to one aspect of the present disclosure, the information processing system may further include a third acquisition unit. The third acquisition unit may be configured to acquire the value of at least one index related to the sales environment of the product as an environmental value of the third index.

The calculation unit may calculate the contribution of each of the first index, the second index, and the third index to the sales result based on the planned value, the performance value, and the environmental value. The output unit may output the calculated contribution of the first index, the second index, and the third index.

The sales environment can also affect sales results. Therefore, an information processing system that outputs the degree of contribution including indicators related to the sales environment can be of great help in improving store operations.

According to one aspect of the present disclosure, the third indicator may include at least one of an indicator related to the weather around the store, an indicator related to the traffic volume around the store, and an indicator related to the spatial characteristics within the store.

According to one aspect of the present disclosure, the calculation unit may calculate the contribution degree through constructing a regression model having the first index, the second index, and the third index as explanatory variables and the sales performance as a response variable. According to one aspect of the present disclosure, the calculation unit may calculate the contribution degree by calculating the Shapley values of the first index, the second index, and the third index using the regression model.

According to one aspect of the present disclosure, the first index may include an index related to the product's shelf placement plan. The second index may include an index related to the product's shelf placement performance. By employing such indexes, the user can consider whether to prioritize improvement of the product placement plan or the realization level based on the output contribution level.

According to one aspect of the present disclosure, the output unit may output the contribution degree by displaying it on a display. The contribution degrees of the first index and the second index may be displayed side by side on the display. By displaying the first and second indexes side by side, it is possible to display information that is visually easy for the user to understand and is useful for improving the store.

According to one aspect of the present disclosure, the output unit may output the contribution rate to a simulator that simulates product sales based on the contribution rate. Using the simulator, a user can learn in detail how sales activity plans and results affect sales results.

According to one aspect of the present disclosure, a computer program may be provided. The computer program may be a computer program for causing a computer to realize the functions of at least a part of the first acquisition unit, the second acquisition unit, the calculation unit, and the output unit in the information processing system described above.

According to one aspect of the present disclosure, the computer program may be provided by being recorded on a computer-readable recording medium. According to one aspect of the present disclosure, an information processing method corresponding to the above-described information processing system may be provided.

According to one aspect of the present disclosure, an information processing method executed by a computer may be provided. The information processing method may include obtaining a value of at least one indicator related to a sales activity plan for a product in a store as a planned value of a first indicator.

The information processing method may further include acquiring the value of at least one index related to the sales activity performance of the product in the store as a performance value of the second index. The information processing method may further include calculating the contribution of the first index and the second index to the sales result based on the planned value and the performance value.

The information processing method may further include outputting the calculated contributions of the first index and the second index. According to this information processing method, it is possible to obtain the same effect as the information processing system described above.

FIG. 1 is a block diagram showing a configuration of an information processing system. 11 is a flowchart showing an analysis process executed by a processor. FIG. 13 is a diagram showing an example of a contribution degree explanation screen. FIG. 4A is a diagram showing an example of a table of first indices, and FIG. 4B is a diagram showing an example of a table of second indices. FIG. 2 is an explanatory diagram of a simulator.

Exemplary embodiments of the present disclosure will now be described with reference to the drawings.
The information processing system 1 of the present embodiment is configured by installing a computer program specific to the present embodiment in a general-purpose computer system. The information processing system 1 shown in Fig. 1 includes a processor 11, a memory 12, a storage 13, a display 15, an input device 17, a media reader/writer 18, and a communication device 19.

The processor 11 is configured to execute processing in accordance with a computer program stored in the storage 13. The memory 12 includes a RAM. The memory 12 is used as a working area when the processor 11 executes processing in accordance with the computer program. The memory 12 temporarily stores the computer program and data read from the storage 13.

Storage 13 stores computer programs and various data. One of the computer programs stored in storage 13 includes a computer program for calculating the contribution of sales activity plans and results to sales results based on plans for product sales activities in the store and results of product sales activities in the store, in particular the degree of realization of the plans and sales results. Examples of storage 13 include hard disk drives and solid state drives.

The display 15 is configured to display various information to the user. The display 15 is, for example, a liquid crystal display. The input device 17 is configured to input operation signals from the user to the processor 11. The input device 17 includes a keyboard and a pointing device that can be operated by the user.

The media reader/writer 18 is configured to be capable of reading information recorded on a recording medium such as a memory card and to be capable of writing new information to the recording medium. The communication device 19 is configured to be controlled by the processor 11 and to communicate with external devices within the local area network and/or the wide area network.

When a command to execute an analysis process is input by the user via the input device 17, the processor 11 executes the analysis process shown in FIG. 2 according to a computer program. The analysis process is a process for calculating the contribution of multiple factors that affect sales results to sales results.

Examples of sales performance include sales volume. Examples of sales volume include sales volume calculated in units or value, i.e., number of units sold or revenue. In the analysis process described below, the contribution of multiple factors to revenue is calculated.

When the analysis process starts, the processor 11 acquires the plan data (S110). The processor 11 can acquire the plan data by reading the plan data recorded in the storage 13.

According to this embodiment, a sales activity plan, which is a plan for product sales activities, is formulated for multiple stores (hereinafter referred to as target stores). Hereinafter, the sales activity plan will be simply referred to as a sales plan. Plan data explaining the formulated sales plan can be generated by a user and recorded in storage 13.

The plan data describes one or more sales plans. Each of the sales plans is applied to one or more of a plurality of target stores. One of the one or more sales plans is applied to each of the target stores. Each of the sales plans includes a plan for product display, which is one of the sales activities. In each target store, product sales activities, including product display, are carried out based on the applied sales plan.

The product display plan includes a display plan for a specific product group on a product shelf for a specific category (hereinafter referred to as "category shelf"). The category in this case refers to product categories such as cosmetics, hair wash, cold medicine, etc.

The specific product group is a product group in a specific category sold by the company that desires the analysis results (hereinafter referred to as the "target company"). The display plan includes a plan regarding the placement of products on category shelves, in other words, the product layout.

Based on the acquired planning data, the processor 11 calculates the values of multiple first indicators for each sales plan with respect to one or more sales plans (S120). Through this calculation, the processor 11 obtains the values of multiple first indicators. The multiple first indicators represent the characteristics of the sales plan. Hereinafter, the value of the first indicator is also referred to as the planned value.

For example, in the final stage of the analysis process, in order to display the contribution explanation screen shown in FIG. 3 on the display 15, the processor 11 calculates, for each sales plan, the SKU share, SKU composition, face share, display position score, and product appeal value for a specific product group in the corresponding sales plan as planned values.

The SKU share is an indicator that expresses the proportion of the target company's products displayed on category shelves as a percentage in the sales plan. In other words, the SKU share corresponds to the value obtained by dividing the "number of the target company's products on the category shelves" by the "total number of products on the category shelves." The number of products here is expressed in SKUs (Stock Keeping Units). In other words, the number of products, more specifically, is the number of product types.

The SKU composition is an indicator that expresses, as a percentage, the proportion of products that belong to the top-selling product groups within a group of similar stores among the group of products that are planned to be displayed in the store. A similar store group here refers to a group of stores that have similar display plans and/or sales records. The SKU composition corresponds to the value obtained by dividing the "number of products in the top-selling product groups of category shelf display products included in the display plan" by the "number of products displayed on category shelves based on the display plan."

A similar store group refers to a group of stores to which a single sales plan is applied, or a group of stores where the similarity based on the displayed products in the display plan exceeds a certain threshold. The products in the top-selling product group are the products with the highest sales determined by the sales aggregation of the similar store group. The products in the top-selling product group correspond to a group of products from the product with the highest sales to a specified rank.

Face share is the ratio of the number of faces for a specific product group on a planned category shelf to the total number of faces on the category shelf, i.e., the "number of faces for a specific product group" divided by the "total number of faces," and is an indicator expressed as a percentage.

The display position score corresponds to the total score of the sections in which a specific product group is displayed when a category shelf is divided into multiple sections and a score is defined for each section. The score is defined so that a section in which products are likely to be noticed by consumers, or a section that contributes relatively to sales based on sales performance on the category shelf, is given a higher score than other sections.

Product appeal is an index that expresses, as a percentage, the proportion of the target company's products among the products for which promotional activities are conducted on category shelves. To calculate product appeal, data can be prepared that not only indicates the necessity of promotional activities for each of the target company's specific products, but also describes the schedule of promotional activities of other companies other than the target company. The planning data may include information that describes this schedule.

Above, SKU share, SKU composition, face share, display position score, and product appeal were given as examples of first indicators, but other indicators that represent the characteristics of the sales plan may also be used as the first indicator.

Next, the processor 11 acquires transaction data regarding purchasing activities for each of the target stores for the multiple target stores, and further acquires status data for each of the surveyed stores for the multiple surveyed stores (S130). The transaction data may be, for example, POS (Point Of Sales) data.

Transaction data for each target store is obtained, for example, from a point-of-sale management system and stored in storage 13. The transaction data for each target store includes sales records of products at the corresponding store, and is data that allows the sales of a specific product group at the corresponding store to be aggregated. Processor 11 can obtain the transaction data for each target store from storage 13.

The multiple surveyed stores are the stores among the multiple target stores that are visited and surveyed by investigators. When an all-store survey is conducted, the multiple target stores and the multiple surveyed stores are the same set of stores. In what follows, each of the multiple target stores other than the surveyed stores will be referred to as an unsurveyed store.

The status data for each surveyed store describes the status of product display in the corresponding store. For example, for each surveyed store, the product display status of the category shelves in the corresponding store is visually determined by an investigator upon visiting the store, and survey record data describing the product display status is created by the investigator operating an information terminal. Alternatively, based on image data of the category shelves captured by a photographic device such as a camera carried by the investigator, survey record data describing the product display status is created by the investigator operating an information terminal.

The created survey record data is imported into the information processing system 1 from the surveyor's information terminal, for example, via the communication device 19, and is recorded as status data in the storage 13. The processor 11 can obtain the status data for each surveyed store from the storage 13.

If the multiple target stores include unsurveyed stores, the processor 11 generates status data for each unsurveyed store using loss completion techniques based on the transaction data of the multiple target stores and the status data of the multiple surveyed stores (S135).

For example, the processor 11 can generate a model that estimates the product display status from the transaction data based on the transaction data and status data of multiple surveyed stores, and generate status data for each unsurveyed store by inputting the transaction data of each unsurveyed store into the model.

The model may be generated by machine learning using transaction data and status data from multiple surveyed stores as training data. Characteristic data such as the size and location of each target store may be obtained along with the transaction data and used to generate the model.

Next, in S140, the processor 11 calculates, for each of the multiple target stores, the values of multiple second indicators based on the status data of the corresponding store and the plan data of the corresponding store. Through this calculation, the processor 11 obtains the values of multiple second indicators.

The multiple second indicators are indicators related to the results of sales activities, specifically, indicators related to the results and performance of the execution of the sales plan applied to the corresponding store. The multiple second indicators include an indicator related to the degree of realization of the sales plan during the period in which sales activities based on the sales plan were carried out. The second indicators include an indicator that indicates the degree of realization of the plan related to product display as the display performance. Hereinafter, the value of the second indicator is also referred to as the performance value. The period in which sales activities based on the sales plan were carried out is referred to as the implementation period.

Specifically, in the final stage of the analysis process, in order to display the contribution explanation screen shown in FIG. 3 on the display 15, the processor 11 calculates the product assortment realization rate, face realization rate, display position realization rate, sales promotion realization rate, and out-of-stock rate as performance values for each target store.

The product lineup realization rate is an indicator that expresses, as a percentage, the proportion of products that were planned to be displayed in the sales plan that were displayed on category shelves as planned. For example, the product lineup realization rate corresponds to the number of products that were actually displayed in a specific product group that was planned to be displayed divided by the number of products that were planned to be displayed. The number of products is counted in SKU units as described above.

The face realization rate is an index that represents the realization rate of the number of faces for a specific product group that was planned in the sales plan. Specifically, the face realization rate corresponds to the value obtained by dividing the number of faces for a specific product group that was realized on a category shelf by the number of faces that was planned.

The display position realization rate is an index that represents the realization rate of the display position score. Specifically, the display position realization rate refers to the percentage of products whose actual product placement was appropriate or estimated to be appropriate compared to the planned product placement out of the number of products planned for display on category shelves.

The promotion realization rate is an index that expresses, as a percentage, the proportion of a specific product group of the target company for which promotional activities were actually carried out in the store among the product groups for which promotional activities were planned in the sales plan. For example, the proportion of POP (point of purchase advertising) advertisements that were planned to be placed on category shelves and were actually placed corresponds to the promotion realization rate.

The out-of-stock rate is an indicator that expresses, as a percentage, the proportion of products that are out of stock among the products planned for display in the sales plan and displayed on category shelves for a specific product group of the target company.

Next, in S150, the processor 11 acquires sales environment data. The sales environment data includes weather data and traffic data for the area in which the target store group is located.

The weather data may include future weather information in addition to weather information observed during the implementation period of the sales plan. Future here means later in time with respect to the implementation period, and does not mean future with respect to the timing of execution of the analysis process. However, future weather information may include weather forecast information for a time period later than the timing of execution of the analysis process. The weather data may include weather information from the past than the implementation period.

The traffic data describes the traffic volume observed during the implementation period in the area in which the target store group is located. Traffic volume here should be interpreted broadly and includes, for example, the volume of vehicles traveling on roads as well as the volume and flow of people passing by. The traffic data can be data describing not only the traffic volume observed during the implementation period, but also future traffic volume after the implementation period ends, and past traffic volume before the implementation period begins.

The sales environment data may further include, for each target store, spatial characteristic data describing the spatial characteristics of the corresponding store. The spatial characteristic data may include information describing the layout of product shelves of multiple categories, including product shelves of a specific category, in the corresponding store, and/or information describing the product categories of product shelves adjacent to product shelves of a specific category.

The sales environment data may be recorded in advance in storage 13. Processor 11 may acquire the sales environment data recorded in storage 13. Alternatively, processor 11 may acquire the sales environment data from an external device via communication.

For example, weather data for the area in which the target store group is located may be obtained from an external server that provides weather data. Traffic data for the area in which the target store group is located may be obtained from an external server that provides traffic data.

In the next step S160, processor 11 calculates the values of multiple third indicators for each of the multiple target stores based on the sales environment data. Through this calculation, processor 11 obtains the values of multiple third indicators. Hereinafter, the value of the third indicator is also referred to as an environmental value. The multiple third indicators are indicators related to the sales environment of the corresponding store, and include an indicator related to weather, an indicator related to traffic volume, and an indicator related to the spatial characteristics of the store.

The multiple third indicators may include one or more of the average temperature, maximum temperature, minimum temperature, average humidity, maximum humidity, minimum humidity, percentage of sunny days, percentage of rainy days, and average sunshine hours per unit time during the implementation period and before and after the implementation period as indicators related to the weather around the corresponding store. The unit time may be any length of time, such as one day, one week, two weeks, or one month. However, the weather indicators to be calculated are not limited to these.

The multiple third indicators may include, as indicators related to traffic, indicators representing the volume of vehicle and pedestrian traffic in the area in which the corresponding store is located per unit time during the implementation period and before and after the implementation period. The multiple third indicators may include, as indicators related to the spatial characteristics of the store, indicators representing the characteristics related to the layout of shelves for multiple categories of products in the corresponding store.

In the next step S170, the processor 11 uses a plurality of first indices X1[1], X1[2], ..., X1[M1], a plurality of second indices X2[1], X2[2], ..., X2[M2], and a plurality of third indices X3[1], X3[2], ..., X3[M3] as explanatory variables, and uses store sales during the implementation period Y as an objective variable, and constructs a regression model that explains the relationship between the explanatory variables X1[1], X1[2], ..., X1[M1], X2[1], X2[2], ..., X2[M2], X3[1], X3[2], ..., X3[M3] and the objective variable Y by regression analysis. Here, M1 is the number of first indices, M2 is the number of second indices, and M3 is the number of third indices.

The regression model is, for example, a linear regression model, and is expressed by the regression equation Y = K1.X1 + K2.X2 + K3.X3 = K1[1].X1[1] + K1[2].X1[2] + ... + K1[M1].X1[M1] + K2[1].X2[1] + K2[1].X2[2] + ... + K2[M2].X2[M2] + K3[1].X3[1] + K3[2].X3[2] + ... + K3[M3].X3[M3].

Vector X1 is the vector representation of the first index, X1 = (X1[1], X1[2], ..., X1[M1]). Vector X2 is the vector representation of the second index, X2 = (X2[1], X2[2], ..., X2[M2]). Vector X3 is the vector representation of the third index, X3 = (X3[1], X3[2], ..., X3[M3]).

Vector K1 is a vector representation K1 = (K1[1], K1[2], ..., K1[M1]) of the regression coefficients acting on vector X1. Vector K2 is a vector representation K2 = (K2[1], K2[2], ..., K2[M2]) of the regression coefficients acting on vector X2. Vector K3 is a vector representation K3 = (K3[1], K3[2], ..., K3[M3]) of the regression coefficients acting on vector X3.

To construct a regression model, the processor 11 generates training data for each target store that compiles the values of the indicators and sales corresponding to the explanatory variables and the objective variables. Each training data is data that compiles the values of the first indicators X1[1], X1[2], ..., X1[M1] according to the sales plan of the corresponding store, the values of the second indicators X2[1], X2[2], ..., X2[M2] of the corresponding store, the values of the third indicators X3[1], X3[2], ..., X3[M3] of the corresponding store, and the sales Y of the corresponding store. Sales Y is determined from the transaction data of the corresponding store. Sales Y is the sales result of the corresponding store, and may be, for example, the sales during the implementation period of the sales plan at the corresponding store.

Processor 11 executes regression analysis using a set of training data from multiple target stores. This calculates the optimal value of the regression coefficient K = (K1[1], K1[2], ..., K1[M1], K2[1], K2[2], ..., K2[M2], K3[1], K3[2], ..., K3[M3]) in the regression model described above. The optimal value is calculated, for example, using the least squares method to search for the regression coefficient that minimizes the sum of squared errors related to the error of the training data from the regression equation.

In regression analysis, explanatory variables and target variables can be standardized. Indicators and sales values used as training data can be standardized. This allows the calculation of a standardized partial regression coefficient K, which takes a value in the range from 0 to 1.

In the next step S180, the processor 11 determines the contribution of the corresponding indicator to sales Y to each of the regression coefficients K1[1], K1[2], ..., K1[M1], K2[1], K2[2], ..., K2[M2], K3[1], K3[2], ..., K3[M3] corresponding to the explanatory variables X1[1], X1[2], ..., X1[M1], X2[1], X2[2], ..., X2[M2], X3[1], X3[2], ..., X3[M3], and displays a contribution explanation screen on the display 15 that explains the contribution of each indicator to sales.

As shown in FIG. 3, the contribution explanation screen displays the contribution of each of the first indicators, SKU share, SKU composition, face share, display position score, and product appeal, using numerical values and bar graphs with lengths corresponding to the numerical values.

The contribution explanation screen further displays the contribution of each of the second indicators, product lineup realization rate, face realization rate, display position realization rate, sales promotion realization rate, and out-of-stock rate, as a numerical value and a bar graph of a length corresponding to the numerical value. The contribution explanation screen further displays the contribution of each of the third indicators, weather, traffic volume, and spatial characteristics of the store, as a numerical value and a bar graph of a length corresponding to the numerical value.

What is noteworthy here is that the contribution explanation screen displays the contribution of the sales plan indicators related to "product lineup," "face share," "display position," and "sales promotion activities" in parallel with the contribution of the indicator for plan realization.

Specifically, the contribution degree of SKU share, which is an index related to the product lineup, and the contribution degree of product lineup realization rate are displayed in parallel on the contribution degree explanation screen. Similarly, the contribution degree of face share, which is an index related to face, and the face realization rate are displayed in parallel on the contribution degree explanation screen.

The display position score, which is an index related to the display position, and the display position realization rate are displayed side by side. The product appeal, which is an index related to sales promotion activities, and the promotion realization rate are displayed side by side.

This side-by-side display allows the user to easily compare the contribution between the plan and the realization rate. Therefore, based on the contribution displayed on the contribution explanation screen, the user can easily understand whether the priority should be given to improving the sales plan itself or to improving the plan realization rate.

In this way, according to this embodiment, the contribution degree explanation screen displays the contribution degrees of the plan and the indicators related to the realization rate in parallel, making it possible to improve product sales activities more efficiently.

In S180, the processor 11 may cause the display 15 to display, in addition to the contribution explanation screen shown in FIG. 3, a table explaining the planned values and performance values used in calculating the contribution.

For example, as shown in FIG. 4A, a table that lists the planned values of the first indicator in the corresponding sales plan for each sales plan may be displayed on the display 15. As shown in FIG. 4B, a table that lists the performance values of the second indicator relating to the realization degree of the sales plan applied to the corresponding store for each target store may be displayed on the display 15.

In S180, the processor 11 may record data describing the regression coefficients K1[1], K1[2], ..., K1[M1], K2[1], K2[2], ..., K2[M2], K3[1], K3[2], ..., K3[M3] in the storage 13 as contribution data. In S180, the processor 11 may execute the screen display and data output in this manner, and terminate the analysis process.

In addition, the information processing system 1 may have a computer program in the storage 13 for causing the processor 11 to execute a function as a simulator. The processor 11 may function as a simulator by executing the computer program based on an input from a user inputted through the input device 17.

The simulator can be configured to predict sales Y based on the input value X1 of the first index, the input value X2 of the second index, and the input value X3 of the third index, using a regression model defined by the regression equation Y = K1.X1 + K2.X2 + K3.X3, as shown in FIG. 5. The simulator can simulate sales of a specific product group in the form of a sales forecast, based on the regression model.

Using this simulator, users can obtain store sales forecasts based on sales plans, the degree to which the targeted plans are being achieved, and the expected sales environment, and can obtain information from the simulator that is useful for improving sales activities.

[Other embodiments]
The present disclosure is not limited to the above embodiment, and various aspects may be adopted. For example, in the above embodiment, the regression model is constructed by performing a linear regression analysis based on a set of teacher data, but the regression model may be constructed based on other algorithms.

For example, as a method for constructing a regression model using a machine learning algorithm, a method for constructing a regression model using gradient boosting or a method for constructing a regression model using support vector regression may be adopted.

In addition, in the above embodiment, the regression coefficient of the regression model is used as the contribution degree, but for example, the Shapley value may be used as the contribution degree. That is, in S170, the processor 11 may calculate the Shapley values of the first index, the second index, and the third index based on the constructed regression model, and use the Shapley values as the contribution degree. On the contribution degree explanation screen, the Shapley value of the corresponding index may be displayed as the contribution degree of each index.

The Shapley value corresponds to a value calculated by using, for example, a regression model obtained by a machine learning algorithm as an explanatory model, and calculating how much the value of the objective variable increases on average in response to changes in each explanatory variable. Therefore, the Shapley value indicates the degree of contribution of the corresponding explanatory variable to the objective variable.

In S170, for example, the processor 11 uses a machine learning algorithm to learn a regression model having a plurality of first indices X1[1], X1[2], ..., X1[M1], a plurality of second indices X2[1], X2[2], ..., X2[M2], and a plurality of third indices X3[1], X3[2], ..., X3[M3] as explanatory variables, and store sales Y during the implementation period as a response variable, using the set of training data from the plurality of target stores described above, thereby constructing a regression model (S171).

Then, processor 11 can use the constructed regression model as an explanatory model and calculate the Shapley value of each index using a set of training data. Processor 11 can calculate each Shapley value as a contribution by rescaling each Shapley value so that the sum of the Shapley values across all of the multiple indexes is 100 (S175).

In addition, other explanatory variables may be introduced into the regression model. For example, an index representing price advantage may be adopted as an explanatory variable. Then, the contribution of price advantage to sales Y may be displayed on the contribution explanation screen.

Price advantage is expressed as the competitor's average selling price for a product group in a specific category divided by the target company's average selling price for that product group. In other words, price advantage is the ratio of the competitor's average selling price to the target company's average selling price for a product group in a specific category. The higher the competitor's average selling price is than the target company's average selling price, the greater the price advantage.

The functions of one component in the above embodiments may be distributed among multiple components. The functions of multiple components may be integrated into one component. Part of the configuration of the above embodiments may be omitted. At least part of the configuration of the above embodiments may be added to or substituted for the configuration of another of the above embodiments. All aspects included in the technical ideas identified from the wording of the claims are embodiments of the present disclosure.

[Technical idea disclosed in this specification]
It can be understood that the present specification discloses the following technical ideas.
[Item 1]
a first acquisition unit configured to acquire a value of at least one index related to a sales activity plan for a product in a store as a planned value of a first index;
a second acquisition unit configured to acquire a value of at least one index related to sales activity performance of the product in the store as a performance value of a second index;
a calculation unit configured to calculate a contribution of the first index and the second index to a sales result of the product based on the planned value and the performance value;
an output unit configured to output the calculated contribution degree of the first index and the second index;
An information processing system comprising:
[Item 2]
The sales activity plan includes a plan regarding the display of the merchandise,
The first acquisition unit acquires a value of at least one index including an index related to the display of the products in the sales activity plan as a planned value of the first index;
2. The information processing system according to item 1, wherein the second acquisition unit acquires a value of at least one index related to the display performance of the product as a performance value of the second index.
[Item 3]
3. The information processing system according to item 1 or 2, wherein the calculation unit calculates the contribution degree through construction of a regression model having the first index and the second index as explanatory variables and the sales performance as a response variable.
[Item 4]
4. The information processing system according to item 3, wherein the calculation unit calculates the contribution degree by calculating Shapley values of the first index and the second index using the regression model.
[Item 5]
a third acquisition unit configured to acquire a value of at least one index related to the sales environment of the product as an environment value of a third index,
the calculation unit calculates a contribution degree of each of the first index, the second index, and the third index to the sales result based on the plan value, the performance value, and the environment value;
3. The information processing system according to item 1 or 2, wherein the output unit outputs the calculated contribution degrees of the first index, the second index, and the third index.
[Item 6]
6. The information processing system according to item 5, wherein the third indicator includes at least one of an indicator related to weather in the vicinity of the store, an indicator related to traffic volume in the vicinity of the store, and an indicator related to spatial characteristics within the store.
[Item 7]
7. The information processing system according to item 5 or 6, wherein the calculation unit calculates the contribution degree through construction of a regression model having the first index, the second index, and the third index as explanatory variables and the sales performance as a response variable.
[Item 8]
8. The information processing system according to item 7, wherein the calculation unit calculates the contribution degree by calculating Shapley values of the first index, the second index, and the third index using the regression model.
[Item 9]
The first index includes an index regarding a layout plan of the product on a product shelf,
The information processing system according to any one of items 1 to 8, wherein the second indicator includes an indicator regarding the placement performance of the product on the product shelf.
[Item 10]
10. The information processing system according to any one of items 1 to 9, wherein the output unit outputs the contribution degree by displaying it on a display, and the contribution degrees of the first index and the second index are displayed side by side on the display.
[Item 11]
11. The information processing system according to any one of items 1 to 10, wherein the output unit outputs the degree of contribution to a simulator that simulates sales of the product based on the degree of contribution.
[Item 12]
12. A computer program for causing a computer to realize functions as the first acquisition unit, the second acquisition unit, the calculation unit, and the output unit in the information processing system according to any one of items 1 to 11.
[Item 13]
1. A computer-implemented information processing method, comprising:
acquiring a value of at least one index related to a sales activity plan for the product in the store as a planned value of a first index;
acquiring a value of at least one index related to sales activity performance of the product in the store as a performance value of a second index;
Calculating the contribution of the first index and the second index to sales results based on the planned value and the performance value;
outputting the calculated contribution degrees of the first index and the second index;
An information processing method comprising:

1...information processing system, 11...processor, 12...memory, 13...storage, 15...display, 17...input device, 18...media reader/writer, 19...communication device.

Claims (13)

a first acquisition unit configured to acquire a value of at least one index related to a sales activity plan for a product in a store as a planned value of a first index;
a second acquisition unit configured to acquire a value of at least one index related to sales activity performance of the product in the store as a performance value of a second index;
a calculation unit configured to calculate a contribution of the first index and the second index to a sales result of the product based on the planned value and the performance value;
an output unit configured to output the calculated contribution degree of the first index and the second index;
An information processing system comprising: The sales activity plan includes a plan regarding the display of the merchandise,
The first acquisition unit acquires a value of at least one index including an index related to the display of the products in the sales activity plan as a planned value of the first index;
The information processing system according to claim 1 , wherein the second acquisition unit acquires a value of at least one index relating to the display performance of the product as a performance value of the second index. The information processing system of claim 1, wherein the calculation unit calculates the contribution rate by constructing a regression model having the first index and the second index as explanatory variables and the sales performance as a response variable. The information processing system of claim 3, wherein the calculation unit calculates the contribution degree by calculating Shapley values of the first index and the second index using the regression model. a third acquisition unit configured to acquire a value of at least one index related to the sales environment of the product as an environment value of a third index,
the calculation unit calculates a contribution degree of each of the first index, the second index, and the third index to the sales result based on the plan value, the performance value, and the environment value;
The information processing system according to claim 1 , wherein the output unit outputs the calculated contribution degrees of the first index, the second index, and the third index. The information processing system according to claim 5, wherein the third indicator includes at least one of an indicator related to the weather around the store, an indicator related to the traffic volume around the store, and an indicator related to the spatial characteristics within the store. The information processing system of claim 5, wherein the calculation unit calculates the contribution rate by constructing a regression model having the first index, the second index, and the third index as explanatory variables and the sales performance as a response variable. The information processing system of claim 7, wherein the calculation unit calculates the contribution degree by calculating Shapley values of the first index, the second index, and the third index using the regression model. The first index includes an index regarding a layout plan of the product on a product shelf,
The information processing system according to claim 1 , wherein the second indicator includes an indicator relating to a placement performance of the product on the product shelf. The information processing system according to claim 1, wherein the output unit outputs the degree of contribution by displaying it through a display, and the degree of contribution of each of the first index and the second index is displayed side by side on the display. The information processing system according to claim 1, wherein the output unit outputs the contribution rate to a simulator that simulates sales of the product based on the contribution rate. A computer program for causing a computer to realize the functions of the first acquisition unit, the second acquisition unit, the calculation unit, and the output unit in the information processing system according to any one of claims 1 to 11. 1. A computer-implemented information processing method, comprising:
acquiring a value of at least one index related to a sales activity plan for the product in the store as a planned value of a first index;
acquiring a value of at least one index related to sales activity performance of the product in the store as a performance value of a second index;
Calculating the contribution of the first index and the second index to sales results based on the planned value and the performance value;
outputting the calculated contribution degrees of the first index and the second index;
An information processing method comprising:

Images